Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking

by   Hui Zhou, et al.

Online Multi-Object Tracking (MOT) is a challenging problem and has many important applications including intelligence surveillance, robot navigation and autonomous driving. In existing MOT methods, individual object's movements and inter-object relations are mostly modeled separately and relations between them are still manually tuned. In addition, inter-object relations are mostly modeled in a symmetric way, which we argue is not an optimal setting. To tackle those difficulties, in this paper, we propose a Deep Continuous Conditional Random Field (DCCRF) for solving the online MOT problem in a track-by-detection framework. The DCCRF consists of unary and pairwise terms. The unary terms estimate tracked objects' displacements across time based on visual appearance information. They are modeled as deep Convolution Neural Networks, which are able to learn discriminative visual features for tracklet association. The asymmetric pairwise terms model inter-object relations in an asymmetric way, which encourages high-confidence tracklets to help correct errors of low-confidence tracklets and not to be affected by low-confidence ones much. The DCCRF is trained in an end-to-end manner for better adapting the influences of visual information as well as inter-object relations. Extensive experimental comparisons with state-of-the-arts as well as detailed component analysis of our proposed DCCRF on two public benchmarks demonstrate the effectiveness of our proposed MOT framework.


page 3

page 4

page 5

page 6

page 10


End-to-End Learning Deep CRF models for Multi-Object Tracking

Existing deep multi-object tracking (MOT) approaches first learn a deep ...

Learnable Online Graph Representations for 3D Multi-Object Tracking

Tracking of objects in 3D is a fundamental task in computer vision that ...

Enhancing the Association in Multi-Object Tracking via Neighbor Graph

Most modern multi-object tracking (MOT) systems follow the tracking-by-d...

Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections

In currently available literature, no tracking-by-detection (TBD) paradi...

Multi-object Tracking via End-to-end Tracklet Searching and Ranking

Recent works in multiple object tracking use sequence model to calculate...

Please sign up or login with your details

Forgot password? Click here to reset