我正在检测图像中的SURF特征,然后将它们写入yml文件。然后,我想再次从yml文件中加载功能,以尝试检测对象,但此刻我在加载要在图像上绘制关键点时遇到了麻烦。

我正在这样写关键点:

cv::FileStorage fs("keypointsVW.yml", cv::FileStorage::WRITE);
write(fs, "keypoints_1", keypoints_1);
fs.release();

我试图这样阅读它们:
cv::FileStorage fs2("keypointsVW.yml", cv::FileStorage::READ);
read(fs2, "keypoints_1", keypoints_1);
fs2.release();

但这会产生大量错误。

检测并绘制代码:
    cv::Mat img_1 = cv::imread(argv[1], CV_LOAD_IMAGE_GRAYSCALE);
    int minHessian = 400;
    cv::SurfFeatureDetector detector(minHessian);
    std::vector<cv::KeyPoint> keypoints_1;
    detector.detect(img_1, keypoints_1);
    cv::Mat img_keypoints_1;
    //......write code
    //.......read code
    drawKeypoints(img_1, keypoints_1, img_keypoints_1);
    imshow("keypoints_1", img_keypoints_1);

最佳答案

找到了解决方案,如果有人遇到同样的问题,我将在这里发布。

std::vector<cv::KeyPoint> testPoints;
cv::FileStorage fs2("keypointsVW.yml", cv::FileStorage::READ);
cv::FileNode kptFileNode = fs2["keypointsVW"];
read(kptFileNode, testPoints);
fs2.release();

关于c++ - 加载保存的SURF关键点,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/27841067/

10-15 19:58