Abstract
To alleviate the problem of background interference in the person re-identification (Re-ID) field, the paper proposes a novel Re-ID method with background suppression ability. First, it analyzes the implicit relationship between foreground and background in the multi-camera surveillance scene according the experiments. Second, a background suppression network is designed, which is composed of foreground sub network, background sub network and noise suppression module. By the noise suppression loss function, the ability of person feature extraction is enhanced, while the background noise is suppressed. The experimentation results on Market1501 and DukeMTMC-reID datasets show that the proposed method has lower computation complexity, and it boosts the recognition performance and improves the transferable ability.
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 callMore From: Journal of Computer-Aided Design & Computer Graphics
Disclaimer: 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.
