Pedestrian re-identification method based on multi-task joint supervised learning

The invention discloses a pedestrian re-identification method based on multi-task joint supervised learning, and the method comprises the following steps: S1, constructing a multi-task deep learning network which comprises a backbone network and a branch network, wherein the branch network comprises: a part segmentation network which receives the output of the backbone network and is used for classifying human body parts in an image, an attributive character network which is used for receiving the output of the backbone network and the component segmentation network and carrying out attributive character identification, and a global feature network which is used for receiving the output of the backbone network and carrying out global feature identification; and S2, constructing a loss function: performing loss calculation by utilizing the characteristics after the global characteristics and the attribute characteristics are spliced to obtain the loss function of the multi-task deep learning network. According