Video-based convolutional neural networks for activity recognition from robot-centric videos

M. S. Ryoo; Larry Matthies

doi:10.1117/12.2229531

13 May 2016 Video-based convolutional neural networks for activity recognition from robot-centric videos

M. S. Ryoo, Larry Matthies

Proceedings Volume 9837, Unmanned Systems Technology XVIII; 98370R (2016) https://doi.org/10.1117/12.2229531
Event: SPIE Defense + Security, 2016, Baltimore, MD, United States

Abstract

In this evaluation paper, we discuss convolutional neural network (CNN)-based approaches for human activity recognition. In particular, we investigate CNN architectures designed to capture temporal information in videos and their applications to the human activity recognition problem. There have been multiple previous works to use CNN-features for videos. These include CNNs using 3-D XYT convolutional ﬁlters, CNNs using pooling operations on top of per-frame image-based CNN descriptors, and recurrent neural networks to learn temporal changes in per-frame CNN descriptors. We experimentally compare some of these diﬀerent representatives CNNs while using ﬁrst-person human activity videos. We especially focus on videos from a robots viewpoint, captured during its operations and human-robot interactions.

Citation Download Citation

M. S. Ryoo and Larry Matthies "Video-based convolutional neural networks for activity recognition from robot-centric videos", Proc. SPIE 9837, Unmanned Systems Technology XVIII, 98370R (13 May 2016); https://doi.org/10.1117/12.2229531

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available