Multi-Class Multi-Object Tracking using Changing Point Detection
It addresses robust tracking for unlimited object classes in videos, which is an incremental improvement for computer vision applications.
The paper tackles multi-class multi-object tracking by combining detection responses with a changing point detection algorithm to handle occlusions and drifts, achieving very encouraging results compared to state-of-the-art techniques on benchmark datasets like ImageNet VID and MOT.
This paper presents a robust multi-class multi-object tracking (MCMOT) formulated by a Bayesian filtering framework. Multi-object tracking for unlimited object classes is conducted by combining detection responses and changing point detection (CPD) algorithm. The CPD model is used to observe abrupt or abnormal changes due to a drift and an occlusion based spatiotemporal characteristics of track states. The ensemble of convolutional neural network (CNN) based object detector and Lucas-Kanede Tracker (KLT) based motion detector is employed to compute the likelihoods of foreground regions as the detection responses of different object classes. Extensive experiments are performed using lately introduced challenging benchmark videos; ImageNet VID and MOT benchmark dataset. The comparison to state-of-the-art video tracking techniques shows very encouraging results.