CRTrack: Low-Light Semi-Supervised Multi-object Tracking Based on Consistency Regularization

TL;DR

CRTrack introduces a semi-supervised multi-object tracking approach tailored for low-light environments, utilizing a new dataset and consistency regularization to improve tracking accuracy despite limited annotated data.

Contribution

The paper presents a novel low-light multi-object tracking dataset and a semi-supervised tracking method that resists noisy pseudo-labels through consistency regularization.

Findings

Effective handling of noisy pseudo-bounding boxes.

Enhanced tracking performance with unannotated data.

Successful construction of a low-light tracking dataset.

Abstract

Multi-object tracking under low-light environments is prevalent in real life. Recent years have seen rapid development in the field of multi-object tracking. However, due to the lack of datasets and the high cost of annotations, multi-object tracking under low-light environments remains a persistent challenge. In this paper, we focus on multi-object tracking under low-light conditions. To address the issues of limited data and the lack of dataset, we first constructed a low-light multi-object tracking dataset (LLMOT). This dataset comprises data from MOT17 that has been enhanced for nighttime conditions as well as multiple unannotated low-light videos. Subsequently, to tackle the high annotation costs and address the issue of image quality degradation, we propose a semi-supervised multi-object tracking method based on consistency regularization named CRTrack. First, we calibrate a consistent adaptive sampling assignment to replace the static IoU-based strategy, enabling the semi-supervised tracking method to resist noisy pseudo-bounding boxes. Then, we design a adaptive semi-supervised network update method, which effectively leverages unannotated data to enhance model performance. Dataset and Code: https://github.com/ZJZhao123/CRTrack.