Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking

TL;DR

This paper introduces a vehicle tracking method that relies solely on motion patterns, using deep graph convolutional networks to improve long-term tracking without appearance cues, achieving competitive results.

Contribution

It presents a novel motion-only vehicle tracking approach utilizing a reconstruct-to-embed strategy with GCNs, avoiding appearance features and reducing computational complexity.

Findings

Achieves competitive performance on KITTI and UA-Detrac datasets.

Effectively handles long-term tracking without appearance information.

Demonstrates robustness against occlusion and detection errors.

Abstract

Vehicle tracking is an essential task in the multi-object tracking (MOT) field. A distinct characteristic in vehicle tracking is that the trajectories of vehicles are fairly smooth in both the world coordinate and the image coordinate. Hence, models that capture motion consistencies are of high necessity. However, tracking with the standalone motion-based trackers is quite challenging because targets could get lost easily due to limited information, detection error and occlusion. Leveraging appearance information to assist object re-identification could resolve this challenge to some extent. However, doing so requires extra computation while appearance information is sensitive to occlusion as well. In this paper, we try to explore the significance of motion patterns for vehicle tracking without appearance information. We propose a novel approach that tackles the association issue for long-term tracking with the exclusive fully-exploited motion information. We address the tracklet embedding issue with the proposed reconstruct-to-embed strategy based on deep graph convolutional neural networks (GCN). Comprehensive experiments on the KITTI-car tracking dataset and UA-Detrac dataset show that the proposed method, though without appearance information, could achieve competitive performance with the state-of-the-art (SOTA) trackers. The source code will be available at https://github.com/GaoangW/LGMTracker.