【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.更多还原

【Abstract】 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 designed,which mixes together multiple features such as histograms of optical flow,histograms of oriented gradients,Hu’s moments,block-silhouettes and self-similarity matrices. To fit with the boosting 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 further 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 BPAdaBoost algorithm combined with hierarchical recognition can greatly reduce the computational cost and confusions among actions to achieve high recognition accuracy.更多还原