Local Attention Mechanism and Temporal Prediction-Based Multi-Person Pose Estimation

In recent years, attention mechanisms have been widely used in many fields due to their excellent image focusing ability to produce more discriminative feature representations. However, in human pose estimation, methods based on attention mechanisms tend to have high computational overhead and are difficult to process video data in real time. In addition, existing algorithms do not make good use of the similarity between consecutive frames, and often repeat the computation many times on the same image. Therefore, this paper proposes a method based on a local attention mechanism and temporal prediction. The method first passes the input image through a body detector and then focuses attention on the head of the person, generating a large module of head information perception. This helps to find all the people in the image, avoiding missed detections, and this approach, which uses a local attention mechanism, has a small computational overhead. Then, to make the network layers closer to each other while keeping the parameters sparse, the features generated by the deep network will be reconstructed and compared with the input image. Finally, in order to reduce repetitive computation, the method determines the similarity between the preceding and following frames by means of multiple sampling points, which is used to determine whether the information from the previous frame is used to guide the localization of the nodes in the following frame. This allows the algorithm to remain real time when processing video. Experiments on the COCO and PoseData I datasets show that the algorithm outperforms all 10 comparison algorithms in terms of both accuracy and image continuity.