Revision history [back]

SURF, SIFT etc got a big issue: textureless objects can't be detected with them because you will not find any keypoints on them. Pedestrian most of the time are best described by their shape and, depending on the camera quality/speed, you will find very low quality keypoints on them

SURF, SIFT etc got a big issue: textureless objects can't be detected with them because you will not find any keypoints on them. Pedestrian most of the time are best described by their shape and, depending on the camera quality/speed, you will find very low quality keypoints on themthem.

SURF, SIFT etc got a big issue: textureless objects can't be detected with them because you will not find any keypoints on them. Pedestrian most of the time are best described by their shape and, depending on the camera quality/speed, you will find very low quality keypoints on them.

But if you need to detect textured object keypoints based technique may be good. objects (especially if you have good quality video sequences), keypoint-based techniques are generally better. There are many researches on topic (even with online learning keypoint-based) you can watch a tracking algorithm here for example: Matrioska: Tracking By detection using Keypoints

SURF, SIFT etc got a big issue: textureless objects texture-less objects can't be detected with them because you will not find any keypoints on them. Pedestrian most of the time are best described by their shape and, depending on the camera quality/speed, you will find very low quality keypoints on them.

But if you need to detect textured objects (especially if you have good quality video sequences), keypoint-based techniques techniques are generally better. There are many researches on topic (even with online learning keypoint-based) you can watch a tracking algorithm here for example: Matrioska: Tracking By detection using Keypoints