G2EMOT: Guided Embedding Enhancement for Multiple Object Tracking in Complex Scenes

Ma J, Wu F, Li C, Tang C, Zhang J, Xu Z, Li M, Liu D (2024)

Publication Language: English

Publication Type: Journal article, Original article

Publication year: 2024

Journal

IEEE Transactions on Instrumentation and Measurement Institute of Electrical and Electronics Engineers (IEEE)

Book Volume: 73

Pages Range: 1-14

Article Number: 2527214

URI: https://ieeexplore.ieee.org/document/10653748

DOI: 10.1109/TIM.2024.3449952

Abstract

The one-shot multiple object tracking framework simultaneously generates detected targets and re-identification (ReID) embeddings, and employs them to associate previous tracks. However, the continuity between the learning and extraction within the ReID task is unconsciously neglected because of treating them as two isolated stages. This leads to unreliable ReID embeddings and poses a challenge to target matching especially in complex and crowded scenarios. To this end, we propose a guided embedding enhancement multiple object tracker, named G2EMOT. It consists of three innovative designs aiming at improving the embedding representation capability for individual targets. First, based on the original feature map, a global instance-specific context decoupling (GICD) module is devised to facilitate the respective feature learning for detection and ReID branches. Then, a heatmap guided embedding enhancement (HGEE) module is introduced to connect the processes of embedding learning and extraction, ensuring that the detected target coordinates are accurately aligned with the discriminative ReID embeddings. Finally, to associate and stabilize matched targets, we present a novel two-gate guided embedding update (TG-GEU) strategy that dynamically updates ReID embeddings. With the proposed three components, G2EMOT achieves outstanding performance on popular MOT benchmarks, while outperforming the existing one-shot tracking methods by a large margin. In particular, it realizes IDF1 of 76.1% on MOT17 and IDF1 of 74.2% on MOT20. The source codes are released at https://github.com/ydhcg-BoBo/G2EMOT.

Authors with CRIS profile

Fei Wu Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

University of Chinese Academy of Sciences (UCAS) / 中国科学院大学

China (CN) Sichuan University (SCU) / 四川大学

China (CN)

How to cite

APA:

Ma, J., Wu, F., Li, C., Tang, C., Zhang, J., Xu, Z.,... Liu, D. (2024). G2EMOT: Guided Embedding Enhancement for Multiple Object Tracking in Complex Scenes. IEEE Transactions on Instrumentation and Measurement, 73, 1-14. https://doi.org/10.1109/TIM.2024.3449952

MLA:

Ma, Jianbo, et al. "G2EMOT: Guided Embedding Enhancement for Multiple Object Tracking in Complex Scenes." IEEE Transactions on Instrumentation and Measurement 73 (2024): 1-14.

BibTeX: Download