Multi-granularity and Multi-semantic Model for Person Re-identification in Variable Illumination

Person re-identification (Re-ID) with deep neural networks has made tremendous improvements recently. The existing person Re-ID methods can do well in viewpoint, occlusion, resolution, etc. However, they are short of robustness under varying lighting conditions. The variable illumination will result in the inconsistency of color, contrast, and SNR (signal-noise ratio), which will cause lots of difficulties to identify the right person. This paper presents a multi-granularity and multi-semantic Re-ID model combined with image enhancement method to minimize the impact of illumination variations and optimize the feature extraction. The Retinex-based image enhancement method is used to balance the variable illumination and enhance the contour information of images. Furthermore, we add multi-granularity and multi-semantic layers in the network to extract powerful feature representation. The proposed model is evaluated on the Market-1501, DukeMTMC-reID and CUHK03 datasets. Extensive experiments show that the new deep neural network model can extract more robustness features from the enhanced images, and verify the effectiveness of our method under changing illumination conditions.