基于DenseNet和深度运动图的行为识别算法

Action recognition algorithm based on DenseNet and depth motion map

结合深度信息以及RGB视频序列中丰富的纹理信息,提出了一种基于DenseNet和深度运动图像的人体行为识别算法。该算法基于DenseNet网络结构,首先获取彩色纹理信息和光流信息,然后从同步的深度视频序列获取深度信息,以增强特征互补性;再将空间流、时间流和深度流三种特征信息分别作为网络的输入;最后通过LSTMs进行特征融合和行为分类。实验结果表明,在公开的动作识别库UTD-MHAD数据集上,该算法识别准确率为92.11%,与该领域中的同类算法相比表现优异。

This paper proposes a human behavior recognition algorithm based on DenseNet and DMM,which integrates depth information and rich texture information in RGB video sequence.Based on the DenseNet network structure,the algorithm firstly obtains color texture information and optical flow information,and then obtains depth information from synchronous depth video sequence to enhance feature complementarity.Three kinds of characteristic information are used as the input of spatial flow network,temporal flow network and deep flow network.Then LSTMs is used for feature fusion and behavior classification.Experimental results show that the recognition rate of UTD-MHAD data set is 92.11%,which is an excellent performance compared with similar algorithms in this field.