Lightweight Cross-Fusion Network on Human Pose Estimation for Edge Device

The deployment of human pose estimation on edge devices are essential task in computer vision. Due to memory and storage space limitations, it is difficult for edge devices to maintain implementing Convolutional Neural Networks, which deployed large-scale terminal platforms with abundant computing resources. This paper proposed novel Lightweight Cross-fusion Network on Human Pose Estimation with information sharing. Using state-of-the-art efficient neural architecture, and Ghost Net, as the backbone, which are gradually applying a cross-information fusion network for key points extraction in the baseline and strengthen phases. As a result, the computational cost significantly reduced, while maintaining feature confidence more accurate and predicting key points heatmaps more precisely. The network model entirely executed on edge devices, and extensive self-comparison experiments evaluated the architecture's effectiveness. The MS COCO 2017 dataset proved that the cross-fusion network is superior than other lightweight structures for pose estimation.