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

by   Tao Hu, et al.
Horizon Robotics

Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to ground-truth in the training stage leads to the training-inference discrepancy problem, i.e., exposure bias, where association error could accumulate in the inference and make the trajectories drift. In this paper, we propose a novel method for optimizing tracklet consistency, which directly takes the prediction errors into account by introducing an online, end-to-end tracklet search training process. Notably, our methods directly optimize the whole tracklet score instead of pairwise affinity. With sequence model as appearance encoders of tracklet, our tracker achieves remarkable performance gain from conventional tracklet association baseline. Our methods have also achieved state-of-the-art in MOT15 17 challenge benchmarks using public detection and online settings.


Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking

Traditional multiple object tracking methods divide the task into two pa...

End-to-End Multi-Object Tracking with Global Response Map

Most existing Multi-Object Tracking (MOT) approaches follow the Tracking...

Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking

In this work, we present an end-to-end framework to settle data associat...

Transformer-based assignment decision network for multiple object tracking

Data association is a crucial component for any multiple object tracking...

Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking

Identity Switching remains one of the main difficulties Multiple Object ...

FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking

Data association-based multiple object tracking (MOT) involves multiple ...

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

Online Multi-Object Tracking (MOT) is a challenging problem and has many...

Please sign up or login with your details

Forgot password? Click here to reset