期刊
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
卷 -, 期 -, 页码 3265-3275出版社
IEEE
DOI: 10.1109/CVPR42600.2020.00333
关键词
-
资金
- Natural Science Foundation of China (NSFC) [61722209, 6181001011, 61971260, U1936202]
- Shenzhen Science and Technology Research and Development Funds [JCYJ20180507183706645]
We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset, for large-scale, long-term, and multi-object visual analysis. The videos in PANDA were captured by a gigapixel camera and cover real-world scenes with both wide field-of-view (similar to 1 km(2) area) and high-resolution details (similar to gigapixel-level/frame). The scenes may contain 4k head counts with over 100x scale variation. PANDA provides enriched and hierarchical ground-truth annotations, including 15,974.6k bounding boxes, 111.8k fine-grained attribute labels, 12.7k trajectories, 2.2k groups and 2.9k interactions. We benchmark the human detection and tracking tasks. Due to the vast variance of pedestrian pose, scale, occlusion and trajectory, existing approaches are challenged by both accuracy and efficiency. Given the uniqueness of PANDA with both wide FoV and high resolution, a new task of interaction-aware group detection is introduced. We design a 'global-to-local zoom-in' framework, where global trajectories and local interactions are simultaneously encoded, yielding promising results. We believe PANDA will contribute to the community of artificial intelligence and praxeology by understanding human behaviors and interactions in large-scale real-world scenes. PANDA Website: http://www.panda-dataset.com.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据