DetFlowTrack: 3D Multi-object Tracking based on Simultaneous Optimization of Object Detection and Scene Flow Estimation

TL;DR

This paper introduces DetFlowTrack, a 3D multi-object tracking framework that simultaneously optimizes object detection and scene flow estimation, improving accuracy and robustness in dynamic scenes for unmanned vehicle perception.

Contribution

The paper proposes a novel framework that integrates detection and scene flow estimation for 3D MOT, with a detection-guidance module and a new ground truth calculation method for rotation scenarios.

Findings

Achieves competitive results on KITTI MOT dataset.

Demonstrates robustness under extreme rotational motion.

Improves inter-frame association accuracy.

Abstract

3D Multi-Object Tracking (MOT) is an important part of the unmanned vehicle perception module. Most methods optimize object detection and data association independently. These methods make the network structure complicated and limit the improvement of MOT accuracy. we proposed a 3D MOT framework based on simultaneous optimization of object detection and scene flow estimation. In the framework, a detection-guidance scene flow module is proposed to relieve the problem of incorrect inter-frame assocation. For more accurate scene flow label especially in the case of motion with rotation, a box-transformation-based scene flow ground truth calculation method is proposed. Experimental results on the KITTI MOT dataset show competitive results over the state-of-the-arts and the robustness under extreme motion with rotation.