Extended Co-occurrence HOG with Dense Trajectories for Fine-Grained Activity Recognition
Extended Co-occurrence HOG with Dense Trajectories for Fine-Grained Activity Recognition
复制标题
DOI：
10.1007/978-3-319-16814-2_22
复制
发表时间：
2014-11
期刊：
影响因子：
--
通讯作者：
Hirokatsu Kataoka;K. Hashimoto;K. Iwata;Y. Satoh;Nassir Navab;Slobodan Ilic;Y. Aoki
中科院分区：
文献类型：
--
作者：
Hirokatsu Kataoka;K. Hashimoto;K. Iwata;Y. Satoh;Nassir Navab;Slobodan Ilic;Y. Aoki
本文提出了一种新的特征描述符扩展共现HOG (ECoHOG)，并将其与密集点轨迹相结合，证明了其在细粒度活动识别中的有效性。该特征的灵感来自于原始的共现HOG (CoHOG)，它基于图像中图像梯度对出现的直方图。而不是仅仅依赖于纯直方图，我们引入了图像中共存的图像梯度对的梯度幅度之和。这使得物体边界变得更加重要，同时也使移动前景和静态背景之间的差异变得更加明显。我们还将ECoHOG与使用从视频序列中提取的光流提取的密集点轨迹相结合，并证明它们非常适合于细粒度的活动识别。使用我们的功能，我们在这项任务中优于最先进的方法，并提供广泛的定量评估。
In this paper we propose a novel feature descriptor Extended Co-occurrence HOG (ECoHOG) and integrate it with dense point trajectories demonstrating its usefulness in fine grained activity recognition. This feature is inspired by original Co-occurrence HOG (CoHOG) that is based on histograms of occurrences of pairs of image gradients in the image. Instead relying only on pure histograms we introduce a sum of gradient magnitudes of co-occurring pairs of image gradients in the image. This results in giving the importance to the object boundaries and straightening the difference between the moving foreground and static background. We also couple ECoHOG with dense point trajectories extracted using optical flow from video sequences and demonstrate that they are extremely well suited for fine grained activity recognition. Using our feature we outperform state of the art methods in this task and provide extensive quantitative evaluation.