DeepAI AI Chat
Log In Sign Up

Real-time Multi-Object Tracking Based on Bi-directional Matching

by   Huilan Luo, et al.

In recent years, anchor-free object detection models combined with matching algorithms are used to achieve real-time muti-object tracking and also ensure high tracking accuracy. However, there are still great challenges in multi-object tracking. For example, when most part of a target is occluded or the target just disappears from images temporarily, it often leads to tracking interruptions for most of the existing tracking algorithms. Therefore, this study offers a bi-directional matching algorithm for multi-object tracking that makes advantage of bi-directional motion prediction information to improve occlusion handling. A stranded area is used in the matching algorithm to temporarily store the objects that fail to be tracked. When objects recover from occlusions, our method will first try to match them with objects in the stranded area to avoid erroneously generating new identities, thus forming a more continuous trajectory. Experiments show that our approach can improve the multi-object tracking performance in the presence of occlusions. In addition, this study provides an attentional up-sampling module that not only assures tracking accuracy but also accelerates training speed. In the MOT17 challenge, the proposed algorithm achieves 63.4 speed.


page 5

page 10

page 14

page 15


Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation

Occlusion between different objects is a typical challenge in Multi-Obje...

End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning

The majority of contemporary object-tracking approaches used in autonomo...

Distributed Multi-object Tracking under Limited Field of View Sensors

We consider the challenging problem of tracking multiple objects using a...

Learning to Track with Object Permanence

Tracking by detection, the dominant approach for online multi-object tra...

Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering

In this paper, we propose the methods to handle temporal errors during m...

Simple online and real-time tracking with occlusion handling

Multiple object tracking is a challenging problem in computer vision due...