Learning action patterns in difference images for efficient action recognition
Learning action patterns in difference images for efficient action recognition
复制标题
DOI：
10.1016/j.neucom.2013.06.042
复制
发表时间：
2014
期刊：
影响因子：
6
通讯作者：
Guoliang Lu;Mineichi Kudo
中科院分区：
文献类型：
--
作者：
Guoliang Lu;Mineichi Kudo
提出了一种面向单人的动作识别新框架。该框架不需要检测/定位人体的边界框，也不需要在每个帧中进行运动估计。新的描述符/模式的动作表示的学习与本地时间自相似性（LTSS）直接从不同的图像。词袋框架，然后用于动作分类，利用这些描述符。我们在两个公共人类行为数据集上研究了该框架的有效性：Weizmann数据集和KTH数据集。在Weizmann数据集上，该框架的识别率达到了95.6%，在KTH数据集上达到了91.1%，这两种方法都与最先进的方法具有竞争力，但它有很大的潜力来实现更快的执行性能。
A new framework is presented for single-person oriented action recognition. This framework does not require detection/location of bounding boxes of human body nor motion estimation in each frame. The novel descriptor/pattern for action representation is learned with local temporal self-similarities (LTSSs) derived directly from difference images. Thebag-of-wordsframework is then employed for action classification taking advantages of these descriptors. We investigated the effectiveness of the framework on two public human action datasets: the Weizmann dataset and the KTH dataset. In the Weizmann dataset, the proposed framework achieves a performance of 95.6% in the recognition rate and that of 91.1% in the KTH dataset, both of which are competitive with those ofstate-of-the-artapproaches, but it has a high potential to achieve a faster execution performance.