MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916184209752064 |
|---|---|
| author | Woo, Sanghyun Park, Kwanyong Shin, Inkyu Kim, Myungchul Kweon, In So |
| author_facet | Woo, Sanghyun Park, Kwanyong Shin, Inkyu Kim, Myungchul Kweon, In So |
| contents | Multi-target multi-camera tracking is a crucial task that involves identifying and tracking individuals over time using video streams from multiple cameras. This task has practical applications in various fields, such as visual surveillance, crowd behavior analysis, and anomaly detection. However, due to the difficulty and cost of collecting and labeling data, existing datasets for this task are either synthetically generated or artificially constructed within a controlled camera network setting, which limits their ability to model real-world dynamics and generalize to diverse camera configurations. To address this issue, we present MTMMC, a real-world, large-scale dataset that includes long video sequences captured by 16 multi-modal cameras in two different environments - campus and factory - across various time, weather, and season conditions. This dataset provides a challenging test-bed for studying multi-camera tracking under diverse real-world complexities and includes an additional input modality of spatially aligned and temporally synchronized RGB and thermal cameras, which enhances the accuracy of multi-camera tracking. MTMMC is a super-set of existing datasets, benefiting independent fields such as person detection, re-identification, and multiple object tracking. We provide baselines and new learning setups on this dataset and set the reference scores for future studies. The datasets, models, and test server will be made publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_20225 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark Woo, Sanghyun Park, Kwanyong Shin, Inkyu Kim, Myungchul Kweon, In So Computer Vision and Pattern Recognition Multi-target multi-camera tracking is a crucial task that involves identifying and tracking individuals over time using video streams from multiple cameras. This task has practical applications in various fields, such as visual surveillance, crowd behavior analysis, and anomaly detection. However, due to the difficulty and cost of collecting and labeling data, existing datasets for this task are either synthetically generated or artificially constructed within a controlled camera network setting, which limits their ability to model real-world dynamics and generalize to diverse camera configurations. To address this issue, we present MTMMC, a real-world, large-scale dataset that includes long video sequences captured by 16 multi-modal cameras in two different environments - campus and factory - across various time, weather, and season conditions. This dataset provides a challenging test-bed for studying multi-camera tracking under diverse real-world complexities and includes an additional input modality of spatially aligned and temporally synchronized RGB and thermal cameras, which enhances the accuracy of multi-camera tracking. MTMMC is a super-set of existing datasets, benefiting independent fields such as person detection, re-identification, and multiple object tracking. We provide baselines and new learning setups on this dataset and set the reference scores for future studies. The datasets, models, and test server will be made publicly available. |
| title | MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.20225 |