A pedestrian recognition method based on dynamic occlusion samples

Abstract

The embodiment of the invention discloses a pedestrian recognition method based on dynamic occlusion samples. The method comprises: constructing an original image feature learning network framework; inputting a pedestrian image of a training set to obtain n local features, and learning and optimizing the local features, serially connecting the obtained n optimized local features as the original image features of the training pedestrian image; building the generator; generating an occluded pedestrian image; inputting the occluded pedestrian image into the generator to obtain n local features, and learning and optimizing the local features, serially connecting the obtained n local features as occluded image features; obtaining the final features of the training pedestrian image by using theoriginal image features and the occlusion image features, and performing pedestrian recognition by using the final features of the training pedestrian image. The invention makes full use of the advantages of the convolution neural network, learns the original image feature and the occlusion image feature of the pedestrian, and finally fuses the two features to represent the pedestrian image, thereby further improving the matching accuracy of the pedestrian recognition.

Description

technical field [0001] The invention belongs to the fields of pattern recognition and artificial intelligence, and in particular relates to a pedestrian re-identification method based on dynamic occlusion samples. Background technique [0002] Person Re-Identification (Person Re-Identification) mainly studies the method of searching for the same pedestrian under different cameras. This technology can quickly and accurately locate target pedestrians, so it has been widely used in security defense and other fields. However, due to the large changes in pedestrian posture, clothing, lighting and camera angles in real scenes, and pedestrians are often blocked by obstacles, these make pedestrian re-identification technology face huge challenges. [0003] In recent years, researchers have made great progress after applying deep learning methods to the field of pedestrian re-identification, which has greatly improved the correct search rate of pedestrian re-identification. In orde...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the technical problem that the occluded pedestrian image cannot match the dynamic model state and does not improve the performance of occluded samples. Therefore, the present invention provides a pedestrian re-identification method based on dynamic occluded samples

Images