基于多特征融合和分层反向传播增强算法的人体动作识别  

Human action recognition based on multi-feature fusion and hierarchical BP-AdaBoost algorithm

作　　者：李拟珺[1] 程旭[1] 郭海燕[1] 吴镇扬[1] 

机构地区：[1]东南大学信息科学与工程学院,南京210096

出　　处：《东南大学学报（自然科学版）》2014年第3期493-498,共6页Journal of Southeast University：Natural Science Edition

基　　金：国家自然科学基金资助项目(60971098);国家自然科学基金青年基金资助项目(61302152)

摘　　要：为了推广神经网络在人体动作识别中的应用,设计了一种基于分层识别框架和增强算法的动作识别系统,该系统融合了光流直方图、有向梯度直方图、Hu的矩特征、分块剪影和自相似矩阵等多种特征.为了与反向传播网络的增强相匹配,将传统的二分类增强算法扩展到多分类版本.此外,系统采用了包含预判决和后判决的分层识别框架,前者通过分析运动显著区域的位置,把动作粗分为几个子类,后者则利用额外的特征进一步提高识别准确率.基于Weizmann和KTH数据库的实验结果表明:神经网络相对于常用的支持向量机具有明显的优越性;结合分层识别的反向传播增强算法可以极大减少运算代价与动作类间的混淆,识别准确率较高.To popularize the application of neural network in human action recognition,an action recognition system based on the hierarchical recognition framework and the boosting algorithm is de-signed,which mixes together multiple features such as histograms of optical flow,histograms of ori-ented gradients,Hu’s moments,block-silhouettes and self-similarity matrices.To fit with the boos-ting of back-propagation （BP）networks,the standard binary AdaBoost algorithm is extended to a multiclass version.Besides,this system adopts a hierarchical recognition framework consisting of pre-decision and post-decision.The former can roughly classify the actions into several subcategories by analyzing the locations of motion salient regions,whereas the latter exploits extra features to fur-ther enhance recognition accuracy.The experimental results on Weizmann and KTH datasets show that neural networks exhibit obvious advantages over the popular support vector machine.The BP-AdaBoost algorithm combined with hierarchical recognition can greatly reduce the computational cost and confusions among actions to achieve high recognition accuracy.

关 键 词：特征提取 动作识别 反向传播增强算法 神经网络 分层识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]