A lightweight high-resolution Human pose estimation method with an integrated attention mechanism

Deep learning has significant advantages in the field of human posture estimation. However, traditional methods often increase the parameter size and complexity of posture estimation networks by widening and deepening them to improve performance. To address this issue, this paper proposes a lightweight human posture estimation network, ADNet, based on the high-resolution network(HRNet). ADNet replaces Basic Blocks and downsampling in the high-resolution network with GABlocks and GDBlocks that incorporate lightweight convolution and attention mechanisms to reduce the number of parameters and computational complexity in the network. Additionally, ADNet solves the problem of feature redundancy by fusing relationships between different channels to make effective feature channels fully utilized. Experimental results show that ADNet achieves high-precision detection of human keypoint information even with fewer parameters and less computational complexity than commonly used human posture estimation networks, such as Cascaded Pyramid Network (CPN), Stacked Hourglass Network(Hourglass), and HRNet. Results also indicate that, compared to HRNet, ADNet reduces the model parameter size by 69.1% and computational complexity by 58.9% under the same image resolution and environment configuration. Furthermore, in the visualization of feature maps, the network using ADNet exhibits stronger feature extraction performance and less feature redundancy.