Unveiling the Power of Self-supervision for Multi-view Multi-human Association and Tracking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929230168719360 |
|---|---|
| author | Feng, Wei Wang, Feifan Han, Ruize Qian, Zekun Wang, Song |
| author_facet | Feng, Wei Wang, Feifan Han, Ruize Qian, Zekun Wang, Song |
| contents | Multi-view multi-human association and tracking (MvMHAT), is a new but important problem for multi-person scene video surveillance, aiming to track a group of people over time in each view, as well as to identify the same person across different views at the same time, which is different from previous MOT and multi-camera MOT tasks only considering the over-time human tracking. This way, the videos for MvMHAT require more complex annotations while containing more information for self learning. In this work, we tackle this problem with a self-supervised learning aware end-to-end network. Specifically, we propose to take advantage of the spatial-temporal self-consistency rationale by considering three properties of reflexivity, symmetry and transitivity. Besides the reflexivity property that naturally holds, we design the self-supervised learning losses based on the properties of symmetry and transitivity, for both appearance feature learning and assignment matrix optimization, to associate the multiple humans over time and across views. Furthermore, to promote the research on MvMHAT, we build two new large-scale benchmarks for the network training and testing of different algorithms. Extensive experiments on the proposed benchmarks verify the effectiveness of our method. We have released the benchmark and code to the public. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_17617 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unveiling the Power of Self-supervision for Multi-view Multi-human Association and Tracking Feng, Wei Wang, Feifan Han, Ruize Qian, Zekun Wang, Song Computer Vision and Pattern Recognition Artificial Intelligence Multi-view multi-human association and tracking (MvMHAT), is a new but important problem for multi-person scene video surveillance, aiming to track a group of people over time in each view, as well as to identify the same person across different views at the same time, which is different from previous MOT and multi-camera MOT tasks only considering the over-time human tracking. This way, the videos for MvMHAT require more complex annotations while containing more information for self learning. In this work, we tackle this problem with a self-supervised learning aware end-to-end network. Specifically, we propose to take advantage of the spatial-temporal self-consistency rationale by considering three properties of reflexivity, symmetry and transitivity. Besides the reflexivity property that naturally holds, we design the self-supervised learning losses based on the properties of symmetry and transitivity, for both appearance feature learning and assignment matrix optimization, to associate the multiple humans over time and across views. Furthermore, to promote the research on MvMHAT, we build two new large-scale benchmarks for the network training and testing of different algorithms. Extensive experiments on the proposed benchmarks verify the effectiveness of our method. We have released the benchmark and code to the public. |
| title | Unveiling the Power of Self-supervision for Multi-view Multi-human Association and Tracking |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2401.17617 |