基于深度视频的人体行为特征表示与识别

深度视频中的人体行为的识别研究主要集中在对深度视频进行特征表示上,为了获得具有判别性的特征表示,首先提出了深度视频中一种基于表面法向信息的局部二值模式( local binary pattern, LBP)算子作为初级特征,然后基于稀疏表示模型训练初级特征字典,获取初级特征的稀疏表示,最后对用自适应的时空金字塔划分的若干个子序列使用时空池化方法进行初级特征与稀疏系数的规格化,得到深度视频的高级特征,最终的特征表示实现了深度视频中的准确的人体行为识别。在公开的动作识别库MSR Action3D和手势识别库MSR Gesture3D上的实验证明了本文提出的特征表示的有效性和优越性。

Action Feature Representation and Recognition Based on Depth Video

Researches of human behavior recognition in depth video focused on depth video ’ s action feature representation was conducted to obtain a discriminative feature representation. Firstly a LBP operator based on the surface normal in depth video as a lower feature was proposed. Then the features were used to train a dictionary to get sparse representation. Lastly the original depth video was divided into some sub depth video by an adaptive spatio-temporal pyramid and a pooling method was adopted to normalize the lower features and the sparse coefficient to get a higher representation. The high representation realizes an accurate recognition of human behavior. The experiments on the action recognition dataset MSR Action3 D and gesture recognition dataset MSR Gesture3 D prove the author's improved encoding algorithm’ s feasibility and superiority.