A Biological Motivated Multi-scale Keypoint Detector for local 3D Descriptors

Most object recognition algorithms use a large number of descriptors extracted in a dense grid, so they have a very high computational cost, preventing real-time processing. The use of keypoint detectors allows the reduction of the processing time and the amount of redundancy in the data. Local descriptors extracted from images have been extensively reported in the computer vision literature. In this paper, we present a keypoint detector inspired by the behavior of the early visual system. Our method is a color extension of the BIMP keypoint detector, where we include both color and intensity channels of an image. The color information is included in a biological plausible way and reproduces the color information in the retina. Multi-scale image features are combined into a single keypoints map. Our detector is compared against state-of-the-art detectors and is particularly well-suited for tasks such as category and object recognition. The evaluation allowed us to obtain the best pair keypoint detector/descriptor on a RGB-D object dataset. Using our keypoint detector and the SHOTCOLOR descriptor we obtain a good category recognition rate and for object recognition it is with the PFHRGB descriptor that we obtain the best results.