Two-Stream RNN/CNN for Action Recognition in 3D Videos

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)(2018)

引用 109|浏览53
暂无评分
摘要
The recognition of actions from video sequences has many applications in health monitoring, assisted living, surveillance, and smart homes. Despite advances in sensing, in particular related to 3D video, the methodologies to process the data are still subject to research. We demonstrate superior results by a system which combines recurrent neural networks with convolutional neural networks in a voting approach. The gated-recurrent-unit-based neural networks are particularly well-suited to distinguish actions based on long-term information from optical tracking data; the 3D-CNNs focus more on detailed, recent information from video data. The resulting features are merged in an SVM which then classifies the movement. In this architecture, our method improves recognition rates of state-of-the-art methods by 14% on standard data sets.
更多
查看译文
关键词
recognition rates,action recognition,video sequences,recurrent neural networks,convolutional neural networks,voting approach,gated-recurrent-unit,optical tracking data,3D-CNNs focus,two-stream CNN,SVM
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要