Abstract
This article introduces a cascaded multitask framework to improve the performance of person search by fully utilizing the combination of pedestrian detection and person re-identification tasks. Inspired by Faster R-CNN, a Pre-extracting Net is used in the front part of the framework to produce the low-level feature maps of a query or gallery. Then, a well-designed Pedestrian Proposal Network called Deformable Pedestrian Space Transformer is introduced with affine transformation combined by parameterized sampler as well as deformable pooling dealing with the challenge of spatial variance of person re-identification. At last, a Feature Sharing Net, which consists of a convolution net and a fully connected layer, is applied to produce output for both detection and re-identification. Moreover, we compare several loss functions including a specially designed Online Instance Matching loss and triplet loss, which supervise the training process. Experiments on three data sets including CUHK-SYSU, PRW and SJTU318 are implemented and the results show that our work outperforms existing frameworks.
Highlights
Video surveillance[1] is an important part of social security, whose effectiveness depends on whether the specific person can be found in the recording
Our work considers a unified approach, which uses the Re-ID loss function based on comparison to supervise the pedestrian search network
An average precision (AP) is computed for each target person image based on the precision–recall curve. mean Average Precision (mAP) is the average of APs and focuses on the entire output list, which means that with higher mAP the last one of the positive samples is more likely to be placed in the front of the list
Summary
Video surveillance[1] is an important part of social security, whose effectiveness depends on whether the specific person can be found in the recording. As the complexity of video surveillance networks grows, traditional manual video monitoring method has been infeasible.[2] Apparently, it’s important to find a way to obtain information from videos quickly and accurately. Person search under multi-camera video surveillance network is a very challenging and practical issue. It is of great significance in realworld applications like security surveillance,[3] crowd flow monitoring[4] and human behaviour analysis.[5].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
