Multiple Object Tracking Using Edge Multi-Channel Gradient Model With ORB Feature

Abstract

Multiple object tracking based on tracking-by-detection is the most common method used in addressing illumination change and occlusion problems. In this paper, we present a tracking algorithm based on Edge Multi-channel Gradient Model. We first use the canny operator to extract the edges of the image, and establish a biologically inspired Multi-channel Gradient Model that integrate the spatio-temporal-spectral information of the edge to detect moving multiple objects. Under this model, the ORB feature is introduced to solve the problem of matching the object with the object library. Therefore, we can achieve object consistency, and the threshold classification method can solve the problem of multiple object occlusion in the process of persistent multiple object tracking. The experimental results show that the proposed method can effectively deal with the problems of occlusion and illumination changes. Compared with other state-of-the-art algorithms, the proposed algorithm achieves better performance on MOTA, MOTP, and IDF1. In particular, it performs best on IDSW on MOT2015 dataset, with an average improvement ratio of 28.99% over the second-place algorithm. In addition, our algorithm has a better performance in running time, achieving a good compromise between the speed and the accuracy.

Keywords

• Multiple object tracking
• multiple object detection
• ORB
• E-McGM
• tracking by detection