3D Descriptors for Object and Category Recognition: a Comparative Evaluation

Abstract

Abstract — Often practitioners face the issue of choosing the most adequate 3D features for their problem. As with many other problems, there isn’t a “best ” feature to use. Nonetheless, we can gauge the relative accuracy of available features on common datasets. That is what we propose to do in this paper: we describe the existing feature extraction algorithms in a public available point cloud library and perform a comparative evaluation on 3D point clouds, investigation both the object and category recognition performance. The main conclusions are: increasing the number of keypoints improves recognition results at the expense of size and time; since there are big differences in terms of recognition performance, size and time requirements, the descriptor has to be matched to the desired task; one should use a descriptor that takes advantage of color; the SHOTCOLOR descriptor shows a good balance between recognition accuracy and time complexity. I.