基于双分支时空步态特征融合的深度学习步态识别

针对现有步态识别方法易受拍摄视角、着装变化影响的问题,提出一种融合二维无肩姿态拓扑能量图(shoulderless pose topological energy maps, SPTEM)和三维局部骨骼步态特征(local skeleton gait features, LSGF)的深度学习步态识别方法.首先,利用轻量级BlazePose姿态估计算法提取步态视频序列中的人体姿态拓扑图以生成SPTEM,在提高检测速度的同时减弱衣物变化带来的影响;然后,引入LSGF以弥补单一能量图特征在多变视角情况下识别准确率较低的不足;最后,提出结合注意力机制的时空特征提取网络模型,并在全连接层将双流特征进行一致融合.在CASIA-B数据集上对所提出方法进行验证,并与当前主流的步态识别方法进行比较,结果表明,所提出方法在跨视角和穿大衣/棉衣条件下的步态识别率都有明显提升.

Deep learning gait recognition based on two branch spatiotemporal gait feature fusion

Aiming at the problem that the existing gait recognition methods are easily affected by shooting angle and clothing changes, this paper proposes a deep learning gait recognition method that fuses 2D shoulderless pose topological energy maps(SPTEMs) and 3D local skeleton gait features(LSGFs). Firstly, the lightweight BlazePose pose estimation algorithm is used to extract the human posture topology in the gait video sequence to generate the SPTEM, which improves the detection speed and reduces the impact of clothing changes. Then, the LSGF is introduced to make up for the low recognition accuracy deficiency of a single energy map feature in the case of variable viewing angles. Finally, a spatio-temporal feature extraction network model fused with an attention mechanism is proposed, and the two-stream features are fused uniformly in the fully connected layer. The proposed algorithm is validated on the CASIA-B dataset and compared with the current mainstream gait recognition methods. The results show that the gait recognition rate of the proposed method is significantly improved under cross-view and cl conditions.