OpenCV官方：AKAZE和ORB目标检测对比
OpenCV官方：AKAZE和ORB目标检测对比
小锋学长生活大爆炸
发布于 2021-10-19 09:48:05
发布于 2021-10-19 09:48:05
介绍
在本教程中，我们将使用AKAZE和ORB本地特性来查找视频帧之间的匹配和跟踪对象运动。 算法如下:
- 检测和描述第一帧的关键点，手动设置对象边界
- 对于每一帧:
- 检测并描述关键点
- 使用brute匹配器匹配它们
- 用RANSAC估计单应变换
- 过滤所有匹配的嵌套
- 对边界框应用单应变换来找到对象
- 绘制边界框和嵌线，计算嵌线比率作为评价指标
数据
为了进行跟踪，我们需要视频和对象的位置在第一帧。 你可以从这里下载我们的示例视频和数据。 要运行代码，你必须指定输入和输出视频路径和对象边界框。
./planar_tracking blais.mp4 result.avi blais_bb.xml.gz源程序
#include <opencv2/features2d.hpp>
#include <opencv2/videoio.hpp>
#include <opencv2/opencv.hpp>
#include <vector>
#include <iostream>
#include <iomanip>
#include "stats.h" // Stats structure definition
#include "utils.h" // Drawing and printing functions
using namespace std;
using namespace cv;
const double akaze_thresh = 3e-4; // AKAZE detection threshold set to locate about 1000 keypoints
const double ransac_thresh = 2.5f; // RANSAC inlier threshold
const double nn_match_ratio = 0.8f; // Nearest-neighbour matching ratio
const int bb_min_inliers = 100; // Minimal number of inliers to draw bounding box
const int stats_update_period = 10; // On-screen statistics are updated every 10 frames
class Tracker
{
public:
Tracker(Ptr<Feature2D> _detector, Ptr<DescriptorMatcher> _matcher) :
detector(_detector),
matcher(_matcher)
{}
void setFirstFrame(const Mat frame, vector<Point2f> bb, string title, Stats& stats);
Mat process(const Mat frame, Stats& stats);
Ptr<Feature2D> getDetector() {
return detector;
}
protected:
Ptr<Feature2D> detector;
Ptr<DescriptorMatcher> matcher;
Mat first_frame, first_desc;
vector<KeyPoint> first_kp;
vector<Point2f> object_bb;
};
void Tracker::setFirstFrame(const Mat frame, vector<Point2f> bb, string title, Stats& stats)
{
first_frame = frame.clone();
detector->detectAndCompute(first_frame, noArray(), first_kp, first_desc);
stats.keypoints = (int)first_kp.size();
drawBoundingBox(first_frame, bb);
putText(first_frame, title, Point(0, 60), FONT_HERSHEY_PLAIN, 5, Scalar::all(0), 4);
object_bb = bb;
}
Mat Tracker::process(const Mat frame, Stats& stats)
{
vector<KeyPoint> kp;
Mat desc;
detector->detectAndCompute(frame, noArray(), kp, desc);
stats.keypoints = (int)kp.size();
vector< vector<DMatch> > matches;
vector<KeyPoint> matched1, matched2;
matcher->knnMatch(first_desc, desc, matches, 2);
for(unsigned i = 0; i < matches.size(); i++) {
if(matches[i][0].distance < nn_match_ratio * matches[i][1].distance) {
matched1.push_back(first_kp[matches[i][0].queryIdx]);
matched2.push_back( kp[matches[i][0].trainIdx]);
}
}
stats.matches = (int)matched1.size();
Mat inlier_mask, homography;
vector<KeyPoint> inliers1, inliers2;
vector<DMatch> inlier_matches;
if(matched1.size() >= 4) {
homography = findHomography(Points(matched1), Points(matched2),
RANSAC, ransac_thresh, inlier_mask);
}
if(matched1.size() < 4 || homography.empty()) {
Mat res;
hconcat(first_frame, frame, res);
stats.inliers = 0;
stats.ratio = 0;
return res;
}
for(unsigned i = 0; i < matched1.size(); i++) {
if(inlier_mask.at<uchar>(i)) {
int new_i = static_cast<int>(inliers1.size());
inliers1.push_back(matched1[i]);
inliers2.push_back(matched2[i]);
inlier_matches.push_back(DMatch(new_i, new_i, 0));
}
}
stats.inliers = (int)inliers1.size();
stats.ratio = stats.inliers * 1.0 / stats.matches;
vector<Point2f> new_bb;
perspectiveTransform(object_bb, new_bb, homography);
Mat frame_with_bb = frame.clone();
if(stats.inliers >= bb_min_inliers) {
drawBoundingBox(frame_with_bb, new_bb);
}
Mat res;
drawMatches(first_frame, inliers1, frame_with_bb, inliers2,
inlier_matches, res,
Scalar(255, 0, 0), Scalar(255, 0, 0));
return res;
}
int main(int argc, char **argv)
{
if(argc < 4) {
cerr << "Usage: " << endl <<
"akaze_track input_path output_path bounding_box" << endl;
return 1;
}
VideoCapture video_in(argv[1]);
VideoWriter video_out(argv[2],
(int)video_in.get(CAP_PROP_FOURCC),
(int)video_in.get(CAP_PROP_FPS),
Size(2 * (int)video_in.get(CAP_PROP_FRAME_WIDTH),
2 * (int)video_in.get(CAP_PROP_FRAME_HEIGHT)));
if(!video_in.isOpened()) {
cerr << "Couldn't open " << argv[1] << endl;
return 1;
}
if(!video_out.isOpened()) {
cerr << "Couldn't open " << argv[2] << endl;
return 1;
}
vector<Point2f> bb;
FileStorage fs(argv[3], FileStorage::READ);
if(fs["bounding_box"].empty()) {
cerr << "Couldn't read bounding_box from " << argv[3] << endl;
return 1;
}
fs["bounding_box"] >> bb;
Stats stats, akaze_stats, orb_stats;
Ptr<AKAZE> akaze = AKAZE::create();
akaze->set("threshold", akaze_thresh);
Ptr<ORB> orb = ORB::create();
orb->setMaxFeatures(stats.keypoints);
Ptr<DescriptorMatcher> matcher = DescriptorMatcher::create("BruteForce-Hamming");
Tracker akaze_tracker(akaze, matcher);
Tracker orb_tracker(orb, matcher);
Mat frame;
video_in >> frame;
akaze_tracker.setFirstFrame(frame, bb, "AKAZE", stats);
orb_tracker.setFirstFrame(frame, bb, "ORB", stats);
Stats akaze_draw_stats, orb_draw_stats;
int frame_count = (int)video_in.get(CAP_PROP_FRAME_COUNT);
Mat akaze_res, orb_res, res_frame;
for(int i = 1; i < frame_count; i++) {
bool update_stats = (i % stats_update_period == 0);
video_in >> frame;
akaze_res = akaze_tracker.process(frame, stats);
akaze_stats += stats;
if(update_stats) {
akaze_draw_stats = stats;
}
orb_tracker.getDetector()->set("nFeatures", stats.keypoints);
orb_res = orb_tracker.process(frame, stats);
orb_stats += stats;
if(update_stats) {
orb_draw_stats = stats;
}
drawStatistics(akaze_res, akaze_draw_stats);
drawStatistics(orb_res, orb_draw_stats);
vconcat(akaze_res, orb_res, res_frame);
video_out << res_frame;
cout << i << "/" << frame_count - 1 << endl;
}
akaze_stats /= frame_count - 1;
orb_stats /= frame_count - 1;
printStatistics("AKAZE", akaze_stats);
printStatistics("ORB", orb_stats);
return 0;
}解释
类追踪器
这个类使用给定的特征检测器和描述符匹配器实现上述算法。
- 设置第一个帧
void Tracker::setFirstFrame(const Mat frame, vector<Point2f> bb, string title, Stats& stats)
{
first_frame = frame.clone();
(*detector)(first_frame, noArray(), first_kp, first_desc);
stats.keypoints = (int)first_kp.size();
drawBoundingBox(first_frame, bb);
putText(first_frame, title, Point(0, 60), FONT_HERSHEY_PLAIN, 5, Scalar::all(0), 4);
object_bb = bb;
}我们计算并存储第一帧的关键点和描述符，并为输出做好准备。 我们需要保存检测到的关键点的数量，以确保两个探测器大致定位相同数量的关键点。
- 处理框架
- 定位关键点并计算描述符
(*detector)(frame, noArray(), kp, desc);为了在帧之间找到匹配，我们必须先定位关键点。 在本教程中，检测器被设置为在每一帧中找到大约1000个关键点。
- 使用2-nn匹配器查找对应联系
matcher->knnMatch(first_desc, desc, matches, 2);
for(unsigned i = 0; i < matches.size(); i++) {
if(matches[i][0].distance < nn_match_ratio * matches[i][1].distance) {
matched1.push_back(first_kp[matches[i][0].queryIdx]);
matched2.push_back( kp[matches[i][0].trainIdx]);
}
}如果最接近的匹配是nn_match_ratio比第二接近的更接近，那么它就是一个匹配。
- 用RANSAC估计单应变换
homography = findHomography(Points(matched1), Points(matched2),
RANSAC, ransac_thresh, inlier_mask);如果有至少4个匹配，我们可以使用随机样本一致性估计图像变换。
- 保存这个内点
for(unsigned i = 0; i < matched1.size(); i++) {
if(inlier_mask.at<uchar>(i)) {
int new_i = static_cast<int>(inliers1.size());
inliers1.push_back(matched1[i]);
inliers2.push_back(matched2[i]);
inlier_matches.push_back(DMatch(new_i, new_i, 0));
}
}由于findHomography计算嵌套，我们只需要保存选择的点和匹配。
- 目标对象边界框
perspectiveTransform(object_bb, new_bb, homography);如果有合理数量的嵌套，我们可以使用估计转换来定位对象。
结果
AKAZE统计:
Matches 626
Inliers 410
Inlier ratio 0.58
Keypoints 1117ORB统计:
Matches 504
Inliers 319
Inlier ratio 0.56
Keypoints 1112本文参与 腾讯云自媒体同步曝光计划，分享自作者个人站点/博客。
原始发表：2021-10-15 ，如有侵权请联系 cloudcommunity@tencent.com 删除
评论
登录后参与评论
推荐阅读
目录