基于显著性检测和稠密轨迹的人体行为识别

Human action recognition based on dense trajectories with saliency detection

稠密轨迹的人体行为识别对每一帧全图像密集采样导致特征维数高、计算量大且包含了无关的背景信息。提出基于显著性检测和稠密轨迹的人体行为识别方法。首先对视频帧进行多尺度静态显著性检测获取动作主体位置,并与对视频动态显著性检测的结果线性融合获取主体动作区域,通过仅在主体动作区域内提取稠密轨迹来改进原算法;然后采用Fisher Vector取代词袋模型对特征编码增强特征表达充分性;最后利用支持向量机实现人体行为识别。在KTH数据集和UCF Sports数据集上进行仿真实验,结果表明改进的算法相比于原算法识别准确率有所提升。

Human action recognition based on dense trajectories samples the whole image of every frame densely, which leads to high feature dimensionality, large computational cost and containing the irrelevant background information. A human action recognition method is proposed based on dense trajectories with saliency detection. First, a multi-scale static saliency detection is used to get the action subject positions, which then is combined with the results of dynamic saliency detection to get human action areas. The original algorithm is improved by only extracting dense trajectories in these areas.To enhance adequacy of feature expression, Fisher vector is used to replace BOW model encoding the features. At last,SVM is used to get the results of human action recognition. The experimental results conducted on KTH dataset and UCF Sports dataset show that the proposed method has improved on the recognition accuracy compared with the original algorithm.