A lightweight gesture recognition network

As one of the main human-computer interaction methods, gesture recognition has an urgent issue to be addressed, which huge paramaters and massive computation of the classification and recognition algorithm cause high cost in practical applications. To reduce cost and enhance the detection efficiency, a lightweight model of gesture recognition algorithms is proposed in this paper, based on the YOLOv5s framework. Firstly, we adopt ShuffleNetV2 as the backbone network to reduce the computational load and enhance the model's detection speed. Additionally, lightweight modules such as GSConv and VoVGSCSP are introduced into the neck network to further compress the model size while maintaining accuracy. Furthermore, the BiFPN (Bi-directional Feature Pyramid Network) structure is incorporated to enhance the network's detection accuracy at a lower computational cost. Lastly, we introduce the Coordinate Attention (CA) mechanism to enhance the network's focus on key features. To investigate the rationale behind the introduction of the CA attention mechanism and the BiFPN network structure, we analyze the extracted features and validate the network's attention on different parts of the feature maps through visualization. Experimental results demonstrate that the proposed algorithm achieves an average precision of 95.2% on the HD-HaGRID dataset. Compared to the original YOLOv5s model, the proposal model reduces the parameter count by 70.6% and the model size by 69.2%. Therefore, this model is suitable for real-time gesture recognition classification and detection, demonstrating significant potential for practical applications.