ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-ID
This work addresses occlusion and background issues in person re-identification for surveillance and content video applications, representing an incremental improvement.
The paper tackles the challenge of person re-identification in content videos by proposing an entropy-based semantic feature alignment model that reduces the negative effects of mask segmentation errors, achieving superior performance on both existing and new datasets.
Person re-identification (re-ID) is a challenging task in real-world. Besides the typical application in surveillance system, re-ID also has significant values to improve the recall rate of people identification in content video (TV or Movies). However, the occlusion, shot angle variations and complicated background make it far away from application, especially in content video. In this paper we propose an entropy based semantic feature alignment model, which takes advantages of the detailed information of the human semantic feature. Considering the uncertainty of semantic segmentation, we introduce a semantic alignment with an entropy-based mask which can reduce the negative effects of mask segmentation errors. We construct a new re-ID dataset based on content videos with many cases of occlusion and body part missing, which will be released in future. Extensive studies on both existing datasets and the new dataset demonstrate the superior performance of the proposed model.