A Multiperson Pose Estimation Method Using Depthwise Separable Convolutions and Feature Pyramid Network

In the process of multiperson pose estimation, there are problems such as slow detection speed, low detection accuracy of key point targets, and inaccurate positioning of the boundaries of people with serious occlusion. A multiperson pose estimation method using depthwise separable convolutions and feature pyramid network is proposed. Firstly, the YOLOv3 target detection algorithm model based on the depthwise separable convolution is used to improve the running speed of the human body detector. Then, based on the improved feature pyramid network, a multiscale supervision module and a multiscale regression module are added to assist training and to solve the difficult key point detection problem of the human body. Finally, the improved soft-argmax method is used to further eliminate redundant attitudes and improve the accuracy of attitude boundary positioning. Experimental results show that the proposed model has a score of 73.4% in AP on the 2017 COCO test-dev dataset, and it scored 86.24% on PCKh@0.5 on the MPII dataset.