基于支持向量机优化的人体动作识别方法  

Human action recognition method based on support vector machine optimization

作　　者：王晋[1] WANG Jin(Xi’an Technological University,Xi’an 710021,China)

机构地区：[1]西安工业大学,陕西西安710021

出　　处：《电子设计工程》2018年第17期6-9,16,共5页Electronic Design Engineering

基　　金：陕西省社科基金项目(2016Q022)

摘　　要：为了能够有效改善人体动作识别过程中传统支持向量机使用一对一识别策略,并且实现识别结果的输出,对大部分动作种类进行忽略,从而降低识别效率及识别进度的问题,就提出了基于支持向量机优化的人体动作识别。基于向量机优化的人体动作识别使用支持向量机改进策略实现动作识别,在识别过程中利用分类器识别精度实现传统策略的完善,并且在识别结果输出的过程中输出相对应的置信度,通过置信度处理识别结果。最后对其进行实现,通过实验结果表示,基于支持向量优化的识别率为98.7%,表示此方法具有有效性,能够提高人体动作识别的精准度及效率。In order to identify a strategy using traditional support can effectively improve the human action recognition in the process of vector machine,output and achieve recognition results,most of the action types are ignored,thus reducing the efficiency of identification and recognition of the progress of the problem,it is proposed to support the optimization of human action recognition based on svm.Human action recognition vector machine optimization using improved support vector machine strategy implementation action recognition based on improving the traditional strategy using the classifier recognition accuracy in the identification process,and in the process of recognition results output in the corresponding output confidence,through confidence recognition results.Finally,it is implemented.The experimental results show that the recognition rate based on support vector optimization is 98.7%,indicating that this method is effective,and it can improve the accuracy and efficiency of human action recognition.

关 键 词：支持向量 优化 动作识别 运动模型 

分 类 号：TN99[电子电信—信号与信息处理]