文献目录

[1] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine Susstrunk. SLIC 超像素与现有超像素方法的比较 (SLIC Superpixels Compared to State-of-the-Art Superpixel Methods). IEEE Trans. Pattern Anal. Mach. Intell., 34(11):2274–2282, 2012年11月。

[3] A. Aggarwal, J. Chang, and Chee K. Yap. 外接多边形的最小面积 (Minimum area circumscribing Polygons). The Visual Computer, 7:112–117, 1985。

[3] Motilal Agrawal, Kurt Konolige, and Morten Rufus Blas. Censure：用于实时特征检测与匹配的中心环绕极值 (Censure: Center surround extremas for realtime feature detection and matching)。收录于 Computer Vision–ECCV 2008, 第 102–115 页。Springer, 2008。

[4] Timo Ahonen, Abdenour Hadid, and Matti Pietikäinen. 基于局部二进制模式的人脸识别 (Face recognition with local binary patterns)。收录于 Computer vision-eccv 2004, 第 469–481 页。Springer, 2004。

[5] Cuneyt Akinlar and Cihan Topal. EDLines：一种带有错误检测控制的实时线段检测器 (EDLines: A real-time line segment detector with a false detection control)。Pattern Recognition Letters, 32(13):1633–1642, 2011。

[6] Cuneyt Akinlar and Cihan Topal. EDPF：一种带有错误检测控制的实时无参数边缘段检测器 (EDPF: a real-time parameter-free edge segment detector with a false detection control)。International Journal of Pattern Recognition and Artificial Intelligence, 26(01):1255002, 2012。

[7] Cuneyt Akinlar and Cihan Topal. EDCircles：一种带有错误检测控制的实时圆检测器 (EDCircles: A real-time circle detector with a false detection control)。Pattern Recognition, 46(3):725–740, 2013。

[8] Cuneyt Akinlar and Cihan Topal. ColorED：通过边缘绘图（ED）进行的彩色边缘和段检测 (ColorED: Color edge and segment detection by Edge Drawing (ED))。Journal of Visual Communication and Image Representation, 44:82-94, 2017。

[9] Yagiz Aksoy, Tunc Ozan Aydin, and Marc Pollefeys. 为自然图像抠图设计有效的像素间信息流 (Designing effective inter-pixel information flow for natural image matting)。收录于 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 第 29–37 页, 2017。

[10] Alexandre Alahi, Raphael Ortiz, and Pierre Vandergheynst. Freak：快速视网膜关键点 (Freak: Fast retina keypoint)。收录于 Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, 第 510–517 页, 2012。

[11] Pablo Fernández Alcantarilla, Adrien Bartoli, and Andrew J Davison. KAZE 特征 (KAZE features)。收录于 Computer Vision–ECCV 2012, 第 214–227 页。Springer, 2012。

[12] Pablo Fernández Alcantarilla, Jesús Nuevo, and Adrien Bartoli. 用于非线性尺度空间加速特征的快速显式扩散 (Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces)。BMVA Press, 2013。

[13] Stefano Allegretti, Federico Bolelli, and Costantino Grana. 用于在 GPU 上标记连通分量的优化块算法 (Optimized block-based algorithms to label connected components on GPUs)。IEEE Transactions on Parallel and Distributed Systems, 31(2):423–438, 2019。

[14] Nicolas Andreff, Radu Horaud, and Bernard Espiau. 在线手眼标定 (On-line Hand-eye Calibration)。收录于 Proceedings of the 2Nd International Conference on 3-D Digital Imaging and Modeling, 第 430–436 页。IEEE Computer Society, 1999。

[15] Relja Arandjelovic. 每个人都应该知道的改进目标检索的三件事 (Three Things Everyone Should Know to Improve Object Retrieval)。收录于 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 第 2911–2918 页。IEEE Computer Society, 2012。

[16] David Arthur and Sergei Vassilvitskii. k-means++：仔细初始化种子的优势 (k-means++: The advantages of careful seeding)。收录于 Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms, 第 1027–1035 页。Society for Industrial and Applied Mathematics, 2007。

[17] Boris Babenko, Ming-Hsuan Yang, and Serge Belongie. 使用在线多示例学习的视觉跟踪 (Visual tracking with online multiple instance learning)。收录于 Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, 第 983–990 页, 2009。

[18] Dana H Ballard. 推广霍夫变换以检测任意形状 (Generalizing the Hough transform to detect arbitrary shapes)。Pattern recognition, 13(2):111–122, 1981。

[19] Daniel Barath and Jiri Matas. 图割 RANSAC (Graph-Cut RANSAC)。收录于 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018年6月。

[20] Daniel Barath, Maksym Ivashechkin, and Jiri Matas. 渐进式 NAPSAC：从逐渐增长的邻域中采样 (Progressive NAPSAC: sampling from gradually growing neighborhoods)。2019。

[21] Daniel Barath, Jana Noskova, Maksym Ivashechkin, and Jiri Matas. MAGSAC++，一种快速、可靠且准确的鲁棒估计器 (MAGSAC++, a Fast, Reliable and Accurate Robust Estimator)。收录于 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020年6月。

[22] Jonathan T Barron and Ben Poole. 快速双边求解器 (The Fast Bilateral Solver)。收录于 European Conference on Computer Vision (ECCV), 第 617–632 页。Springer International Publishing, 2016。

[23] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool. Surf：加速鲁棒特征 (Surf: Speeded up robust features)。Computer Vision–ECCV 2006, 404–417, 2006。

[24] Asker M Bazen and Sabih H Gerez. 指纹方向场和奇异点计算的系统方法 (Systematic methods for the computation of the directional fields and singular points of fingerprints)。IEEE transactions on pattern analysis and machine intelligence, 24(7):905–919, 2002。

[25] Christian Beecks, Merih Seran Uysal, and Thomas Seidl. 签名二次型距离 (Signature Quadratic Form Distance)。收录于 CIVR, 第 438–445 页。ACM, 2010。

[26] Peter N. Belhumeur, João P Hespanha, and David Kriegman. 特征脸 vs. 费舍尔脸：使用特定类线性投影的识别 (Eigenfaces vs. fisherfaces: Recognition using class specific linear projection)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 19(7):711–720, 1997。

[27] Alexandre Benoit, Alice Caplier, Barthélémy Durette, and Jeanny Hérault. 使用人类视觉系统建模进行生物启发式底层图像处理 (Using human visual system modeling for bio-inspired low level image processing)。Computer vision and Image understanding, 114(7):758–773, 2010。

[28] L Berger, V A Raghunathan, C Launay, D Ausserré, and Y Gallot. 二维聚结：薄共聚物膜实验和数值模拟 (Coalescence in 2 dimensions: experiments on thin copolymer films and numerical simulations)。The European Physical Journal B - Condensed Matter and Complex Systems, 2(1):93-99, 1998。

[29] JiaWang Bian, Wen-Yan Lin, Yasuyuki Matsushita, Sai-Kit Yeung, Tan Dat Nguyen, and Ming-Ming Cheng. GMS：用于快速、超鲁棒特征对应的基于网格的运动统计 (GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence)。收录于 IEEE Conference on Computer Vision and Pattern Recognition, 2017。

[30] Lluis Gomez i Bigorda and Dimosthenis Karatzas. 一种用于多脚本和任意方向场景文本提取的快速分层方法 (A Fast Hierarchical Method for Multi-script and Arbitrary Oriented Scene Text Extraction)。CoRR, abs/1407.7504, 2014。

[31] Josef Bigun. 有方向的视觉 (Vision with direction)。Springer, 2006。

[32] Stan Birchfield and Carlo Tomasi. 一种对图像采样不敏感的像素差异度量 (A pixel dissimilarity measure that is insensitive to image sampling)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 20(4):401–406, 1998。

[33] Stan Birchfield and Carlo Tomasi. 通过像素对像素立体视觉实现深度不连续 (Depth discontinuities by pixel-to-pixel stereo)。International Journal of Computer Vision, 35(3):269–293, 1999。

[34] Jose-Luis Blanco. 关于 SE(3) 变换参数化和流形上优化的教程 (A tutorial on SE(3) transformation parameterizations and on-manifold optimization)。马拉加大学, 2010。

[35] Federico Bolelli, Michele Cancilla, and Costantino Grana. 两种加速连通分量标记算法的策略 (Two More Strategies to Speed Up Connected Components Labeling Algorithms)。收录于 Image Analysis and Processing - ICIAP 2017, 第 48–58 页。Springer, 2017。

[36] Federico Bolelli, Stefano Allegretti, Lorenzo Baraldi, and Costantino Grana. 意大利面条标记法：用于基于块的连通分量标记的有向无环图 (Spaghetti Labeling: Directed Acyclic Graphs for Block-Based Connected Components Labeling)。IEEE Transactions on Image Processing, 29(1):1999–2012, 2019。

[37] Federico Bolelli, Stefano Allegretti, and Costantino Grana. 统一的有向无环图 (One DAG to Rule Them All)。IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021。

[38] David S. Bolme, J. Ross Beveridge, Bruce A. Draper, and Man Lui Yui. 使用自适应相关滤波器的视觉目标跟踪 (Visual Object Tracking using Adaptive Correlation Filters)。收录于 Conference on Computer Vision and Pattern Recognition (CVPR), 2010。

[39] Gunilla Borgefors. 数字图像中的距离变换 (Distance transformations in digital images)。Computer vision, graphics, and image processing, 34(3):344–371, 1986。

[40] Léon Bottou. 使用随机梯度下降进行大规模机器学习 (Large-scale machine learning with stochastic gradient descent)。收录于 Proceedings of COMPSTAT’2010, 第 177–186 页。Springer, 2010。

[41] Jean-Yves Bouguet. Lucas Kanade 特征跟踪器的金字塔实现算法描述 (Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of the algorithm)。Intel Corporation, 5, 2001。

[42] Jean-Yves Bouguet. Matlab 相机标定工具箱 [EB/OL]。2004。

[43] Gary R Bradski. 用于感知用户界面的计算机视觉人脸跟踪 (Computer vision face tracking for use in a perceptual user interface)。Citeseer, 1998。

[44] GR Bradski and J Davis. 具有运动历史梯度的运动分割和姿态识别 (Motion segmentation and pose recognition with motion history gradients)。收录于 Applications of Computer Vision, 2000, Fifth IEEE Workshop on., 第 238–244 页。IEEE, 2000。

[45] Leo Breiman, Jerome Friedman, Charles J Stone, and Richard A Olshen. 分类与回归树 (Classification and regression trees)。CRC press, 1984。

[46] Thomas Breuel. 游程长度表示上的二值形态学及相关操作 (Binary Morphology and Related Operations on Run-Length Representations)。收录于 VISAPP 2008 - 3rd International Conference on Computer Vision Theory and Applications, Proceedings, 第 159-166 页, 2008年1月。

[47] Matthew Brown and David G Lowe. 使用不变特征的自动全景图像拼接 (Automatic panoramic image stitching using invariant features)。International journal of computer vision, 74(1):59–73, 2007。

[48] Thomas Brox, Andres Bruhn, Nils Papenberg, and Joachim Weickert. 基于翘曲理论的高精度光流估计 (High accuracy optical flow estimation based on a theory for warping)。收录于 Computer Vision-ECCV 2004, 第 25–36 页。Springer, 2004。

[49] Roberto Brunelli and Tomaso Poggio. 通过几何特征进行人脸识别 (Face recognition through geometrical features)。收录于 Computer Vision—ECCV’92, 第 792–800 页, 1992。

[50] Antoni Buades, Bartomeu Coll, and Jean-Michel Morel. 图像序列去噪不需要运动估计 (Denoising image sequences does not require motion estimation)。IEEE Conference on Advanced Video and Signal Based Surveillance, 2005., 70-74, 2005。

[51] Christopher JC Burges. 模式识别支持向量机教程 (A tutorial on support vector machines for pattern recognition)。Data mining and knowledge discovery, 2(2):121–167, 1998。

[52] Peter J Burt and Edward H Adelson. 一种多分辨率样条及其在图像拼接中的应用 (A multiresolution spline with application to image mosaics)。ACM Transactions on Graphics (TOG), 2(4):217–236, 1983。

[53] Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua. Brief：二进制鲁棒独立基本特征 (Brief: Binary robust independent elementary features)。收录于 Computer Vision–ECCV 2010, 第 778–792 页。Springer, 2010。

[54] John Canny. 边缘检测的计算方法 (A computational approach to edge detection)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 679–698, 1986。

[55] Antonin Chambolle, Vicent Caselles, Daniel Cremers, Matteo Novaga, and Thomas Pock. 图像分析的总变分介绍 (An introduction to total variation for image analysis)。Theoretical foundations and numerical methods for sparse recovery, 9:263–340, 2010。

[56] Chih-Chung Chang and Chih-Jen Lin. LIBSVM：支持向量机库 (LIBSVM: a library for support vector machines)。ACM Transactions on Intelligent Systems and Technology (TIST), 2(3):27, 2011。

[57] Carl Chatfield. 椭圆距离的简单方法 (A Simple Method for Distance to Ellipse)。GitHub, 2017。

[58] Fran\c cois Chaumette and S. Hutchinson. 视觉伺服控制，第一部分：基本方法 (Visual servo control, Part I: Basic approaches)。IEEE Robotics and Automation Magazine, 13(4):82-90, 2006。

[59] Fran\c cois Chaumette and S. Hutchinson. 视觉伺服控制，第一部分：基本方法 (Visual servo control, Part I: Basic approaches)。IEEE Robotics and Automation Magazine, 13(4):82-90, 2006。

[60] Fran\c cois Chaumette and S. Hutchinson. 视觉伺服控制，第二部分：高级方法 (Visual servo control, Part II: Advanced approaches)。IEEE Robotics and Automation Magazine, 14(1):109-118, 2007。

[61] Ming-Ming Cheng, Ziming Zhang, Wen-Yan Lin, and Philip Torr. BING：300fps 的二值化规范梯度目标性估计 (BING: Binarized normed gradients for objectness estimation at 300fps)。收录于 IEEE CVPR, 2014。

[62] Dongliang Cheng, Brian Price, Scott Cohen, and Michael S Brown. 使用简单特征的基于学习的有效光源估计 (Effective learning-based illuminant estimation using simple features)。收录于 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 第 1000–1008 页, 2015。

[63] Ming-Ming Cheng, Yun Liu, Qibin Hou, Jiawang Bian, Philip Torr, Shi-Min Hu, and Zhuowen Tu. HFS：用于高效图像分割的分层特征选择 (HFS: Hierarchical Feature Selection for Efficient Image Segmentation)。收录于 European Conference on Computer Vision, 第 867–882 页, 2016。

[64] Hojin Cho, Hyunjoon Lee, Henry Kang, and Seungyong Lee. 双边纹理滤波 (Bilateral Texture Filtering)。ACM Transactions on Graphics, 33(4):128:1–128:8, 2014年7月。

[65] Ondrej Chum, Jiri Matas, and Josef Kittler. 局部优化 RANSAC (Locally Optimized RANSAC)。收录于 DAGM, 2003。

[66] Ondrej Chum, Tomas Werner, and Jiri Matas. 通过 RANSAC 进行的对极几何估计得益于定向对极约束 (Epipolar geometry estimation via RANSAC benefits from the oriented epipolar constraint)。收录于 Proceedings of the 17th International Conference on Pattern Recognition. ICPR 2004, 第 112-115 页，第1卷, 2004。

[67] Ondrej Chum, Tomas Werner, and Jiri. Matas. 不受主平面影响的对极几何估计 (Epipolar Geometry Estimation Unaffected by the Dominant Plane)。收录于 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2005。

[68] Ondrej Chum and Jiri Matas. 使用 PROSAC 进行匹配 - 渐进式采样一致性 (Matching with PROSAC - Progressive Sampling Consensus)。收录于 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2005。

[69] Toby Collins and Adrien Bartoli. 无穷小平面姿态估计 (Infinitesimal Plane-Based Pose Estimation)。International Journal of Computer Vision, 109(3):252-286, 2014。

[70] Pengyu Cong, Zhiwei Xiong, Yueyi Zhang, Shenghui Zhao, and Feng Wu. 傅里叶辅助相移的高精度动态 3D 感知 (Accurate dynamic 3D sensing with Fourier-assisted phase shifting)。IEEE Journal of Selected Topics in Signal Processing, 9(3):396–408, 2015。

[71] Navneet Dalal and Bill Triggs. 用于人体检测的定向梯度直方图 (Histograms of oriented gradients for human detection)。收录于 Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 第 886–893 页。IEEE, 2005。

[72] M. Danelljan, F.S. Khan, M. Felsberg, and J. van de Weijer. 用于实时视觉跟踪的自适应颜色属性 (Adaptive Color Attributes for Real-Time Visual Tracking)。收录于 Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, 第 1090-1097 页, 2014年6月。

[73] Konstantinos Daniilidis. 使用对偶四元数进行手眼标定 (Hand-Eye Calibration Using Dual Quaternions)。International Journal of Robotics Research, 18:286–298, 1998。

[74] James W Davis and Aaron F Bobick. 使用时间模板表示和识别人类运动 (The representation and recognition of human movement using temporal templates)。收录于 Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on, 第 928–934 页。IEEE, 1997。

[75] Brice Chaix De Lavarène, David Alleysson, Barthélémy Durette, and Jeanny Hérault. 通过递归滤波实现高效去马赛克 (Efficient demosaicing through recursive filtering)。收录于 Image Processing, 2007. ICIP 2007. IEEE International Conference on, 第 II–189 页, 2007。

[76] Paul E Debevec and Jitendra Malik. 从照片中恢复高动态范围辐射图 (Recovering high dynamic range radiance maps from photographs)。收录于 ACM SIGGRAPH 2008 classes, 第 31 页。ACM, 2008。

[77] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet：大规模分层图像数据库 (ImageNet: A Large-Scale Hierarchical Image Database)。收录于 CVPR09, 2009。

[78] Ferdinando Di Martino, Vincenzo Loia, Irina Perfilieva, and Salvatore Sessa. 一种基于直接和逆模糊变换的图像编码/解码方法 (An image coding/decoding method based on direct and inverse fuzzy transforms)。International Journal of Approximate Reasoning, 48(1):110–131, 2008。

[79] Yaqing Ding, Jian Yang, Viktor Larsson, Carl Olsson, and Kalle Åström. 重访 P3P 问题 (Revisiting the P3P Problem)。收录于 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 第 4872–4880 页, 2023。

[80] Piotr Dollár, Zhuowen Tu, Pietro Perona, and Serge Belongie. 积分通道特征 (Integral Channel Features)。收录于 BMVC, 第 5 页, 2009。

[81] Piotr Dollár and C Lawrence Zitnick. 用于快速边缘检测的结构化森林 (Structured forests for fast edge detection)。收录于 Computer Vision (ICCV), 2013 IEEE International Conference on, 第 1841–1848 页, 2013。

[82] Frédéric Drago, Karol Myszkowski, Thomas Annen, and Norishige Chiba. 用于显示高对比度场景的自适应对数映射 (Adaptive logarithmic mapping for displaying high contrast scenes)。收录于 Computer Graphics Forum, 第 419–426 页。Wiley, 2003。

[83] Bertram Drost and Slobodan Ilic. 使用多模态点对特征的 3D 目标检测与定位 (3d object detection and localization using multimodal point pair features)。收录于 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), 2012 Second International Conference on, 第 9–16 页, 2012。

[84] Tom Drummond and Roberto Cipolla. 复杂结构的实时视觉跟踪 (Real-time visual tracking of complex structures)。IEEE Transactions on pattern analysis and machine intelligence, 24(7):932–946, 2002。

[85] Richard O Duda, Peter E Hart, and David G Stork. 模式分类 (Pattern classification)。John Wiley & Sons, 2012。

[86] Alexander Duda and Udo Frese. 用于标定的棋盘角点准确检测与定位 (Accurate Detection and Localization of Checkerboard Corners for Calibration)。收录于 29th British Machine Vision Conference. British Machine Vision Conference (BMVC-29), September 3-6, Newcastle, United Kingdom. BMVA Press, 2018。

[87] Frédo Durand and Julie Dorsey. 用于高动态范围图像显示的快速双边滤波 (Fast bilateral filtering for the display of high-dynamic-range images)。收录于 ACM Transactions on Graphics (TOG), 第 257–266 页。ACM, 2002。

[88] Ethan Eade. Gauss-Newton / Levenberg-Marquardt 优化 (Gauss-Newton / Levenberg-Marquardt Optimization)。2013。

[89] Ethan Eade. 二维和三维变换的李群 (Lie Groups for 2D and 3D Transformation)。2017。

[90] Niki Estner. 分割叶片脉络的最佳方法 (Best Way of Segmenting Veins in Leaves)。

[91] Georgios D Evangelidis and Emmanouil Z Psarakis. 使用增强相关系数最大化的参数化图像对齐 (Parametric image alignment using enhanced correlation coefficient maximization)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 30(10):1858–1865, 2008。

[92] M. Everingham, L. Van~Gool, C. K. I. Williams, J. Winn, and A. Zisserman. Pascal 视觉目标类 (VOC) 挑战赛 (The Pascal Visual Object Classes (VOC) Challenge)。International Journal of Computer Vision, 88(2):303–338, 2010年6月。

[93] Zeev Farbman, Raanan Fattal, Dani Lischinski, and Richard Szeliski. 用于多尺度色调和细节处理的边缘保持分解 (Edge-preserving decompositions for multi-scale tone and detail manipulation)。收录于 ACM Transactions on Graphics (TOG), 第 67 页, 2008。

[94] Gunnar Farnebäck. 基于多项式展开的双帧运动估计 (Two-frame motion estimation based on polynomial expansion)。收录于 Image Analysis, 第 363–370 页。Springer, 2003。

[95] Sina Farsiu, Dirk Robinson, Michael Elad, and Peyman Milanfar. 快速且鲁棒的超分辨率 (Fast and robust super-resolution)。收录于 Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on, 第 II–291 页。IEEE, 2003。

[96] Raanan Fattal, Dani Lischinski, and Michael Werman. 梯度域高动态范围压缩 (Gradient domain high dynamic range compression)。收录于 ACM Transactions on Graphics (TOG), 第 249–256 页。ACM, 2002。

[97] Pedro Felzenszwalb and Daniel Huttenlocher. 采样函数的距离变换 (Distance transforms of sampled functions)。康奈尔大学, 2004。

[98] Pedro F Felzenszwalb and Daniel P Huttenlocher. 高效的基于图的图像分割 (Efficient graph-based image segmentation)。Springer, 2004。

[99] Pedro F Felzenszwalb and Daniel P Huttenlocher. 用于早期视觉的高效信念传播 (Efficient belief propagation for early vision)。International journal of computer vision, 70(1):41–54, 2006。

[100] Pedro F Felzenszwalb, Ross B Girshick, and David McAllester. 具有可变形部件模型的级联目标检测 (Cascade object detection with deformable part models)。收录于 Computer vision and pattern recognition (CVPR), 2010 IEEE conference on, 第 2241–2248 页, 2010。

[101] Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. 判别式训练部件模型的目标检测 (Object detection with discriminatively trained part-based models)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 32(9):1627–1645, 2010。

[102] Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. 判别式训练部件模型的目标检测 (Object detection with discriminatively trained part-based models)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 32(9):1627–1645, 2010。

[103] Martin A. Fischler and Robert C. Bolles. 随机采样一致性：一种模型拟合范例及其在图像分析和自动化制图中的应用 (Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography)。Association for Computing Machinery, 1981年6月。

[104] Martin A Fischler and Robert C Bolles. 随机采样一致性：一种模型拟合范例及其在图像分析和自动化制图中的应用 (Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography)。Communications of the ACM, 24(6):381–395, 1981。

[105] Ronald A Fisher. 多重测量在分类问题中的应用 (The use of multiple measurements in taxonomic problems)。Annals of eugenics, 7(2):179–188, 1936。

[106] Andrew W Fitzgibbon and Robert B Fisher. 圆锥拟合买家指南 (A buyer’s guide to conic fitting)。收录于 Proceedings of the 6th British conference on Machine vision (Vol. 2), 第 513–522 页。BMVA Press, 1995。

[107] Per-Erik Forssén. 用于识别和匹配的最大稳定色彩区域 (Maximally stable colour regions for recognition and matching)。收录于 Computer Vision and Pattern Recognition, 2007. CVPR’07. IEEE Conference on, 第 1–8 页。IEEE, 2007。

[108] W Forstner. 一种用于检测和精确确定独特点、角点及圆形特征中心的高速算子 (A fast operator for detection and precise location of distincs points, corners and center of circular features)。收录于 Proc. of the Intercommission Conference on Fast Processing of Photogrammetric Data, Interlaken, Switzerland, 1987, 第 281–305 页, 1987。

[109] Jerome Friedman, Trevor Hastie, and Robert Tibshirani. 加性逻辑回归：Boosting 的统计观点 (Additive Logistic Regression: a Statistical View of Boosting)。1998。

[110] Guillermo Gallego and Anthony J. Yezzi. 指数坐标系下三维旋转导数的紧凑公式 (A Compact Formula for the Derivative of a 3-D Rotation in Exponential Coordinates)。Journal of Mathematical Imaging and Vision, 51:378-384, 2014。

[111] S. Garrido-Jurado, R. Muñoz-Salinas, F.J. Madrid-Cuevas, and M.J. Marín-Jiménez. 遮挡下高可靠性基准标记的自动生成与检测 (Automatic generation and detection of highly reliable fiducial markers under occlusion)。Pattern Recognition, 47(6):2280 - 2292, 2014。

[112] Eduardo SL Gastal and Manuel M Oliveira. 用于边缘感知图像和视频处理的域变换 (Domain transform for edge-aware image and video processing)。收录于 ACM Transactions on Graphics (TOG), 第 69 页。ACM, 2011。

[113] Eduardo SL Gastal and Manuel M Oliveira. 用于边缘感知图像和视频处理的域变换 (Domain transform for edge-aware image and video processing)。收录于 ACM Transactions on Graphics (TOG), 第 69 页, 2011。

[114] Eduardo SL Gastal and Manuel M Oliveira. 用于实时高维滤波的自适应流形 (Adaptive manifolds for real-time high-dimensional filtering)。ACM Transactions on Graphics (TOG), 31(4):33, 2012。

[115] Jonas Geistert, Tobias Senst, and Thomas Sikora. 鲁棒局部光流：稠密运动矢量场插值 (Robust Local Optical Flow: Dense Motion Vector Field Interpolation)。收录于 Picture Coding Symposium, 第 1–5 页, 2016。

[116] N. Genser, J. Seiler, F. Schilling, and A. Kaup. 用于误差隐藏的信号和损失几何感知频率选择性外推 (Signal and Loss Geometry Aware Frequency Selective Extrapolation for Error Concealment)。收录于 Proc. Picture Coding Symposium (PCS), 第 159-163 页, 2018年6月。

[117] Athinodoros S. Georghiades, Peter N. Belhumeur, and David Kriegman. 从少到多：变光照和姿态下人脸识别的光照锥模型 (From few to many: Illumination cone models for face recognition under variable lighting and pose)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 23(6):643–660, 2001。

[118] Pascal Getreuer. Malvar-He-Cutler 线性图像去马赛克 (Malvar-He-Cutler Linear Image Demosaicking)。Image Processing on Line, 2011。

[119] Andrew B Godbehere, Akihiro Matsukawa, and Ken Goldberg. 用于响应式音频艺术装置的变光条件下人类视觉跟踪 (Visual tracking of human visitors under variable-lighting conditions for a responsive audio art installation)。收录于 American Control Conference (ACC), 2012, 第 4305–4312 页。IEEE, 2012。

[120] Rafael C Gonzalez 等人。数字图像基础，数字图像处理 (Digital Image Fundamentals, Digital Imaging Processing)。Addison Wesley Publishing Company, 1987。

[121] Helmut Grabner, Michael Grabner, and Horst Bischof. 通过在线 Boosting 进行实时跟踪 (Real-Time Tracking via On-line Boosting)。收录于 BMVC, 第 6 页, 2006。

[122] Costantino Grana, Daniele Borghesani, and Rita Cucchiara. 具有决策树的优化块基连通分量标记 (Optimized Block-Based Connected Components Labeling With Decision Trees)。IEEE Transactions on Image Processing, 19(6):1596–1609, 2010。

[123] Rafael Grompone von Gioi, Jérémie Jakubowicz, Jean-Michel Morel, and Gregory Randall. LSD：线段检测器 (LSD: a Line Segment Detector)。Image Processing On Line, 2:35–55, 2012。

[124] S. Grosche, J. Seiler, and A. Kaup. 非规则图像采样模式的设计技术 (Design Techniques for Incremental Non-Regular Image Sampling Patterns)。收录于 Proc. IEEE International Conference on Imaging Systems and Techniques (IST), 第 1-6 页, 2018年10月。

[125] S. Grosche, J. Seiler, and A. Kaup. 非规则采样传感器的四分之一采样掩码迭代优化 (Iterative Optimization of Quarter Sampling Masks for Non-Regular Sampling Sensors)。收录于 Proc. 25th IEEE International Conference on Image Processing (ICIP), 第 26-30 页, 2018年10月。

[126] Matthias Grundmann, Vivek Kwatra, and Irfan Essa. 具有鲁棒 L1 优化相机路径的自动引导视频稳定 (Auto-directed video stabilization with robust l1 optimal camera paths)。收录于 Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, 第 225–232 页。IEEE, 2011。

[127] N Guil, José Mar’\ia Gonzalez-Linares, and Emilio L Zapata. 使用不变方法的二维形状检测 (Bidimensional shape detection using an invariant approach)。Pattern Recognition, 32(6):1025–1038, 1999。

[128] L. Guo, D. Xu, and Z. Qiang. 使用局部 SVD 二进制模式的背景减除 (Background Subtraction Using Local SVD Binary Pattern)。收录于 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 第 1159-1167 页, 2016年6月。

[129] Llu’\is Gómez and Dimosthenis Karatzas. 自然场景中的多脚本文本提取 (Multi-script Text Extraction from Natural Scenes)。收录于 Proceedings of the 2013 12th International Conference on Document Analysis and Recognition, 第 467–471 页。IEEE Computer Society, 2013。

[130] Z. Wang, L. Cormack H.R. Sheikh and A.C. Bovik. LIVE 图像质量评估数据库发布版 2。网址 http://live.ece.utexas.edu/research/quality, 2005。

[131] Chris Harris and Carl Stennett. RAPID - 视频速率目标跟踪器 (RAPID-a video rate object tracker)。收录于 BMVC, 第 1–6 页, 1990。

[132] Richard I Hartley. 投影校正的理论与实践 (Theory and practice of projective rectification)。International Journal of Computer Vision, 35(2):115–127, 1999。

[133] Richard Hartley and Andrew Zisserman. 计算机视觉中的多视图几何 (Multiple view geometry in computer vision)。剑桥大学出版社, 2003。

[134] Kaiming He, Jian Sun, and Xiaoou Tang. 引导图像滤波 (Guided image filtering)。收录于 Computer Vision–ECCV 2010, 第 1–14 页。Springer, 2010。

[135] Kaiming He and Jian Sun. 图像补全的块偏移统计 (Statistics of patch offsets for image completion)。收录于 Computer Vision–ECCV 2012, 第 16–29 页。Springer, 2012。

[136] Kaiming He and Jian Sun. 快速引导滤波 (Fast guided filter)。arXiv 预印本 arXiv:1505.00996, 2015。

[137] J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. 利用核函数跟踪检测的循环结构 (Exploiting the Circulant Structure of Tracking-by-detection with Kernels)。收录于 proceedings of the European Conference on Computer Vision, 2012。

[138] J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. 使用核化相关滤波器的高速跟踪 (High-Speed Tracking with Kernelized Correlation Filters)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2015。

[139] Kyriakos Herakleous and Charalambos Poullis. 3DUNDERWORLD-SLS：用于快速几何采集的开源结构光扫描系统 (3DUNDERWORLD-SLS: An Open-Source Structured-Light Scanning System for Rapid Geometry Acquisition)。arXiv 预印本 arXiv:1406.6595, 2014。

[140] S. Hinterstoisser, S. Benhimane, V. and Lepetit, and N. Navab. 使用简单线性分类器的局部块同时识别与单应性提取 (Simultaneous Recognition and Homography Extraction of Local Patches with a Simple Linear Classifier)。BMVC British Machine Vision Conference 2008, 2008。

[141] Heiko Hirschmuller. 通过半全局匹配和互信息的立体处理 (Stereo processing by semiglobal matching and mutual information)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 30(2):328–341, 2008。

[142] Gerhard J. Holzmann. 超越摄影：数字暗房 (Beyond Photography: The Digital Darkroom)。Prentice Hall, 1988年。

[143] Radu Horaud and Fadi Dornaika. 手眼标定 (Hand-eye Calibration)。Int. J. Rob. Res., 14(3):195–210, 1995年6月。

[144] Berthold KP Horn and Brian G Schunck. 确定光流 (Determining Optical Flow)。Artificial Intelligence, 17:185–203, 1981。

[145] Xiaodi Hou and Liqing Zhang. 显著性检测：一种谱残差方法 (Saliency detection: A spectral residual approach)。收录于 Computer Vision and Pattern Recognition, 2007. CVPR’07. IEEE Conference on, 第 1–8 页, 2007。

[146] Zdenek Hrazd’\ira, Miloslav Druckmüller, and Shadia Habbal. 用于高精度亚像素图像配准的迭代相位相关算法 (Iterative phase correlation algorithm for high-precision subpixel image registration)。The Astrophysical Journal Supplement Series, 247(1):8, 2020。

[147] Ming-Kuei Hu. 矩不变量的视觉模式识别 (Visual pattern recognition by moment invariants)。Information Theory, IRE Transactions on, 8(2):179–187, 1962。

[148] Yinlin Hu, Yunsong Li, and Rui Song. 用于大位移光流的对应关系鲁棒插值 (Robust interpolation of correspondences for large displacement optical flow)。收录于 IEEE Conference on Computer Vision and Pattern Recognition, 第 481–489 页, 2017。

[149] Seth A. Hutchinson, Gregory Hager, and Peter Corke. 视觉伺服控制教程 (A tutorial on visual servo control)。IEEE Trans. Robotics Autom., 12:651-670, 1996。

[150] Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, and Kurt Keutzer. SqueezeNet：参数减少 50 倍且模型大小 \(<\)0.5MB 的 AlexNet 级精度 (SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \(<\)0.5MB model size)。arXiv:1602.07360, 2016。

[151] ITU. 建议 ITU-R BT.709-6 (Recommendation ITU-R BT.709-6)。ITU, 2015。

[152] Shahram Izadi, David Kim, Otmar Hilliges, David Molyneaux, Richard Newcombe, Pushmeet Kohli, Jamie Shotton, Steve Hodges, Dustin Freeman, Andrew Davison, and Andrew Fitzgibbon. KinectFusion：使用移动深度相机的实时 3D 重建与交互 (KinectFusion: Real-time 3D Reconstruction and Interaction Using a Moving Depth Camera)。ACM, 2011年10月。

[153] Bernd Jahne. 计算机视觉与应用：学生与从业者指南 (Computer vision and applications: a guide for students and practitioners)。Elsevier, 2000。

[154] Herault Jeanny. 视觉：图像、信号和神经网络 - 视觉感知中神经处理的模型 (Vision: Images, Signals and Neural Networks-Models of Neural Processing in Visual Perception)。World Scientific, 2010。

[155] Qi Jia, Xin Fan, Zhongxuan Luo, Lianbo Song, and Tie Qiu. 使用投影不变剪枝的快速椭圆检测器 (A fast ellipse detector using projective invariant pruning)。IEEE Transactions on Image Processing, 26(8):3665–3679, 2017。

[156] Pakorn KaewTraKulPong and Richard Bowden. 一种改进的带阴影检测的实时跟踪自适应背景混合模型 (An improved adaptive background mixture model for real-time tracking with shadow detection)。收录于 Video-Based Surveillance Systems, 第 135–144 页。Springer, 2002。

[157] Pakorn KaewTraKulPong and Richard Bowden. 一种改进的带阴影检测的实时跟踪自适应背景混合模型 (An improved adaptive background mixture model for real-time tracking with shadow detection)。收录于 Video-Based Surveillance Systems, 第 135–144 页。Springer, 2002。

[158] Zdenek Kalal, Krystian Mikolajczyk, and Jiri Matas. 前向-后向误差：跟踪失败的自动检测 (Forward-backward error: Automatic detection of tracking failures)。收录于 Pattern Recognition (ICPR), 2010 20th International Conference on, 第 2756–2759 页, 2010。

[159] Zdenek Kalal, Krystian Mikolajczyk, and Jiri Matas. 跟踪-学习-检测 (Tracking-learning-detection)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 34(7):1409–1422, 2012。

[160] Takeo Kanade. 计算机图像处理系统与人脸识别 (Picture processing system by computer complex and recognition of human faces)。1974。

[161] Juho Kannala and Sami Brandt. 传统、广角和鱼眼镜头的通用相机模型与标定方法 (A Generic Camera Model and Calibration Method for Conventional, Wide-Angle, and Fish-Eye Lenses)。IEEE transactions on pattern analysis and machine intelligence, 28:1335-40, 2006年9月。

[162] Michael Kass and Andrew Witkin. 分析定向模式 (Analyzing oriented patterns)。Computer vision, graphics, and image processing, 37(3):362–385, 1987。

[163] Tong Ke and Stergios Roumeliotis. 透视三点问题的有效代数解 (An Efficient Algebraic Solution to the Perspective-Three-Point Problem)。收录于 Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on。IEEE, 2017。

[164] Khurram Khurshid, Imran Siddiqi, Claudie Faure, and Nicole Vincent. 古代文档 Niblack 启发式二值化方法的比较 (Comparison of Niblack inspired Binarization methods for ancient documents)。收录于 IS&T/SPIE Electronic Imaging, 第 72470U–72470U 页, 2009。

[165] Junhwan Kim, Vladimir Kolmogorov, and Ramin Zabih. 使用能量最小化和互信息的视觉对应 (Visual correspondence using energy minimization and mutual information)。收录于 Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, 第 1033–1040 页。IEEE, 2003。

[166] S. Kirkpatrick, C. D. Jr Gelatt, and M. P. Vecchi. 模拟退火优化 (Optimization by Simulated Annealing)。Science, 220(4598):671–680, 1983。

[167] Victor Klee and Michael C Laskowski. 寻找包含给定凸多边形的最小三角形 (Finding the smallest triangles containing a given convex polygon)。Journal of Algorithms, 6(3):359–375, 1985。

[168] Adrian Ilie Kok-Lim Low. 最大化目标图像区域的视锥优化 (View Frustum Optimization to Maximize Object’s Image Area)。Journal of Graphics, (GPU, & Game) Tools (JGT), 8:3-15, 2003。

[169] Neal Krawetz. 看起来像它 (Looks Like It)。

[170] Till Kroeger, Radu Timofte, Dengxin Dai, and Luc Van Gool. 使用稠密逆搜索的快速光流 (Fast Optical Flow using Dense Inverse Search)。收录于 Proceedings of the European Conference on Computer Vision (ECCV), 2016。

[171] Martin Krulis, Jakub Lokoc, and Tomas Skopal. 使用 GPU 架构高效提取基于聚类的特征签名 (Efficient extraction of clustering-based feature signatures using GPU architectures)。Multimedia Tools Appl., 75(13):8071–8103, 2016。

[172] Vivek Kwatra, Arno Schödl, Irfan Essa, Greg Turk, and Aaron Bobick. 图割纹理：使用图割的图像和视频合成 (Graphcut textures: image and video synthesis using graph cuts)。收录于 ACM Transactions on Graphics (ToG), 第 277–286 页。ACM, 2003。

[173] Kuang-Chih Lee, Jeffrey Ho, and David Kriegman. 获取变光照下人脸识别的线性子空间 (Acquiring linear subspaces for face recognition under variable lighting)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 27(5):684–698, 2005。

[174] Jin Han Lee, Sehyung Lee, Guoxuan Zhang, Jongwoo Lim, Wan Kyun Chung, and Il Hong Suh. 使用直线识别城市环境中的户外地点 (Outdoor place recognition in urban environments using straight lines)。收录于 2014 IEEE International Conference on Robotics and Automation (ICRA), 第 5550–5557 页, 2014。

[175] Hai Lei, Xin-yu Chang, Fei Wang, Xiao-Tang Hu, and Xiao-Dong Hu. 一种基于可靠性直方图处理的二维相位解缠新算法 (A novel algorithm based on histogram processing of reliability for two-dimensional phase unwrapping)。Optik-International Journal for Light and Electron Optics, 126(18):1640–1644, 2015。

[176] Vincent Lepetit, Francesc Moreno-Noguer, and Pascal Fua. Epnp：Pnp 问题的准确 o(n) 解决方案 (Epnp: An accurate o (n) solution to the pnp problem)。International journal of computer vision, 81(2):155–166, 2009。

[177] Stefan Leutenegger, Margarita Chli, and Roland Yves Siegwart. BRISK：二进制鲁棒不变可扩展关键点 (BRISK: Binary robust invariant scalable keypoints)。收录于 Computer Vision (ICCV), 2011 IEEE International Conference on, 第 2548–2555 页。IEEE, 2011。

[178] Maxime Lhuillier and Long Quan. 使用局部和全局几何约束的鲁棒稠密匹配 (Robust dense matching using local and global geometric constraints)。Proceedings-International Conference on Pattern Recognition, 15(1):968–972, 2000。

[179] Liyuan Li, Weimin Huang, Irene YH Gu, and Qi Tian. 包含复杂背景视频的前景目标检测 (Foreground object detection from videos containing complex background)。收录于 Proceedings of the eleventh ACM international conference on Multimedia, 第 2–10 页。ACM, 2003。

[180] Aiguo Li, Lin Wang, and Defeng Wu. 使用对偶四元数和克罗内克积的同步机器人-世界和手眼标定 (Simultaneous robot-world and hand-eye calibration using dual-quaternions and Kronecker product)。International Journal of Physical Sciences, 5:1530-1536, 2010。

[181] Xi Li, Weiming Hu, Chunhua Shen, Zhongfei Zhang, Anthony Dick, and Anton Van Den Hengel. 视觉目标跟踪中外观模型综述 (A survey of appearance models in visual object tracking)。ACM Transactions on Intelligent Systems and Technology (TIST), 4(4):58, 2013。

[182] Zhengqin Li and Jiansheng Chen. 使用线性谱聚类的超像素分割 (Superpixel Segmentation Using Linear Spectral Clustering)。2015年6月。

[183] Shengcai Liao, Xiangxin Zhu, Zhen Lei, Lun Zhang, and Stan Z Li. 学习多尺度块局部二进制模式用于人脸识别 (Learning multi-scale block local binary patterns for face recognition)。收录于 Advances in Biometrics, 第 828–837 页。Springer, 2007。

[184] Minghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, and Wenyu Liu. TextBoxes：具有单个深度神经网络的快速文本检测器 (TextBoxes: A Fast Text Detector with a Single Deep Neural Network)。收录于 AAAI, 2017。

[185] Minghui Liao, Zhaoyi Wan, Cong Yao, Kai Chen, and Xiang Bai. 具有可微分二值化的实时场景文本检测 (Real-time Scene Text Detection with Differentiable Binarization)。收录于 Proc. AAAI, 2020。

[186] Rainer Lienhart and Jochen Maydt. 一组用于快速目标检测的扩展 Haar 类特征 (An extended set of haar-like features for rapid object detection)。收录于 Image Processing. 2002. Proceedings. 2002 International Conference on, 第 I–900 页。IEEE, 2002。

[187] Joseph J Lim, C Lawrence Zitnick, and Piotr Dollár. 草图标记：一种用于轮廓和目标检测的习得中级表示 (Sketch tokens: A learned mid-level representation for contour and object detection)。收录于 Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, 第 3158–3165 页, 2013。

[188] Yong-Jin Liu, Cheng-Chi Yu, Min-Jing Yu, and Ying He. 内在流形 SLIC：一种计算内容敏感超像素的简单有效方法 (Intrinsic Manifold SLIC: A Simple and Efficient Method for Computing Content-Sensitive Superpixels)。IEEE Computer Society, 2017年3月。

[189] Seng Cheong Loke, Bruce A MacDonald, Matthew Parsons, and Burkhard Claus Wünsche. 使用并行化 DBSCAN 算法的加速超像素图像分割 (Accelerated superpixel image segmentation with a parallelized DBSCAN algorithm)。Journal of Real-Time Image Processing, 1–16, 2021。

[190] H. Louhichi, T. Fournel, J. M. Lavest, and H. Ben Aissia. Scheimpflug 相机的自标定：一种简单的协议 (Self-calibration of Scheimpflug cameras: an easy protocol)。Meas. Sci. Technol., 18(8):2616–2622, 2007。

[191] Manolis I. A. Lourakis and Antonis A. Argyros. SBA：一种用于通用稀疏光束平差的软件包 (SBA: A Software Package for Generic Sparse Bundle Adjustment)。ACM Transactions on Mathematical Software, 36(1):2:1–2:30, 2009年3月。

[192] Kok-Lim Low. 点到平面 ICP 表面配准的线性最小二乘优化 (Linear least-squares optimization for point-to-plane icp surface registration)。北卡罗来纳大学教堂山分校, 2004。

[193] David G. Lowe. 来自尺度不变关键点的独特图像特征 (Distinctive Image Features from Scale-Invariant Keypoints)。Int. J. Comput. Vision, 60(2):91–110, 2004年11月。

[194] Stephanie Lowry and Henrik Andreasson. LOGOS：用于高异常值空间验证的局部几何支持 (LOGOS: Local Geometric Support for High-Outlier Spatial Verification)。2018 IEEE International Conference on Robotics and Automation (ICRA), 7262-7269, 2018。

[195] Cewu Lu, Li Xu, and Jiaya Jia. 对比度保持的去色 (Contrast preserving decolorization)。收录于 Computational Photography (ICCP), 2012 IEEE International Conference on, 第 1–7 页。IEEE, 2012。

[196] Bruce D Lucas, Takeo Kanade 等人。 一种具有立体视觉应用的迭代图像配准技术 (An iterative image registration technique with an application to stereo vision.)。收录于 IJCAI, 第 674–679 页, 1981。

[197] Alan Luke\vzi\vc, Tom’a\vs Voj’i\vr, Luka \vCehovin Zajc, Ji\vr’i Matas, and Matej Kristan. 具有通道和空间可靠性的判别相关滤波器跟踪器 (Discriminative Correlation Filter Tracker with Channel and Spatial Reliability)。International Journal of Computer Vision, 2018。

[198] Yi Ma, Stefano Soatto, Jana Kosecka, and S. Shankar Sastry. 三维视觉邀请：从图像到几何模型 (An Invitation to 3-D Vision: From Images to Geometric Models)。Springer, 2003。

[199] K. Madsen, H. B. Nielsen, and O. Tingleff. 非线性最小二乘问题方法（第 2 版）(Methods for Non-Linear Least Squares Problems (2nd ed.))。信息与数学建模系，丹麦技术大学，DTU, 2004。

[200] Elmar Mair, Gregory D. Hager, Darius Burschka, Michael Suppa, and Gerhard Hirzinger. 基于加速段测试的自适应通用角点检测 (Adaptive and Generic Corner Detection Based on the Accelerated Segment Test)。收录于 European Conference on Computer Vision (ECCV’10), 2010年9月。

[201] Ezio Malis and Manuel Vargas. 更深入理解基于视觉控制的单应性分解 (Deeper understanding of the homography decomposition for vision-based control)。INRIA, 2007。

[202] Rafal Mantiuk, Karol Myszkowski, and Hans-Peter Seidel. 用于高动态范围图像对比度处理的感知框架 (A perceptual framework for contrast processing of high dynamic range images)。ACM Transactions on Applied Perception (TAP), 3(3):286–308, 2006。

[203] Eric Marchand, Hideaki Uchiyama, and Fabien Spindler. 增强现实中的姿态估计：实操综述 (Pose Estimation for Augmented Reality: A Hands-On Survey)。IEEE Transactions on Visualization and Computer Graphics, 22(12):2633 - 2651, 2016年12月。

[204] Aleix M Mart’\inez and Avinash C Kak. PCA 与 LDA (Pca versus lda)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 23(2):228–233, 2001。

[205] Jiri Matas, Charles Galambos, and Josef Kittler. 使用渐进式概率霍夫变换的鲁棒线检测 (Robust detection of lines using the progressive probabilistic hough transform)。Computer Vision and Image Understanding, 78(1):119–137, 2000。

[206] Jiri Matas and Ondrej Chum. 带序贯概率比检验的随机 RANSAC (Randomized RANSAC with sequential probability ratio test)。第十届 IEEE 国际计算机视觉会议 (ICCV) 第 1 卷, 2:1727-1732, 2005。

[207] Wolfram Mathematica. Ridge Filter Mathematica。

[208] Yasuyuki Matsushita, Eyal Ofek, Weina Ge, Xiaoou Tang, and Heung-Yeung Shum. 具有运动修复的全帧视频稳定 (Full-frame video stabilization with motion inpainting)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 28(7):1150–1163, 2006。

[209] Tom Mertens, Jan Kautz, and Frank Van Reeth. 曝光融合 (Exposure fusion)。收录于 Computer Graphics and Applications, 2007. PG’07. 15th Pacific Conference on, 第 382–390 页。IEEE, 2007。

[210] Kieron Messer 等人。人脸识别算法的性能表征及其对严重光照变化的敏感性 (Performance characterisation of face recognition algorithms and their sensitivity to severe illumination changes)。收录于 Advances in Biometrics, 第 1–11 页。Springer, 2005。

[211] Fernand Meyer. 彩色图像分割 (Color image segmentation)。收录于 Image Processing and its Applications, 1992., International Conference on, 第 303–306 页。IET, 1992。

[212] Laurence Meylan, David Alleysson, and Sabine Süsstrunk. 用于彩色滤光片阵列图像色调映射的视网膜局部适应模型 (Model of retinal local adaptation for the tone mapping of color filter array images)。JOSA A, 24(9):2807–2816, 2007。

[213] Krystian Mikolajczyk and Cordelia Schmid. 尺度与仿射不变兴趣点检测器 (Scale & affine invariant interest point detectors)。International journal of computer vision, 60(1):63–86, 2004。

[214] Dongbo Min, Sunghwan Choi, Jiangbo Lu, Bumsub Ham, Kwanghoon Sohn, and Minh N Do. 基于加权最小二乘的快速全局图像平滑 (Fast global image smoothing based on weighted least squares)。Image Processing, IEEE Transactions on, 23(12):5638–5653, 2014。

[215] Tom M Mitchell. 逻辑回归 (Logistic Regression)。Machine learning, 10:701, 2005。

[216] A. Mittal, A. K. Moorthy, and A. C. Bovik. BRISQUE 软件发布。网址 http://live.ece.utexas.edu/research/quality/BRISQUE_release.zip, 2011。

[217] A. Mittal, A. K. Moorthy, and A. C. Bovik. 空间域的无参考图像质量评估 (No-Reference Image Quality Assessment in the Spatial Domain)。IEEE Transactions on Image Processing, 21(12):4695-4708, 2012。

[218] Dennis Mitzel, Thomas Pock, Thomas Schoenemann, and Daniel Cremers. 基于对偶 TV-L1 光流的视频超分辨率 (Video super resolution using duality based tv-l 1 optical flow)。收录于 Pattern Recognition, 第 432–441 页。Springer, 2009。

[219] Sebastian Montabone and Alvaro Soto. 使用移动平台和源自视觉显著性机制的新型特征进行人体检测 (Human Detection Using a Mobile Platform and Novel Features Derived from a Visual Saliency Mechanism)。收录于 Image and Vision Computing, Vol. 28 Issue 3, 第 391–402 页, 2010。

[220] Alexander Mordvintsev. 带有原始对偶算法的 ROF 和 TV-L1 去噪 (ROF and TV-L1 denoising with Primal-Dual algorithm)。

[221] Eric N. Mortensen and William A. Barrett. 用于图像合成的智能剪刀 (Intelligent Scissors for Image Composition)。收录于 In Computer Graphics, SIGGRAPH Proceedings, 第 191–198 页, 1995。

[222] Marius Muja and David G Lowe. 具有自动算法配置的快速近似最近邻 (Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration)。收录于 VISAPP (1), 第 331–340 页, 2009。

[223] Rafael Muñoz-Salinas, Francisco J. Romero-Ramírez, and Manuel J. Marín-Jiménez. TRUCO：一种用于并行轮廓提取的可扩展无锁算法 (TRUCO: A Scalable Lock-Free Algorithm for Parallel Contour Extraction)。Pattern Recognition 审稿中, 2026。

[224] D. Myatt, Philip Torr, Slawomir Nasuto, John Bishop, and R. Craddock. NAPSAC：高噪声、高维鲁棒估计 - 就在袋子里 (NAPSAC: High Noise, High Dimensional Robust Estimation - it’s in the Bag)。收录于 Proceedings of the British Machine Vision Conference (BMVC), 2002。

[225] V. Lukin 等人。TID2008 - 全参考视觉质量评估指标评估数据库 (TID2008 - A Database for Evaluation of Full-Reference Visual Quality Assessment Metrics)。Advances of Modern Radioelectronics, 10:30-45, 2009。

[226] Lukáš Neumann and Jiří Matas. 使用高效剪枝穷举搜索进行现实世界图像中的文本定位 (Text localization in real-world images using efficiently pruned exhaustive search)。收录于 in Document Analysis and Recognition, 2011 International Conference on. IEEE, 2011, 第 687–691 页。

[227] Neumann, Matas L., and J.. 场景文本定位与识别 (Scene Text Localization and Recognition)。2012。

[228] Richard A. Newcombe, Dieter Fox, and Steven M. Seitz. DynamicFusion：实时非刚性场景的重建与跟踪 (DynamicFusion: Reconstruction and Tracking of Non-Rigid Scenes in Real-Time)。收录于 The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015年6月。

[229] Wayne Niblack. 数字图像处理导论 (An introduction to digital image processing)。Strandberg Publishing Company, 1985。

[230] David Nistér. 五点相对姿态问题的有效解决方案 (An efficient solution to the five-point relative pose problem)。Pattern Analysis and Machine Intelligence, IEEE Transactions on, 26(6):756–770, 2004。

[231] David Nistér and Henrik Stewénius. 线性时间最大稳定极值区域 (Linear time maximally stable extremal regions)。收录于 Computer Vision–ECCV 2008, 第 183–196 页。Springer, 2008。

[232] Mohammad Norouzi, Ali Punjani, and David J Fleet. 使用多索引哈希在汉明空间进行快速搜索 (Fast search in hamming space with multi-index hashing)。收录于 Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, 第 3108–3115 页, 2012。

[233] Joseph O’Rourke, Alok Aggarwal, Sanjeev Maddila, and Michael Baldwin. 寻找最小包含三角形的最佳算法 (An optimal algorithm for finding minimal enclosing triangles)。Journal of Algorithms, 7(2):258–269, 1986。

[234] Radim Hal oy and Jan Flusser. 椭圆拟合的数值稳定直接最小二乘法 (Numerically Stable Direct Least Squares Fitting of Ellipses)。1998。

[235] Philippe Paillou. 检测嘈杂 SAR 图像中的阶跃边缘：一种新的线性算子 (Detecting step edges in noisy SAR images: a new linear operator)。IEEE transactions on geoscience and remote sensing, 35(1):191–196, 1997。

[236] F. C. Park and B. J. Martin. 机器人传感器标定：求解欧几里得群上的 AX=XB (Robot sensor calibration: solving AX=XB on the Euclidean group)。IEEE Transactions on Robotics and Automation, 10(5):717-721, 1994年10月。

[237] Irina Perfilieva. 模糊变换：理论与应用 (Fuzzy transforms: Theory and applications)。Fuzzy sets and systems, 157(8):993–1023, 2006。

[238] Irina Perfilieva, Petra Hod’áková, and Petr Hurtík. 受 Canny 算法启发的人工 \(F^1\)-变换边缘检测器 (F^1-transform edge detector inspired by canny’s algorithm)。收录于 Advances on Computational Intelligence, 第 230–239 页。Springer, 2012。

[239] Irina Perfilieva, Petra Hodáková, and Petr Hurt’\ik. 通过 F-变换进行微分及其在边缘检测中的应用 (Differentiation by the F-transform and application to edge detection)。Fuzzy Sets and Systems, 2014。

[240] Irina Perfilieva and Pavel Vla\vsánek. 通过 F-变换进行图像重建 (Image Reconstruction by means of F-transform)。Knowledge-Based Systems, 70:55–63, 2014。

[241] E Persoon and King-Sun Fu. 使用傅里叶描述符的形状判别 (Shape Discrimination Using Fourier Descriptors)。IEEE Transactions on Pattern Analysis and Machine Intelligence, 7(3):170-179, 1977。

[242] Jan Puzicha, Thomas Hofmann, and Joachim M Buhmann. 用于无监督纹理分割和图像检索的非参数相似度量 (Non-parametric similarity measures for unsupervised texture segmentation and image retrieval)。收录于 Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on, 第 267–272 页。IEEE, 1997。

[243] Patrick Pérez, Michel Gangnet, and Andrew Blake. 泊松图像编辑 (Poisson image editing)。收录于 ACM Transactions on Graphics (TOG), 第 313–318 页。ACM, 2003。

[244] Tahir Rabbani, Frank van den Heuvel, and George Vosselman. 使用平滑约束的点云分割 (Segmentation of point clouds using smoothness constraints)。收录于 ISPRS 2006 : Proceedings of the ISPRS commission V symposium Vol. 35, part 6 : image engineering and vision metrology, Dresden, Germany 25-27 September 2006, 第 248–253 页, 2006。

[245] Deriche Rachid. 使用 Canny 准则推导递归实现的最佳边缘检测器 (Using Canny’s criteria to derive a recursively implemented optimal edge detector)。International journal of computer vision, 1(2):167–187, 1987。

[246] Richard E. Woods Rafael C. Gonzalez. 数字图像处理第 4 版 (Digital Image Processing 4th Edition)。Pearson, 2018。

[247] Sarunas J Raudys and Anil K. Jain. 统计模式识别中的小样本量效应：从业者建议 (Small sample size effects in statistical pattern recognition: Recommendations for practitioners)。IEEE Transactions on pattern analysis and machine intelligence, 13(3):252–264, 1991。

[248] Erik Reinhard and Kate Devlin. 受感光细胞生理学启发的动态范围压缩 (Dynamic range reduction inspired by photoreceptor physiology)。Visualization and Computer Graphics, IEEE Transactions on, 11(1):13–24, 2005。

[249] Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui, and Cordelia Schmid. EpicFlow：光流的边缘保持插值对应关系 (Edge-Preserving Interpolation of Correspondences for Optical Flow)。收录于 Computer Vision and Pattern Recognition (CVPR), IEEE Conference on, 第 1164–1172 页, 2015。

[250] Martin Riedmiller and Heinrich Braun. 更快反向传播学习的直接自适应方法：RPROP 算法 (A direct adaptive method for faster backpropagation learning: The RPROP algorithm)。收录于 Neural Networks, 1993., IEEE International Conference on, 第 586–591 页。IEEE, 1993。

[251] Mark A Robertson, Sean Borman, and Robert L Stevenson. 通过多重曝光进行动态范围改进 (Dynamic range improvement through multiple exposures)。收录于 Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on, 第 159–163 页。IEEE, 1999。

[252] Edward Rosten and Tom Drummond. 高速角点检测的机器学习 (Machine learning for high-speed corner detection)。收录于 Computer Vision–ECCV 2006, 第 430–443 页。Springer, 2006。

[253] Sam T Roweis and Lawrence K Saul. 通过局部线性嵌入的非线性降维 (Nonlinear dimensionality reduction by locally linear embedding)。science, 290(5500):2323–2326, 2000。

[254] Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. ORB：SIFT 或 SURF 的有效替代方案 (ORB: an efficient alternative to SIFT or SURF)。收录于 Computer Vision (ICCV), 2011 IEEE International Conference on, 第 2564–2571 页。IEEE, 2011。

[255] Yossi Rubner, Carlo Tomasi, and Leonidas J Guibas. 地球移动距离作为图像检索的度量 (The Earth Mover’s Distance as a Metric for Image Retrieval)。斯坦福大学, 1998。

[256] Yossi Rubner, Carlo Tomasi, and Leonidas J Guibas. 地球移动距离作为图像检索的度量 (The earth mover’s distance as a metric for image retrieval)。International Journal of Computer Vision, 40(2):99–121, 2000。

[257] Victoria Rudakova and Pascal Monasse. 图像中横向色差的精确校正 (Precise correction of lateral chromatic aberration in images)。收录于 Pacific-Rim Symposium on Image and Video Technology, 第 12–22 页, 2013。

[258] Samuele Salti, Andrea Cavallaro, and Luigi Di Stefano. 视频跟踪中的自适应外观建模：调查与评估 (Adaptive appearance modeling for video tracking: survey and evaluation)。Image Processing, IEEE Transactions on, 21(10):4334–4348, 2012。

[259] Joaquim Salvi, Jordi Pagés, and Joan Batlle. 结构光系统中的模式编码策略 (Pattern codification strategies in structured light systems)。Pattern Recognition, 37(4):827-849, 2004年4月。

[260] Jaakko Sauvola, Tapio Seppanen, Sami Haapakoski, and Matti Pietikainen. 自适应文档二值化 (Adaptive document binarization)。收录于 Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on, 第 147–152 页, 1997。

[261] Marios Savvides, B. V. K. Vijaya Kumar, and P. K. Khosla. 用于人脸识别的可取消生物特征过滤器 (Cancelable Biometric Filters for Face Recognition)。模式识别国际会议, 03:922-925, 2004。

[262] J. Seiler, M. Jonscher, M. Schöberl, and A. Kaup. 使用频率选择性重建将图像从像素位置的非规则子集重采样到规则网格 (Resampling Images to a Regular Grid From a Non-Regular Subset of Pixel Positions Using Frequency Selective Reconstruction)。IEEE Transactions on Image Processing, 24(11):4540-4555, 2015年11月。

[263] Tobias Senst, Volker Eiselein, and Thomas Sikora. 特征跟踪的鲁棒局部光流 (Robust Local Optical Flow for Feature Tracking)。IEEE Transactions on Circuits and Systems for Video Technology, 22(9):1377–1387, 2012。

[264] Tobias Senst, Jonas Geistert, Ivo Keller, and Thomas Sikora. 用于稀疏运动估计的基于双线性方程的鲁棒局部光流估计 (Robust Local Optical Flow Estimation using Bilinear Equations for Sparse Motion Estimation)。收录于 20th IEEE International Conference on Image Processing, 第 2499–2503 页, 2013。

[265] Tobias Senst, Thilo Borgmann, Ivo Keller, and Thomas Sikora. 基于交叉的鲁棒局部光流 (Cross based Robust Local Optical Flow)。收录于 21th IEEE International Conference on Image Processing, 第 1967–1971 页, 2014。

[266] Tobias Senst, Jonas Geistert, and Thomas Sikora. 鲁棒局部光流：长程运动和变化的光照 (Robust local optical flow: Long-range motions and varying illuminations)。收录于 IEEE International Conference on Image Processing, 第 4478–4482 页, 2016。

[267] Tobias Senst. 视频数据中的运动估计与分析 (Estimation and analysis of motion in video data)。2019。

[268] Byung-Kuk Seo, Hanhoon Park, Jong-Il Park, Stefan Hinterstoisser, and Slobodan Ilic. 用于高杂乱背景下无纹理 3D 目标快速鲁棒跟踪的局部搜索优化 (Optimal local searching for fast and robust textureless 3D object tracking in highly cluttered backgrounds)。IEEE transactions on visualization and computer graphics, 20(1):99–110, 2013。

[269] Mili Shah. 使用克罗内克积求解机器人-世界/手眼标定问题 (Solving the Robot-World/Hand-Eye Calibration Problem Using the Kronecker Product)。Journal of Mechanisms and Robotics, 5:031007, 2013。

[270] Ehsan Shahrian, Deepu Rajan, Brian Price, and Scott Cohen. 通过综合采样集改进图像抠图 (Improving image matting using comprehensive sampling sets)。收录于 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 第 636–643 页, 2013。

[271] Jianbo Shi and Carlo Tomasi. 良好的跟踪特征 (Good features to track)。收录于 Computer Vision and Pattern Recognition, 1994. Proceedings CVPR’94., 1994 IEEE Computer Society Conference on, 第 593–600 页。IEEE, 1994。

[272] Baoguang Shi, Xiang Bai, and Cong Yao. 一种用于基于图像的序列识别的端到端可训练神经网络及其在场景文本识别中的应用. IEEE模式分析与机器智能汇刊, 39(11):2298–2304, 2016.

[273] Heung-Yeung Shum and Richard Szeliski. 系统与实验论文：通过全局和局部对齐构建全景图像拼接. 国际计算机视觉期刊, 36(2):101–130, 2000.

[274] K. Simonyan, A. Vedaldi, and A. Zisserman. 使用凸优化学习局部特征描述子. IEEE模式分析与机器智能汇刊, 2014.

[275] Jack Sklansky. 寻找简单多边形的凸包. 模式识别快报, 1(2):79–83, 1982.

[276] Gregory G Slabaugh. 通过旋转矩阵计算欧拉角. 检索于8月, 6:2000, 1999.

[277] Jan Sochman and Jiri Matas. 用于时间约束序列检测的Waldboost学习. 载于 计算机视觉与模式识别，2005. CVPR 2005. IEEE计算机学会会议录, 第150–156页, 2005.

[278] Joan Solà, Jérémie Deray, and Dinesh Atchuthan. 机器人状态估计的李群微积分理论. ArXiv, abs/1812.01537, 2018.

[279] Robert Spangenberg, Tobias Langner, and Raúl Rojas. 用于鲁棒驾驶辅助的加权半全局匹配与中心对称普查变换. 载于 图像与模式的计算机分析, 第34–41页. 施普林格柏林海德堡出版社, 2013.

[280] Henrik Stewenius. 标定五点法求解器.

[281] Henrik Stewenius, Christopher Engels, and David Nister. 直接相对定向的最新进展. ISPRS摄影测量与遥感期刊, 60:284-294, 06 2006.

[282] Danail Stoyanov, Marco Visentini Scarzanella, Philip Pratt, and Guang-Zhong Yang. 机器人辅助微创手术中的实时立体重建. 载于 医学图像计算与计算机辅助干预 (MICCAI 2010), 第275–282页. 施普林格柏林海德堡出版社, 2010.

[283] Sabin Tiberius Strat, Alexandre Benoit, and Patrick Lambert. 用于视频索引的视网膜增强SIFT描述子. 载于 基于内容的多媒体索引 (CBMI)，2013年第11届国际研讨会, 第201–206页, 2013.

[284] S.T. Strat, A. Benoit, and P. Lambert. 用于视频分类的视网膜增强词袋描述子. 载于 信号处理会议 (EUSIPCO)，2014年第22届欧洲会议论文集, 第1307-1311页, 2014年9月.

[285] Klaus H. Strobl and Gerd Hirzinger. 利用不完美平面靶标进行更精确的针孔摄像机标定. 载于 2011 IEEE国际计算机视觉会议 (ICCV), 第1068-1075页. IEEE, 2011年11月.

[286] Satoshi Suzuki and others. 通过边界跟踪对数字化二值图像进行拓扑结构分析. 计算机视觉、图形学与图像处理, 30(1):32–46, 1985.

[287] Iago Suárez, Ghesn Sfeir, JoséM. Buenaposada, and Luis Baumela. BEBLID：提升效率的二值局部图像描述子. 模式识别快报, 133:366–372, 2020.

[288] Iago Suárez, JoséM. Buenaposada, and Luis Baumela. 重访资源受限设备上的二值局部图像描述. IEEE机器人与自动化快报, 6(4):8317–8324, 2021.

[289] R Szeliski. 图像对齐与拼接：教程，微软公司，华盛顿州雷德蒙德. MSR-TR-2004-92, 2004.

[290] Richard Szeliski. 图像对齐与拼接：教程. 计算机图形学与视觉基础与趋势\textregistered, 2(1):1–104, 2006.

[291] Richard Szeliski. 计算机视觉：算法与应用. 施普林格出版社, 2010.

[292] Javier Sánchez Pérez, Enric Meinhardt-Llopis, and Gabriele Facciolo. TV-L1光流估计. 2012.

[293] M. Christoudias, V. Lepetit T. Trzcinski and P. Fua. 提升二值关键点描述子. 载于 计算机视觉与模式识别, 2013.

[294] M. Christoudias T. Trzcinski and V. Lepetit. 用Boosting学习图像描述子. IEEE模式分析与机器智能汇刊 (PAMI), 2013.

[295] Xiaoyang Tan and Bill Triggs. 困难光照条件下人脸识别的增强局部纹理特征集. IEEE图像处理汇刊, 19(6):1635–1650, 2010.

[296] Zhenjun Tang, Yumin Dai, and Xianquan Zhang. 基于不变矩的彩色图像感知哈希. 应用数学, 6(2S):643S–650S, 2012.

[297] Michael Tao, Jiamin Bai, Pushmeet Kohli, and Sylvain Paris. SimpleFlow：一种非迭代、次线性的光流算法. 载于 计算机图形学论坛, 第345–353页, 2012.

[298] Gabriel Taubin. 隐式方程定义的平面曲线、曲面和非平面空间曲线的估计及其在边缘与距离图像分割中的应用. IEEE模式分析与机器智能汇刊, 13(11):1115–1138, 1991.

[299] C-H Teh and Roland T. Chin. 数字曲线上主点检测的研究. IEEE模式分析与机器智能汇刊, 11(8):859–872, 1989.

[300] Alexandru Telea. 一种基于快速行进法的图像修复技术. 图形工具期刊, 9(1):23–34, 2004.

[301] George Terzakis and Manolis Lourakis. 透视n点问题的持续快速且全局最优的解法. 载于 欧洲计算机视觉会议, 第478–494页. 施普林格国际出版社, 2020.

[302] Ryan J Tibshirani. 通过连续分箱进行中值快速计算. arXiv预印本 arXiv:0806.3301, 2008.

[303] E. Tola, V. Lepetit, and P. Fua. DAISY：一种应用于宽基线立体的有效稠密描述子. IEEE模式分析与机器智能汇刊, 32(5):815–830, 2010年5月.

[304] Federico Tombari and Luigi Di Stefano. 通过最大自差异性获取兴趣点. 载于 亚洲计算机视觉会议 – ACCV 2014, 2014.

[305] Cihan Topal and Cuneyt Akinlar. 边缘绘图：一种组合式实时边缘和线段检测器. 视觉通信与图像表示期刊, 23(6):862–872, 2012.

[306] Hastie Trevor, Tibshirani Robert, and Friedman Jerome. 统计学习要素：数据挖掘、推理与预测. 纽约：施普林格出版社, 1(8):371–406, 2001.

[307] Bill Triggs, Philip F. McLauchlan, Richard I. Hartley, and Andrew W. Fitzgibbon. 光束法平差——现代综合. 载于 视觉算法：理论与实践, 第298–372页. 施普林格出版社, 2000.

[308] R. Y. Tsai and R. K. Lenz. 一种全自主且高效的3D机器人手眼标定新技术. IEEE机器人与自动化汇刊, 5(3):345-358, 1989年6月.

[309] Chiara Turati, Viola Macchi Cassia, Francesca Simion, and Irene Leo. 新生儿的人脸识别：内部和外部面部特征的作用. 儿童发展, 77(2):297–311, 2006.

[310] Matthew Turk and Alex Pentland. 用于识别的特征脸. 认知神经科学期刊, 3(1):71–86, 1991.

[311] Jasper RR Uijlings, Koen EA van de Sande, Theo Gevers, and Arnold WM Smeulders. 用于目标识别的选择性搜索. 国际计算机视觉期刊, 104(2):154–171, 2013.

[312] Shinji Umeyama. 两点集之间转换参数的最小二乘估计. IEEE计算机架构快报, 13(04):376–380, 1991.

[313] Matthew Uyttendaele, Ashley Eden, and R Skeliski. 消除图像拼接中的重影和曝光伪影. 载于 计算机视觉与模式识别，2001. CVPR 2001. 2001年IEEE计算机学会会议论文集, 第II–509页. IEEE, 2001.

[314] Antoine Vacavant, Thierry Chateau, Alexis Wilhelm, and Laurent Lequièvre. 户外前景/背景提取的基准数据集. 载于 计算机视觉-ACCV 2012研讨会, 第291–300页. 施普林格出版社, 2013.

[315] Marek Vajgl, Irina Perfilieva, and Petra Hod’áková. 基于F-变换的先进图像融合. 模糊系统进展, 2012:4, 2012.

[316] Michael Van den Bergh, Xavier Boix, Gemma Roig, Benjamin de Capitani, and Luc Van Gool. SEEDS：通过能量驱动采样提取的超像素. 载于 计算机视觉–ECCV 2012, 第13–26页. 施普林格出版社, 2012.

[317] Lucas J Van Vliet and Piet W Verbeek. 数字化图像中方向和各向异性的估计器. 载于 ASCI, 第16–18页, 1995.

[318] Lieven Vandenberghe. QR分解.

[319] Paul Viola and Michael J. Jones. 使用简单特征的提升级联进行快速目标检测. 载于 计算机视觉与模式识别，2001. CVPR 2001. 2001年IEEE计算机学会会议论文集, 第I–511页. IEEE, 2001.

[320] Paul Viola and Michael J. Jones. 鲁棒的实时人脸检测. 国际计算机视觉期刊, 57(2):137–154, 2004.

[321] Pavel Vla\vsánek and Irina Perfilieva. 基于F1-变换的块修复方法. 载于 软计算与模式识别 (SoCPaR)，2015年第7届国际会议, 第235–240页, 2015.

[322] Pavel Vla\vsánek and Irina Perfilieva. 图像处理工具视角下的F-变换. 模糊集值分析期刊, 2016(1):54–62, 2016.

[323] R Grompone Von Gioi, Jeremie Jakubowicz, Jean-Michel Morel, and Gregory Randall. LSD：一种具有误检测控制的快速线段检测器. IEEE模式分析与机器智能汇刊, 32(4):722–732, 2010.

[324] Bin Wang and Piotr Dudek. 一种快速自调优背景减除算法. 载于 计算机视觉与模式识别研讨会 (CVPRW)，2014 IEEE会议, 第401–404页, 2014.

[325] Guofeng Wang, Bin Wang, Fan Zhong, Xueying Qin, and Baoquan Chen. 无纹理3D对象跟踪的全局最优搜索. 视觉计算机, 31(6):979–988, 2015.

[326] John Wang and Edwin Olson. AprilTag 2：高效且鲁棒的基准检测. 载于 IEEE/RSJ智能机器人与系统国际会议论文集 (IROS), 2016年10月.

[327] Shenlong Wang, Sean Ryan Fanello, Christoph Rhemann, Shahram Izadi, and Pushmeet Kohli. 全局块对撞机. 载于 IEEE计算机视觉与模式识别会议 (CVPR), 2016年6月.

[328] Greg Ward. 从手持拍摄合成高动态范围照片的快速、鲁棒图像配准. 图形工具期刊, 8(2):17–30, 2003.

[329] Philippe Weinzaepfel, Jerome Revaud, Zaid Harchaoui, and Cordelia Schmid. DeepFlow：具有深度匹配的大位移光流. 载于 计算机视觉 (ICCV)，2013 IEEE国际会议, 第1385–1392页, 2013.

[330] Greg Welch and Gary Bishop. 卡尔曼滤波导论. 1995.

[331] Simon AJ Winder and Matthew Brown. 学习局部图像描述子. 载于 计算机视觉与模式识别, 第1–8页, 2007.

[332] Laurenz Wiskott, J-M Fellous, N Kuiger, and Christoph Von Der Malsburg. 基于弹性束图匹配的人脸识别. IEEE模式分析与机器智能汇刊, 19(7):775–779, 1997.

[333] Paul Wohlhart and Vincent Lepetit. 学习用于目标识别和3D姿态估计的描述子. 载于 IEEE计算机视觉与模式识别会议论文集, 2015.

[334] Christian Wolf and J-M Jolion. 多媒体文档中人工文本的提取与识别. 模式分析与应用, 6(4):309–326, 2004.

[335] Kesheng Wu, Ekow Otoo, and Kenji Suzuki. 优化两遍连通分量标记算法. 模式分析与应用, 12(2):117-135, 2009年6月.

[336] Yi Wu, Jongwoo Lim, and Ming-Hsuan Yang. 在线对象跟踪：基准测试. 载于 计算机视觉与模式识别 (CVPR)，2013 IEEE会议, 第2411–2418页, 2013.

[337] Bichen Wu, Forrest Iandola, Peter H. Jin, and Kurt Keutzer. SqueezeDet：用于自动驾驶实时目标检测的统一、小型、低功耗全卷积神经网络. 2016.

[338] Jonas Wulff and Michael J. Black. 使用学习基础和层的有效稀疏到稠密光流估计. 载于 IEEE计算机视觉与模式识别会议 (CVPR) 2015, 2015年6月.

[339] Wang Xiangmin. 复杂背景下条形码识别技术的研究. 2015.

[340] Wei Xu and Jane Mulligan. 自动多视图图像和视频拼接色彩校正方法的性能评估. 载于 计算机视觉与模式识别 (CVPR)，2010 IEEE会议, 第263–270页. IEEE, 2010.

[341] Li Xu, Cewu Lu, Yi Xu, and Jiaya Jia. 通过L0梯度最小化进行图像平滑. 载于 ACM图形学汇刊 (TOG), 第174页, 2011.

[342] Y. Xu, P. Monasse, T. Géraud, and L. Najman. 基于树的Morse区域：一种局部特征检测的拓扑方法. IEEE图像处理汇刊, 23(12):5612-5625, 2014年12月.

[343] Guang-Zhong Yang, Peter Burger, David N Firmin, and SR Underwood. 结构自适应各向异性图像滤波. 图像与视觉计算, 14(2):135–145, 1996.

[344] Qingxiong Yang, Liang Wang, and Narendra Ahuja. 一种用于立体匹配的恒定空间置信传播算法. 载于 计算机视觉与模式识别 (CVPR)，2010 IEEE会议, 第1458–1465页. IEEE, 2010.

[345] Zhenqiang Ying, Ge Li, and Wen Gao. 一种用于低光图像增强的生物启发多曝光融合框架. arXiv预印本 arXiv:1711.00591, 2017.

[346] Zhenqiang Ying, Ge Li, Yurui Ren, Ronggang Wang, and Wenmin Wang. 一种使用曝光融合框架的新型图像对比度增强算法. 载于 图像与模式计算机分析国际会议, 第36–46页, 2017.

[347] Guoshen Yu and Jean-Michel Morel. ASIFT：一种全仿射不变比较算法. 图像处理在线, 1:11–38, 2011.

[348] HK Yuen, John Princen, John Illingworth, and Josef Kittler. 圆检测霍夫变换方法的比较研究. 图像与视觉计算, 8(1):71–77, 1990.

[349] Christopher Zach, Thomas Pock, and Horst Bischof. 一种用于实时TV-L1光流的对偶方法. 载于 模式识别, 第214–223页. 施普林格出版社, 2007.

[350] Christoph Zauner. 感知图像哈希函数的实现与基准测试. na, 2010.

[351] Zhengyou Zhang. 一种灵活的相机标定新方法. IEEE模式分析与机器智能汇刊, 22(11):1330–1334, 2000.

[352] Lilian Zhang and Reinhard Koch. 一种基于LBD描述子和成对几何一致性的高效且鲁棒的线段匹配方法. 视觉通信与图像表示期刊, 24(7):794–805, 2013.

[353] Qi Zhang, Li Xu, and Jiaya Jia. 100多倍快速的加权中值滤波器 (WMF). 载于 计算机视觉与模式识别 (CVPR)，2014 IEEE会议, 第2830–2837页, 2014.

[354] Qi Zhang, Xiaoyong Shen, Li Xu, and Jiaya Jia. 滚动导向滤波器. 载于 计算机视觉–ECCV 2014, 第815–830页. 施普林格出版社, 2014.

[355] Wenyi Zhao, Rama Chellappa, P Jonathon Phillips, and Azriel Rosenfeld. 人脸识别：文献综述. ACM计算综述 (CSUR), 35(4):399–458, 2003.

[356] Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, and Jiajun Liang. EAST：一种高效且准确的场景文本检测器. 载于 IEEE计算机视觉与模式识别会议论文集, 第5551–5560页, 2017.

[357] Andrew, Eric Christiansen, David Kriegman, Ziegler and Serge J. Belongie. 局部均匀比较图像描述子. 载于 神经信息处理系统进展, 第1–9页. NIPS, 2012.

[358] Timo Zinßer, Jochen Schmidt, and Heinrich Niemann. 一种用于鲁棒3D对应估计的改进ICP算法. 载于 图像处理，2003. ICIP 2003. 2003年国际会议论文集, 第II–695页, 2003.

[359] C. Lawrence Zitnick and Piotr Dollár. Edge Boxes：从边缘定位目标建议. 载于 ECCV, 2014.

[360] Zoran Zivkovic. 用于背景减除的改进自适应高斯混合模型. 载于 模式识别，2004. ICPR 2004. 第17届国际会议论文集, 第28–31页. IEEE, 2004.

[361] Zoran Zivkovic and Ferdinand van der Heijden. 用于背景减除任务的图像像素级高效自适应密度估计. 模式识别快报, 27(7):773–780, 2006.

[362] Marco Zuliani. RANSAC入门：使用Matlab & Octave等RANSAC工具箱的示例. 2014.

[363] 对比度拉伸.

[364] CS425实验：强度变换与空间滤波.

[365] И.С. Грузман, В.С. Киричук, В.П. Косых, Г.И. Перетягин, and А.А. Спектор. 信息系统中的数字图像处理. 新西伯利亚国立技术大学出版社, 2000.