Designing Compact Convolutional Filters for Lightweight Human Pose Estimation
Shili Niu, Weihua Ou, Shihua Feng, Jianping Gou, Fei Long, Wenchuan Zhang, Wu Zeng · Wireless Communications and Mobile Computing · 2021
Existing methods for human pose estimation usually use a large intermediate tensor, leading to a high computational load, which is detrimental to resource‐limited devices. To solve this problem, we propose a low computational cost pose estimation network, MobilePoseNet, which includes encoder, decoder, and parallel nonmaximum suppression operation. Specifically, we design a lightweight upsampling block instead of transposing the convolution as the decoder and use the lightweight network as our downsampling part. Then, we choose the high‐resolution features as the input for upsampling to reduce the number of model parameters. Finally, we propose a parallel OKS‐NMS, which significantly outperforms the conventional NMS in terms of accuracy and speed. Experimental results on the benchmark datasets show that MobilePoseNet obtains almost comparable results to state‐of‐the‐art methods with a low compilation load. Compared to SimpleBaseline, the parameter of MobilePoseNet is only 4%, while the estimation accuracy reaches 98%.