Cross-modal pedestrian re-identification method and device based on intermediate modal and representation learning

The invention provides a cross-modal pedestrian re-identification method, device and equipment based on joint intermediate modal and representation learning, and a readable storage medium. The method comprises the following steps: acquiring original images of two modes of a visible light image and an infrared image; mapping the original image to a unified feature space by using an intermediate modal generator to generate an intermediate modal image; jointly inputting the intermediate modal image and the original image into a parameter-shared feature extraction network; based on a multi-granularity pooling strategy, optimizing a cross-modal pedestrian re-identification model by adopting a strategy of combining global features and local features and generalized average pooling; a joint loss common optimization model of distribution consistency loss, label smooth cross entropy loss and heterogeneous center triple loss is adopted; and identifying the to-be-identified image by using the optimized image. The model