Lightweight convolutional neural network-based pedestrian detection and re-identification in multiple scenarios

Pedestrian detection and re-identification technology is a research hotspot in the field of computer vision. This technology currently has issues such as insufficient pedestrian expression ability, occlusion, diverse pedestrian attitude, and difficulty of small-scale pedestrian detection. In this paper, we proposed an end-to-end pedestrian detection and re-identification model in real scenes, which can effectively solve these problems. In our model, the original images are processed with a non-overlapped image blocking data augmentation method, and then input them into the YOLOv3 detector to obtain the object position information. LCNN-based pedestrian re-identification model is used to extract the features of the object. Furthermore, the eigenvectors of the object and the detected pedestrians are calculated, and the similarity between them are used to determine whether they can be marked as target pedestrians. Our method is lightweight and end-to-end, which can be applied to the real scenes.