Pedestrian re-identification method and device, electronic equipment and readable storage medium

The embodiment of the invention provides a pedestrian re-identification method and device, electronic equipment and a readable storage medium, and relates to the technical field of computer vision. The method comprises the steps: acquiring a to-be-recognized image containing a portrait, and inputting the to-be-recognized image into a re-recognition model for re-recognition to obtain a re-recognition result, wherein the re-recognition model is a trained appearance sub-network obtained by training a pre-constructed re-recognition network comprising an appearance sub-network and an appearance sub-network by taking a portrait image as a training sample, and the recognition accuracy and the recognition efficiency of pedestrian re-recognition are improved. 本申请实施例提供了一种行人重识别方法、装置、电子设备和可读存储介质，涉及计算机视觉技术领域。通过获取包含人像的待识别图像，将待识别图像输入重识别模型进行重识别，得到重识别结果。其中，重识别模型是将人像图像作为训练样本，对预先构建的包括外形子网络及外观子网络的重识别网络进行训练，得到的训练后的外观子网络，提高了行人重识别的识别准确性和识别效率。