计算机科学
计算机视觉
人工智能
水准点(测量)
跟踪(教育)
保险丝(电气)
一致性(知识库)
校准
眼动
图像配准
跟踪系统
视频跟踪
虚拟现实
虚拟映像
增强现实
特征提取
作者
Zekun Qian,Wei Feng,Feifan Wang,Ruize Han
标识
DOI:10.1109/tpami.2025.3647707
摘要
We handle a new problem of multi-view multi-human tracking in the bird's eye view (BEV). Different from previous works, we require neither the calibration among the multi-view cameras nor the actually captured BEV video. This makes the studied problem closer to real-world applications, however, more challenging. For this purpose, in this work, we propose a novel BEVTrack scheme. Specifically, given multi-view videos, we first use a virtual BEV transform module to obtain the BEV for each view. Then, we propose a unified BEV alignment module to fuse the respectively generated BEVs, in which we specifically design the self-supervised losses by considering both the spatial consistency and the temporal continuity. During the inference, we design the camera-subject collaborative registration and tracking strategy to make use of the mutual dependence between the multi-view cameras and the multiple targets, to achieve the desired BEV tracking. We also build a new benchmark for training and evaluation, the experimental results on which have verified the rationality of the problem and the effectiveness of our method.
科研通智能强力驱动
Strongly Powered by AbleSci AI