Large-Scale Omnidirectional Person Positioning

Location determination finds wide applications in daily life. Instead of existing efforts devoted to localizing tourist photos captured by perspective cameras, in this article, we focus on devising person positioning solutions using fisheye cameras mounted overhead. Such solutions are advantageous in large field of view (FOV), low cost, anti-occlusion, and unaggressive work mode (without the necessity of cameras carried by persons). However, related studies are quite scarce, due to the paucity of data. To stimulate research in this exciting area, we present LOAF, the first large-scale overhead fisheye dataset for person detection and localization. LOAF is built with many essential features, e.g., i) the data cover abundant diversities in scenes, human pose, density, and location; ii) it contains currently the largest number of annotated pedestrian, i.e., 457K bounding boxes with ground-truth orientation and location information; iii) the body-boxes are labeled as radius-aligned so as to fully address the positioning challenge. To approach localization, we build a fisheye person detection network, which exploits the geometry of fisheye images from rotation-equivariance and distortion-awareness two perspectives. Corresponding training strategies are devised to deliver high accuracy, radius-aligned human box and angle predictions in an end-to-end manner. Then, the actual locations of the detected persons are calculated by a numerical solution on the fisheye model and camera altitude data. Extensive experiments on LOAF validate the superiority of our fisheye detector w.r.t. previous methods. This demonstrates that our whole fisheye positioning solution is able to locate all persons in FOV with an accuracy of 0.5 m within 0.1 s.