Closed scottclowe closed 9 years ago
Must make sure parameters are suitable so EVERY image in BOTH train and test datasets have an appropriate number of keypoints detected.
From http://docs.opencv.org/trunk/doc/py_tutorials/py_feature2d/py_orb/py_orb.html:
"ORB is basically a fusion of FAST keypoint detector and BRIEF descriptor with many modifications to enhance the performance. First it use FAST to find keypoints, then apply Harris corner measure to find top N points among them. It also use pyramid to produce multiscale-features. But one problem is that, FAST doesn’t compute the orientation. So what about rotation invariance? Authors came up with following modification."
Therefore, although the detection is implemented in the "image_features.py" module, Scott and I decided not to use FAST in our pipeline, as ORB is more sophisticated.
Use OpenCV to detect corners with FAST and describe them.
http://docs.opencv.org/trunk/modules/features2d/doc/feature_detection_and_description.html