Due to the vast variance of pedestrian pose, scale, occlusion and trajectory, existing approaches are challenged by both accuracy and efficiency. We benchmark the human detection and tracking tasks. 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. The scenes may contain 4k head counts with over 100× scale variation.
The videos in PANDA were captured by a gigapixel camera and cover real-world scenes with both wide field-of-view (~1 square kilometer area) and high-resolution details (~gigapixel-level/frame). Authors: Xueyang Wang, Xiya Zhang, Yinheng Zhu, Yuchen Guo, Xiaoyun Yuan, Liuyu Xiang, Zerun Wang, Guiguang Ding, David Brady, Qionghai Dai, Lu Fang Description: We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset, for large-scale, long-term, and multi-object visual analysis.
0 kommentar(er)
