samples/cpp/train_HOG.cpp

#include "opencv2/imgproc.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/ml.hpp"
#include "opencv2/objdetect.hpp"
#include "opencv2/videoio.hpp"
#include <iostream>
#include <time.h>
 
using namespace cv;
using namespace cv::ml;
using namespace std;
 
vector< float > get_svm_detector( const Ptr< SVM >& svm );
void convert_to_ml( const std::vector< Mat > & train_samples, Mat& trainData );
void load_images( const String & dirname, vector< Mat > & img_lst, bool showImages );
void sample_neg( const vector< Mat > & full_neg_lst, vector< Mat > & neg_lst, const Size & size );
void computeHOGs( const Size wsize, const vector< Mat > & img_lst, vector< Mat > & gradient_lst, bool use_flip );
void test_trained_detector( String obj_det_filename, String test_dir, String videofilename );
 
vector< float > get_svm_detector( const Ptr< SVM >& svm )
{
    // 获取支持向量
    Mat sv = svm->getSupportVectors();
    const int sv_total = sv.rows;
    // 获取决策函数
    Mat alpha, svidx;
    double rho = svm->getDecisionFunction( 0, alpha, svidx );
 
    CV_Assert( alpha.total() == 1 && svidx.total() == 1 && sv_total == 1 );
    CV_Assert( (alpha.type() == CV_64F && alpha.at<double>(0) == 1.) ||
(alpha.type() == CV_32F && alpha.at<float>(0) == 1.f) );
    CV_Assert( sv.type() == CV_32F );
 
vector< float > hog_detector( sv.cols + 1 );
memcpy( &hog_detector[0], sv.ptr(), sv.cols*sizeof( hog_detector[0] ) );
hog_detector[sv.cols] = (float)-rho;
    return hog_detector;
}
 
/*
* 将训练/测试集转换为OpenCV机器学习算法可用的格式。
* TrainData是一个大小为（样本数 x 样本最大列数/行数）的矩阵，类型为32FC1。
* 如有必要，会对样本进行转置。
*/
void convert_to_ml( const vector< Mat > & train_samples, Mat& trainData )
{
    //--转换数据
    const int rows = (int)train_samples.size();
    const int cols = (int)std::max( train_samples[0].cols, train_samples[0].rows );
    Mat tmp( 1, cols, CV_32FC1 );
trainData = Mat( rows, cols, CV_32FC1 );
 
    for( size_t i = 0 ; i < train_samples.size(); ++i )
    {
        CV_Assert( train_samples[i].cols == 1 || train_samples[i].rows == 1 );
 
        if( train_samples[i].cols == 1 )
        {
transpose( train_samples[i], tmp );
tmp.copyTo( trainData.row( (int)i ) );
        }
        else if( train_samples[i].rows == 1 )
        {
train_samples[i].copyTo( trainData.row( (int)i ) );
        }
    }
}
 
void load_images( const String & dirname, vector< Mat > & img_lst, bool showImages = false )
{
vector< String > files;
    glob( dirname, files );
 
    for ( size_t i = 0; i < files.size(); ++i )
    {
        Mat img = imread( files[i] ); // 加载图像
        if ( img.empty() )
        {
cout << files[i] << " is invalid!" << endl; // 无效图像，跳过。
            continue;
        }
 
        如果 (showImages)
        {
            imshow( "image", img );
            waitKey( 1 );
        }
img_lst.push_back( img );
    }
}
 
void sample_neg( const vector< Mat > & full_neg_lst, vector< Mat > & neg_lst, const Size & size )
{
    Rect box;
box.width = size.width;
box.height = size.height;
 
srand( (unsigned int)time( NULL ) );
 
    for ( size_t i = 0; i < full_neg_lst.size(); i++ )
        如果 ( full_neg_lst[i].cols > box.width && full_neg_lst[i].rows > box.height )
        {
box.x = rand() % ( full_neg_lst[i].cols - box.width );
box.y = rand() % ( full_neg_lst[i].rows - box.height );
            Mat roi = full_neg_lst[i]( box );
neg_lst.push_back( roi.clone() );
        }
}
 
void computeHOGs( const Size wsize, const vector< Mat > & img_lst, vector< Mat > & gradient_lst, bool use_flip )
{
    HOGDescriptor hog;
hog.winSize = wsize;
    Mat gray;
vector< float > descriptors;
 
    for( size_t i = 0 ; i < img_lst.size(); i++ )
    {
        如果 ( img_lst[i].cols >= wsize.width && img_lst[i].rows >= wsize.height )
        {
            Rect r = Rect(( img_lst[i].cols - wsize.width ) / 2,
( img_lst[i].rows - wsize.height ) / 2,
wsize.width,
wsize.height);
            cvtColor( img_lst[i](r), gray, COLOR_BGR2GRAY );
hog.compute( gray, descriptors, Size( 8, 8 ), Size( 0, 0 ) );
gradient_lst.push_back( Mat( descriptors ).clone() );
            如果 ( use_flip )
            {
                flip( gray, gray, 1 );
hog.compute( gray, descriptors, Size( 8, 8 ), Size( 0, 0 ) );
gradient_lst.push_back( Mat( descriptors ).clone() );
            }
        }
    }
}
 
void test_trained_detector( String obj_det_filename, String test_dir, String videofilename )
{
cout << "正在测试训练好的检测器..." << endl;
    HOGDescriptor hog;
hog.load( obj_det_filename );
 
vector< String > files;
    glob( test_dir, files );
 
    int delay = 0;
    VideoCapture cap;
 
    如果 ( videofilename != "" )
    {
        如果 ( videofilename.size() == 1 && isdigit( videofilename[0] ) )
cap.open( videofilename[0] - '0' );
        否则
cap.open( videofilename );
    }
 
obj_det_filename = "testing " + obj_det_filename;
    namedWindow( obj_det_filename, WINDOW_NORMAL );
 
    for( size_t i=0;; i++ )
    {
        Mat img;
 
        如果 ( cap.isOpened() )
        {
cap >> img;
delay = 1;
        }
        否则如果( i < files.size() )
        {
img = imread( files[i] );
        }
 
        如果 ( img.empty() )
        {
            返回;
        }
 
vector< Rect > detections;
vector< double > foundWeights;
 
hog.detectMultiScale( img, detections, foundWeights );
        for ( size_t j = 0; j < detections.size(); j++ )
        {
            Scalar color = Scalar( 0, foundWeights[j] * foundWeights[j] * 200, 0 );
            rectangle( img, detections[j], color, img.cols / 400 + 1 );
        }
 
        imshow( obj_det_filename, img );
 
        如果(waitKey( delay ) == 27 )
        {
            返回;
        }
    }
}
 
int main( int argc, char** argv )
{
    const char* keys =
    {
        "{help h| | 显示帮助信息}"
        "{pd | | 包含正样本图像的目录路径}"
        "{nd | | 包含负样本图像的目录路径}"
        "{td | | 包含测试图像的目录路径}"
        "{tv | | 测试视频文件名}"
        "{dw | | 检测器的宽度}"
        "{dh | | 检测器的高度}"
        "{f |false| 指示程序是否生成并使用镜像样本}"
        "{d |false| 训练两次}"
        "{t |false| 测试训练好的检测器}"
        "{v |false| 可视化训练步骤}"
        "{fn |my_detector.yml| 训练好的SVM文件名}"
    };
 
    CommandLineParser parser( argc, argv, keys );
 
    如果 (parser.has("help"))
    {
parser.printMessage();
exit(0);
    }
 
    String pos_dir = parser.get<String>("pd");
    String neg_dir = parser.get<String>("nd");
    String test_dir = parser.get<String>("td");
    String obj_det_filename = parser.get<String>("fn");
    String videofilename = parser.get<String>("tv");
    int detector_width = parser.get<int>("dw");
    int detector_height = parser.get<int>("dh");
    bool test_detector = parser.get<bool>("t");
    bool train_twice = parser.get<bool>("d");
    bool visualization = parser.get<bool>("v");
    bool flip_samples = parser.get<bool>("f");
 
    如果 (test_detector)
    {
test_trained_detector(obj_det_filename, test_dir, videofilename);
exit(0);
    }
 
    如果 (pos_dir.empty() || neg_dir.empty())
    {
parser.printMessage();
cout << "参数数量错误。\n\n"
<< "示例命令行：\n" << argv[0] << " -dw=64 -dh=128 -pd=/INRIAPerson/96X160H96/Train/pos -nd=/INRIAPerson/neg -td=/INRIAPerson/Test/pos -fn=HOGpedestrian64x128.xml -d\n"
<< "\n测试已训练检测器的示例命令行：\n" << argv[0] << " -t -fn=HOGpedestrian64x128.xml -td=/INRIAPerson/Test/pos";
exit(1);
    }
 
vector<Mat> pos_lst, full_neg_lst, neg_lst, gradient_lst;
vector<int> labels;
 
clog << "正在加载正样本图像...";
load_images(pos_dir, pos_lst, visualization);
    如果 (pos_lst.size() > 0)
    {
clog << "...[完成] " << pos_lst.size() << " 个文件。" << endl;
    }
    否则
    {
clog << "在 " << pos_dir << " 中没有图像" << endl;
        返回 1;
    }
 
    Size pos_image_size = pos_lst[0].size();
 
    如果 (detector_width && detector_height)
    {
pos_image_size = Size(detector_width, detector_height);
    }
    否则
    {
        for (size_t i = 0; i < pos_lst.size(); ++i)
        {
            如果 (pos_lst[i].size() != pos_image_size)
            {
cout << "所有正样本图像的大小应该相同！" << endl;
exit(1);
            }
        }
pos_image_size = pos_image_size / 8 * 8;
    }
 
clog << "正在加载负样本图像...";
load_images(neg_dir, full_neg_lst, visualization);
clog << "...[完成] " << full_neg_lst.size() << " 个文件。" << endl;
 
clog << "正在处理负样本图像...";
sample_neg(full_neg_lst, neg_lst, pos_image_size);
clog << "...[完成] " << neg_lst.size() << " 个文件。" << endl;
 
clog << "正在计算正样本图像的梯度直方图...";
computeHOGs(pos_image_size, pos_lst, gradient_lst, flip_samples);
    size_t positive_count = gradient_lst.size();
labels.assign(positive_count, +1);
clog << "...[完成] (正样本图像数量：" << positive_count << " )" << endl;
 
clog << "正在计算负样本图像的梯度直方图...";
computeHOGs(pos_image_size, neg_lst, gradient_lst, flip_samples);
    size_t negative_count = gradient_lst.size() - positive_count;
labels.insert(labels.end(), negative_count, -1);
    CV_Assert(positive_count < labels.size());
clog << "...[完成] (负样本图像数量：" << negative_count << " )" << endl;
 
    Mat train_data;
convert_to_ml(gradient_lst, train_data);
 
clog << "正在训练SVM...";
    Ptr<SVM> svm = SVM::create();
    /* 训练SVM的默认值 */
svm->setCoef0(0.0);
svm->setDegree(3);
svm->setTermCriteria(TermCriteria(TermCriteria::MAX_ITER + TermCriteria::EPS, 1000, 1e-3));
svm->setGamma(0);
svm->setKernel(SVM::LINEAR);
svm->setNu(0.5);
svm->setP(0.1); // 对于EPSILON_SVR，损失函数中的epsilon？
svm->setC(0.01); // 来自论文，软分类器
svm->setType(SVM::EPS_SVR); // C_SVC; // EPSILON_SVR; // 也可能是NU_SVR; // 执行回归任务
svm->train(train_data, ROW_SAMPLE, labels);
clog << "...[完成]" << endl;
 
    如果 (train_twice)
    {
clog << "正在使用负样本图像测试已训练的检测器。这可能需要几分钟...";
        HOGDescriptor my_hog;
my_hog.winSize = pos_image_size;
 
        // 将训练好的svm设置为my_hog
my_hog.setSVMDetector(get_svm_detector(svm));
 
vector< Rect > detections;
vector< double > foundWeights;
 
        for ( size_t i = 0; i < full_neg_lst.size(); i++ )
        {
            如果 (full_neg_lst[i].cols >= pos_image_size.width && full_neg_lst[i].rows >= pos_image_size.height)
my_hog.detectMultiScale(full_neg_lst[i], detections, foundWeights);
            否则
detections.clear();
 
            for ( size_t j = 0; j < detections.size(); j++ )
            {
                Mat detection = full_neg_lst[i](detections[j]).clone();
                resize(detection, detection, pos_image_size, 0, 0, INTER_LINEAR_EXACT);
neg_lst.push_back(detection);
            }
 
            如果 (visualization)
            {
                for ( size_t j = 0; j < detections.size(); j++ )
                {
                    rectangle(full_neg_lst[i], detections[j], Scalar(0, 255, 0), 2);
                }
                imshow("使用负样本图像测试已训练的检测器", full_neg_lst[i]);
                waitKey( 5 );
            }
        }
clog << "...[完成]" << endl;
 
gradient_lst.clear();
clog << "正在计算正样本图像的梯度直方图...";
computeHOGs(pos_image_size, pos_lst, gradient_lst, flip_samples);
positive_count = gradient_lst.size();
clog << "...[完成] ( 正样本数 : " << positive_count << " )" << endl;
 
clog << "正在计算负样本图像的梯度直方图...";
computeHOGs(pos_image_size, neg_lst, gradient_lst, flip_samples);
negative_count = gradient_lst.size() - positive_count;
clog << "...[完成] ( 负样本数 : " << negative_count << " )" << endl;
 
labels.clear();
labels.assign(positive_count, +1);
labels.insert(labels.end(), negative_count, -1);
 
clog << "再次训练SVM...";
convert_to_ml(gradient_lst, train_data);
svm->train(train_data, ROW_SAMPLE, labels);
clog << "...[完成]" << endl;
    }
 
    HOGDescriptor hog;
hog.winSize = pos_image_size;
hog.setSVMDetector( get_svm_detector( svm ) );
hog.save( obj_det_filename );
 
test_trained_detector(obj_det_filename, test_dir, videofilename);
 
    返回 0;
}