Abstract: A multi granularity person re-identification model integrating attention mechanism is proposed to address the complex monitoring environment and the significant differences in image appearance of pedestrians under different conditions such as lighting changes, perspective changes, and occlusion, which make it difficult to extract detailed pedestrian features. The model extracts feature maps containing information at different scales by introducing a multi branch structure; By combining multi granularity segmentation modules and attention mechanisms, further extracting local discriminative information from feature maps, obtaining diverse feature representations, and achieving coordinated and unified features; Supervised training of the model using federated learning to obtain more comprehensive feature descriptions. Excellent performance was achieved on the mainstream person re-identification datasets Market-1501, DukeMTMC-reID, and CUHK03, with mAP reaching 88.42%, 78.86%, and 76.70%, respectively, demonstrating the effectiveness of the proposed model.