Occluded suspect search via channel-guided mechanism
- PDF / 1,379,516 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 74 Downloads / 195 Views
(0123456789().,-volV)(0123456789(). ,- volV)
S.I. : ATCI 2020
Occluded suspect search via channel-guided mechanism Wenxin Huang1,2 • Ruimin Hu1,2 • Xiao Wang1,2 • Chao Liang1,2 • Jun Chen1,2 Received: 30 May 2020 / Accepted: 21 August 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract To elude from the camera, suspects often hide behind other things or persons, leading to a series of occlusion patterns. These suspects are notoriously hard to search due to the substantially various appearance in the intricate occlusion patterns. Existing methods solving occlusion problem depend on learning several frequent patterns separately. It brings not only high consumption but also less coverage of patterns in real application scenarios. Different from the current researches which only concern certain patterns that do not synthesize the occlusion patterns in practical applications, we consider a wide range of occlusion patterns which conform the real application scenarios in one coherent model with less interference of both the occlusion and background areas and without redundant computation. Consequently, we propose a channelguided mechanism (CGM) for occluded suspect search in this paper. The core idea is that different body areas have been activated via different channels in convolutional neural networks. By suppressing the effects of the interference areas, such as occlusion and background areas, we can filter out the visible areas which are the essential elements for the occlusion patterns. Channel-aware attention is introduced to learn the relation between areas and channels. Furthermore, we can identify suspects using a rule which focuses more on the visible area and focuses less on the occluded area in the specific occlusion pattern. Extensive evaluations on two challenging datasets confirm the effectiveness of the proposed CGM. Keywords Person search Occluded patterns Channel-aware attention Channel-guided mechanism Convolutional neural network Surveillance system
1 Introduction
& Ruimin Hu [email protected] Wenxin Huang [email protected] Xiao Wang [email protected] Chao Liang [email protected] Jun Chen [email protected] 1
National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan 430072, China
2
Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan 430072, China
Suspect search is the task of locating and identifying the target suspect from various cameras configured in different cameras. Due to variable pose, viewpoint, illumination, and occlusion, the significant visual changes are the main challenges of suspect search, making intra-personal variations even larger than that of inter-personal variations. Moreover, in real investigation scenarios, suspects often hide behind other objects or persons to evade surveillance cameras, which causes the suspects to be occluded. Consequently, it is difficult to search these suspects since their appearance changes significantly ly
Data Loading...
