摘要
在支持向量机多分类方法基础上,提出了一种改进的有向无环图支持向量机(Directed Acyclic Graph Support Vector Machine,DAGSVM)手势识别方法。首先根据Kinect采集到的场景深度信息将前景和背景分开,分割得到手,然后提取其特征向量,利用特征向量训练多个SVM两分类器,采用DAG拓扑结构构成DAGSVM多分类器,并对其结构排序进行改进。实验证明,与其他支持向量机多分类方法相比,改进后的DAGSVM分类器能够达到更高的识别率,并将这个手势识别方法用于智能轮椅的控制上,收到了良好的效果。
On the basis of SVM ( Support Vector Machine) muhiclass classification, an improved DAGSVM ( Directed Acyclie Graph Support Vector Machine) hand gesture recognition approach is put forward. Firstly, depth information of the scene is collected by using Kinect sensor and hand region is obtained. Then feature vectors are extracted, which are used to train multiple binary SVM classifiers. DAGSVM classifier is constructed using DAG topological structure with trained binary SVM classifiers and its structure sequence is im- proved. Finally, the experimental results proved that the improved DAGSVM could reach higher recognition rate and can be used in the control of intelligent wheelchair successfully.
出处
《控制工程》
CSCD
北大核心
2013年第5期957-959,965,共4页
Control Engineering of China
基金
国家自然科学基金项目(51075420)
国家自然科学基金项目(60905066)
轮椅式机器人导航与控制习用研究(CSTC
2010AA2055)
科技部"基于多模人机接口技术的智能轮椅"国际合作项目(2010DFA12160)