DetFlowTrack: 3D Multi-object Tracking based on Simultaneous Optimization of Object Detection and Scene Flow Estimation
This work addresses 3D MOT for unmanned vehicle perception, offering an incremental improvement by integrating detection and scene flow to simplify the network and enhance accuracy.
The paper tackles the problem of 3D multi-object tracking for unmanned vehicles by proposing a framework that simultaneously optimizes object detection and scene flow estimation, resulting in competitive state-of-the-art performance on the KITTI MOT dataset with robustness under extreme rotational motion.
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.