Marginalised Stacked Denoising Autoencoders for Robust Representation of Real-Time Multi-View Action Recognition

Sensors

Feng Gu²  Francisco Flórez-Revuelta¹  Dorothy Monekosso²  Paolo Remagnino²  Jesús Fontecha³ 

[1] Faculty of Science, Engineering and Computing, Kingston University, Penrhyn Road, Kingston upon Thames KT1 2EE, UK; E-Mail:;School of Computing and Information Systems, Kingston University, Penrhyn Road, Kingston upon Thames KT1 2EE, UK; E-Mails:School of Computing and Information Systems, Kingston University, Penrhyn Road, Kingston upon Thames KT1 2EE, UK;

关键词: deep learning;    marginalised stacked denoising autoencoders;    bag of words;    multiple kernel learning;    multi-view action recognition;   

DOI  :  10.3390/s150717209

来源: mdpi

【 摘 要 】

Multi-view action recognition has gained a great interest in video surveillance, human computer interaction, and multimedia retrieval, where multiple cameras of different types are deployed to provide a complementary field of views. Fusion of multiple camera views evidently leads to more robust decisions on both tracking multiple targets and analysing complex human activities, especially where there are occlusions. In this paper, we incorporate the marginalised stacked denoising autoencoders (mSDA) algorithm to further improve the bag of words (BoWs) representation in terms of robustness and usefulness for multi-view action recognition. The resulting representations are fed into three simple fusion strategies as well as a multiple kernel learning algorithm at the classification stage. Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance. According to results on three multi-view benchmark datasets, the proposed framework improves recognition performance across all three datasets and outputs record recognition performance, beating the state-of-art algorithms in the literature. It is also capable of performing real-time action recognition at a frame rate ranging from 33 to 45, which could be further improved by using more powerful machines in future applications.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.