Person Re-Identification for Suppressing Background Interference

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.