Multi-Class Multi-Object Tracking using Changing Point Detection

Abstract

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.

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge

Cited by in corpus (7)

• Track to Reconstruct and Reconstruct to Track
• Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap
• 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
• Improving needle visibility in LED-based photoacoustic imaging using deep learning with semi-synthetic datasets
• Benchmarking Deep Trackers on Aerial Videos
• Recurrent Autoregressive Networks for Online Multi-Object Tracking
• Towards real-time and energy efficient Siamese tracking -- a hardware-software approach