Dense Trajectories and Motion Boundary Descriptors for Action Recognition
Dense Trajectories and Motion Boundary Descriptors for Action Recognition
复制标题
DOI：
10.1007/s11263-012-0594-8
复制
发表时间：
2013-05-01
影响因子：
19.5
通讯作者：
Liu, Cheng-Lin
中科院分区：
文献类型：
--
作者：
Wang, Heng;Klaeser, Alexander;Liu, Cheng-Lin
本文介绍了一种基于密集轨迹和运动边界描述符的视频表示方法。轨迹捕获视频的局部运动信息。密集表示保证了前景运动以及周围环境的良好覆盖。一个国家的最先进的光流算法，使一个强大的和有效的提取密集的轨迹。作为描述符，我们提取与轨迹对齐的特征来表征形状（点坐标）、外观（定向梯度直方图）和运动（光流直方图）。此外，我们引入了一个描述符的基础上运动边界直方图（MBH）依赖于差分光流。MBH描述符表现出始终优于其他最先进的描述符，特别是在包含大量相机运动的真实世界视频上。我们在九个数据集上评估了我们的视频表示，即KTH，YouTube，Hollywood2，UCF sports，IXMAS，UIUC，Olympic Sports，UCF50和HMDB51。在所有数据集上，我们的方法都优于当前最先进的结果。
This paper introduces a video representation based on dense trajectories and motion boundary descriptors. Trajectories capture the local motion information of the video. A dense representation guarantees a good coverage of foreground motion as well as of the surrounding context. A state-of-the-art optical flow algorithm enables a robust and efficient extraction of dense trajectories. As descriptors we extract features aligned with the trajectories to characterize shape (point coordinates), appearance (histograms of oriented gradients) and motion (histograms of optical flow). Additionally, we introduce a descriptor based on motion boundary histograms (MBH) which rely on differential optical flow. The MBH descriptor shows to consistently outperform other state-of-the-art descriptors, in particular on real-world videos that contain a significant amount of camera motion. We evaluate our video representation in the context of action classification on nine datasets, namely KTH, YouTube, Hollywood2, UCF sports, IXMAS, UIUC, Olympic Sports, UCF50 and HMDB51. On all datasets our approach outperforms current state-of-the-art results.