引入重影特征映射和通道注意力机制的手势识别算法

Gesture Recognition Algorithm Introducing Ghost Feature Mapping and Channel Attention Mechanism

针对轻量型目标检测网络对静态手势特征提取能力不足、错检率和漏检率高的问题,基于YOLOv4-tiny网络结构提出轻量型手势识别算法.首先引入表征力更强、成本更低的重影特征映射,增强网络获取多尺度手势特征的能力;然后嵌入通道注意力机制实现特征重标定,达到减少背景干扰的目的;最后采用Swish作为主激活函数,进一步提升手势识别准确率.在手势数据集上的实验结果表明,相比YOLOv4-tiny,所提算法具有较优的识别性能;并且对于不同环境条件下的多尺度手势,该算法能够实现精准的分类和实时的检测,对小尺度的手势具有更好的识别效果.

To solve the problem that the lightweight object detection network has insufficient ability to extract static gesture features,high false detection rate and missed detection rate,a lightweight gesture recognition algorithm is proposed based on YOLOv4-tiny network structure.First,a more powerful and low-cost ghost feature mapping is introduced to enhance the ability of network to obtain multi-scale gesture features.Then,the embedded channel attention mechanism realizes feature recalibration and achieves the purpose of reducing background interference.Finally,Swish is used as the main activation function to further improve the accuracy of gesture recognition.The experimental results on the gesture dataset show that the proposed algorithm has better recognition performance than YOLOv4-tiny.For multi-scale gestures under different environmental conditions,the algorithm achieves accurate classification as well as real-time detection,and has better recognition performance for small-scale gestures.