Strict NMS: Pedestrian Detection in Crowd Scenes
Ze Zhang, Yuning Wang, Haiyang Jiang, Xiaohui Zeng · 2020
Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel NonMaximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose strict-NMS, which applies a higher suppression threshold to an instance; (2) we apply Mask boot module to the Fast-RCNN to improve the detect capacity. (3) We achieve state of the art results on the CityPersons benchmarks.