Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Zijing, Yu, Jianlong, Zhang, Lin, Zhang, Shunli
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2502.16809
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929728604078080
author Zhao, Zijing
Yu, Jianlong
Zhang, Lin
Zhang, Shunli
author_facet Zhao, Zijing
Yu, Jianlong
Zhang, Lin
Zhang, Shunli
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_16809
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CRTrack: Low-Light Semi-Supervised Multi-object Tracking Based on Consistency Regularization
Zhao, Zijing
Yu, Jianlong
Zhang, Lin
Zhang, Shunli
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title CRTrack: Low-Light Semi-Supervised Multi-object Tracking Based on Consistency Regularization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2502.16809