School of Traffic and Transportation Engineering, Central South University, Changsha 410075, China.
Sensors (Basel). 2023 Aug 19;23(16):7274. doi: 10.3390/s23167274.
As a biological characteristic, gait uses the posture characteristics of human walking for identification, which has the advantages of a long recognition distance and no requirement for the cooperation of subjects. This paper proposes a research method for recognising gait images at the frame level, even in cases of discontinuity, based on human keypoint extraction. In order to reduce the dependence of the network on the temporal characteristics of the image sequence during the training process, a discontinuous frame screening module is added to the front end of the gait feature extraction network, to restrict the image information input to the network. Gait feature extraction adds a cross-stage partial connection (CSP) structure to the spatial-temporal graph convolutional networks' bottleneck structure in the ResGCN network, to effectively filter interference information. It also inserts XBNBlock, on the basis of the CSP structure, to reduce estimation caused by network layer deepening and small-batch-size training. The experimental results of our model on the gait dataset CASIA-B achieve an average recognition accuracy of 79.5%. The proposed method can also achieve 78.1% accuracy on the CASIA-B sample, after training with a limited number of image frames, which means that the model is more robust.
作为一种生物特征，步态利用人类行走的姿势特征进行识别，具有识别距离长、无需被识别者配合等优点。本文提出了一种基于人体关键点提取的步态图像在帧级别的识别研究方法，即使在不连续的情况下也能进行识别。为了减少网络在训练过程中对图像序列时间特征的依赖，在步态特征提取网络的前端添加了一个不连续帧筛选模块，限制网络输入的图像信息。在 ResGCN 网络的时空图卷积网络的瓶颈结构中，步态特征提取添加了跨阶段局部连接（CSP）结构，以有效过滤干扰信息。它还在 CSP 结构的基础上插入了 XBNBlock，以减少由于网络层加深和小批量训练导致的估计误差。我们的模型在步态数据集 CASIA-B 上的实验结果达到了平均识别准确率 79.5%。该方法在使用有限数量的图像帧进行训练后，在 CASIA-B 样本上也可以达到 78.1%的准确率，这意味着模型更加稳健。
