视频稳定模块包含一组可用于解决视频稳定问题的函数和类。实现了几种方法,其中大多数方法在论文[187]和[112]中有所描述。但是,与原始论文的方法相比,存在一些扩展和偏差。
参考文献
- “基于运动修复的全帧视频稳定” Yasuyuki Matsushita, Eyal Ofek, Weina Ge, Xiaoou Tang, 高级会员, and Heung-Yeung Shum
- “具有鲁棒L1最优相机路径的自动定向视频稳定” Matthias Grundmann, Vivek Kwatra, Irfan Essa
|
| cv::videostab::ColorInpainter::ColorInpainter (int method=INPAINT_TELEA, double radius=2.) |
|
模板<typename T > |
const T & | cv::videostab::at (int idx, const std::vector< T > &items) |
|
模板<typename T > |
T & | cv::videostab::at (int idx, std::vector< T > &items) |
|
float | cv::videostab::calcBlurriness (const Mat &frame) |
|
void | cv::videostab::calcFlowMask (const Mat &flowX, const Mat &flowY, const Mat &errors, float maxError, const Mat &mask0, const Mat &mask1, Mat &flowMask) |
|
void | cv::videostab::completeFrameAccordingToFlow (const Mat &flowMask, const Mat &flowX, const Mat &flowY, const Mat &frame1, const Mat &mask1, float distThresh, Mat &frame0, Mat &mask0) |
|
◆ ColorInpainter()
cv::videostab::ColorInpainter::ColorInpainter |
( |
int | method = INPAINT_TELEA, |
|
|
double | radius = 2. ) |
|
内联 |
◆ at() [1/2]
模板<typename T >
const T & cv::videostab::at |
( |
int | idx, |
|
|
const std::vector< T > & | items ) |
|
内联 |
◆ at() [2/2]
模板<typename T >
T & cv::videostab::at |
( |
int | idx, |
|
|
std::vector< T > & | items ) |
|
内联 |
◆ calcBlurriness()
float cv::videostab::calcBlurriness |
( |
const Mat & | frame | ) |
|
◆ calcFlowMask()
void cv::videostab::calcFlowMask |
( |
const Mat & | flowX, |
|
|
const Mat & | flowY, |
|
|
const Mat & | errors, |
|
|
float | maxError, |
|
|
const Mat & | mask0, |
|
|
const Mat & | mask1, |
|
|
Mat & | flowMask ) |
◆ completeFrameAccordingToFlow()
void cv::videostab::completeFrameAccordingToFlow |
( |
const Mat & | flowMask, |
|
|
const Mat & | flowX, |
|
|
const Mat & | flowY, |
|
|
const Mat & | frame1, |
|
|
const Mat & | mask1, |
|
|
float | distThresh, |
|
|
Mat & | frame0, |
|
|
Mat & | mask0 ) |