Recently, occluded person re-identification(Re-ID) remains a challenging task that people are frequently obscured by other people or obstacles, especially in a crowd massing situation. In this paper, we propose a self-supervised deep learning method to improve the location performance for human parts through occluded person Re-ID. Unlike previous works, we find that motion information derived from the photos of various human postures can help identify major human body components. Firstly, a motion-aware transformer encoder-decoder architecture is designed to obtain keypoints heatmaps and part-segmentation maps. Secondly, an affine transformation module is utilized to acquire motion information from the keypoint detection branch. Then the motion information will support the segmentation branch to achieve refined human part segmentation maps, and effectively divide the human body into reasonable groups. Finally, several cases demonstrate the efficiency of the proposed model in distinguishing different representative parts of the human body, which can avoid the background and occlusion disturbs. Our method consistently achieves state-of-the-art results on several popular datasets, including occluded, partial, and holistic.
翻译:最近,隐蔽的人重新身份识别(Re-ID)仍是一项艰巨的任务,人们常常被其他人或障碍所掩盖,特别是在人群聚集的情况下。在本文件中,我们提议了一种自我监督的深层次学习方法,通过隐蔽的人重新身份识别来改善人体部分的位置性能。与以前的工作不同,我们发现从各种人类姿势照片中得出的运动信息有助于识别人体主要组成部分。首先,运动觉变压器编码解密结构的设计是为了获取关键点的热映像和部分分离图。第二,利用一个缝合变形模块从关键点检测部门获取运动信息。然后,运动信息将支持分层部门实现精细的人类部分分割图,有效地将人体分为合理群体。最后,一些案例表明拟议模型在区分人体不同代表部分方面的效率,这些代表可以避免背景和隐蔽。我们的方法始终在几个大众数据集(包括隐蔽、局部、部分和整体)上实现状态结果。