Real-time Action Recognition by Feature-level Fusion of Depth and Inertial Sensor | |
Yi Li; Jun Cheng; Xiaopeng Ji; Wei Feng; Dapeng Tao | |
2017 | |
会议地点 | 日本冲绳 |
英文摘要 | Human action recognition has been an active research topic for its wide applications. Most researches focus on the recognition based on one single modality sensor. In this paper, we present a novel approach for human action recognition, which is based on feature-level fusion of depth and inertial sensor. We extract Fast Fourier Transform (FFT) coefficients from acceleration signals and Histograms of Oriented Gradients (HOG) features from Motion Response Maps (MRM). After obtaining these two modality feature vectors, we adopt Discriminant Correlation Analysis (DCA) to learn a fused feature descriptor with better discriminating ability. To evaluate the effectiveness and efficiency of the proposed approach, we conduct experiments on the multimodal human action database CAS-YNU-MHAD. Experimental results demonstrate the fused feature descriptor exhibits a strong and stable performance in improving the recognition accuracy. Moreover, our approach has a low computational complexity and can be employed in real-time systems. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.siat.ac.cn:8080/handle/172644/11825] |
专题 | 深圳先进技术研究院_集成所 |
作者单位 | 2017 |
推荐引用方式 GB/T 7714 | Yi Li,Jun Cheng,Xiaopeng Ji,et al. Real-time Action Recognition by Feature-level Fusion of Depth and Inertial Sensor[C]. 见:. 日本冲绳. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论