RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images

CVPR Workshops(2020)

引用 50|浏览20
暂无评分
摘要
Recent methods for people detection in overhead, fisheye images either use radially-aligned bounding boxes to represent people, assuming people always appear along image radius or require significant pre-/post-processing which radically increases computational complexity. In this work, we develop an end-to-end rotation-aware people detection method, named RAPiD, that detects people using arbitrarily-oriented bounding boxes. Our fully-convolutional neural network directly regresses the angle of each bounding box using a periodic loss function, which accounts for angle periodicities. We have also created a new dataset with spatio-temporal annotations of rotated bounding boxes, for people detection as well as other vision tasks in overhead fisheye videos. We show that our simple, yet effective method outperforms state-of-the-art results on three fisheye-image datasets. Code and dataset are available at http://vip.bu.edu/rapid .
更多
查看译文
关键词
radially-aligned bounding boxes,arbitrarily-oriented bounding boxes,computational complexity,source code,vision tasks,spatio-temporal annotations,angle periodicities,periodic loss function,RAPiD,fully-convolutional neural network,end-to-end rotation-aware people detection method,image radius,overhead fisheye images,fisheye-image datasets,overhead fisheye videos,rotated bounding boxes
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要