Two-Stream Dictionary Learning Architecture for Action Recognition
Two-Stream Dictionary Learning Architecture for Action Recognition
复制标题
用于动作识别的双流字典学习架构
DOI：
10.1109/tcsvt.2017.2665359
复制
发表时间：
2017
影响因子：
8.4
通讯作者：
Sun Tanfeng
中科院分区：
文献类型：
--
作者：
Xu Ke;Jiang Xinghao;Sun Tanfeng
本文提出了一种基于双流字典学习结构的人体动作识别新方法。该体系结构由兴趣补丁（IP）检测器和描述符，双流字典模型，和支持向量机（SVM）分类。新的IP检测器结合了人体检测器和轮廓检测器来提取人体轮廓上的感兴趣的补丁。然后分别在空间流和时间流中计算IP描述符。在每个流中，使用IP描述符作为动作模型为每个动作训练字典。通过这种方式，将测量动作序列与动作模型之间的相似性转化为利用模型重构该序列中的IP并计算重构误差。对于每个动作，构造IP分布直方图，并且该直方图进一步用于训练每个流中的SVM分类器。采用得分融合方法对空间和时间SVM分类结果进行融合，以做出最终决策。所提出的架构进行了检查的四个公共数据集具有不同的背景复杂性和摄像机运动条件：魏茨曼数据集，KTH数据集，奥运会体育数据集，和HMDB51数据集。在实验部分中，将结果与最先进的方法进行了进一步的比较，以确认该架构的有效性。
In this paper, a novel method based on the two-stream dictionary learning architecture for human action recognition is proposed. The architecture consists of interest patch (IP) detector and descriptor, two-stream dictionary models, and support vector machine (SVM) for classification. The novel IP detector combines a human detector and a contour detector to extract patches of interest on human contours. Then the IP descriptors are calculated in spatial stream and temporal stream separately. In each stream, a dictionary is trained for each action with the IP descriptors as an action model. In this way, measuring the similarity between an action sequence and an action model is transformed to reconstructing the IPs in this sequence with the model and computing the reconstruction error. For each action, an IP distribution histogram is constructed and the histogram is further used to train an SVM classifier in each stream. A score fusion method is applied to fuse the spatial and temporal SVM classification results to make a final decision. The proposed architecture is examined on four public data sets with different background complexities and camera motion conditions: Weizmann data set, KTH data set, Olympic sports data set, and HMDB51 data set. The results are further compared with state-of-the-art approaches in the experiment section to confirm the effectiveness of this architecture.