Adaptive feature selection method for action recognition of human body in RGBD data
- 信息技术－已发表论文 
目前在RGBD视频的行为识别中,为了提高识别准确率,许多方法采用多特征融合的方式。通过实验分析发现,行为在特定特征上的分类效果好,但是多特征融合; 并不能体现个别特征的分类优势,同时融合后的特征维度很高,时空开销大。为了解决这个问题,提出了; RGBD人体行为识别中的自适应特征选择方法,通过随机森林和信息熵分析人体关节点判别力,以高判别力的人体关节点的数量作为特征选择的标准。通过该数量; 阈值的筛选,选择关节点特征或者关节点相对位置作为行为识别特征。实验结果表明,该方法相比于特征融合的算法,行为识别的准确率有了较大提高,超过了大部; 分算法的识别结果。Many methods adopt the technique of multi-feature fusion to improve the; recognition accuracy of RGBD ideo. Experimental analyses revealed that; the classification effect of certain behavior in some features is good;; however, multi-feature fusion cannot reflect the classification; superiority of certain features. Moreover, multi-feature fusion is; highly dimensional and considerably expensive in terms of time and; space. This research proposes an adaptive feature selection method for; RGBD human-action recognition to solve this problem. First, random; forest and information entropy were used to analyze the judgment ability; of the human joints, whereas the number of human joints with high; judgment ability were chosen as the feature selection criterion. By; screening the threshold number, either the joint feature or the relative; positions of the joints was used as the recognition feature of action.; Experimental results show that compared with multi-feature fusion, the; method significantly improved the accuracy of action recognition and; outperformed most other algorithms.