姿态估计算法在视频监控中的应用

Application of pose estimation algorithm in video monitoring

为了满足厨房智能监控的需求,保证食品卫生安全,开发了一个基于姿态估计算法的厨房智能监控系统。该系统将深度神经网络与视频监控技术相融合,实现人脸识别以及衣帽识别等功能,采用Openpose姿态估计算法对人体部位进行有效定位,并针对Openpose算法会出现误判人体关键点的问题进行了改进。实验表明,改进后的姿态估算法能够有效地避免误判问题。

In order to meet the needs of kitchen intelligent monitoring and ensure food safety,a kitchen intelligent monitoring system using pose estimation algorithm is developed in this paper.The system combines with the deep neural network and video monitoring technologies to realize the functions of face recognition and clothing recognition.The Openpose pose estimation algorithm is used to locate the parts of human body effectively,and the improvement is made to solve the problem that the openpose algorithm may misjudge the key points of human body.Experimental results show that the improved pose estimation algorithm can effectively avoid the misjudgment.