Temporal Segmentation and Activity Classification from First-person Sensing - Robotics Institute Carnegie Mellon University

Temporal Segmentation and Activity Classification from First-person Sensing

Ekaterina H. Spriggs, Fernando De la Torre Frade, and Martial Hebert
Workshop Paper, CVPR '09 Workshop on Egocentric Vision, pp. 17 - 24, June, 2009

Abstract

Temporal segmentation of human motion into actions is central to the understanding and building of computational models of human motion and activity recognition. Several issues contribute to the challenge of temporal segmentation and classification of human motion. These include the large variability in the temporal scale and periodicity of human actions, the complexity of representing articulated motion, and the exponential nature of all possible movement combinations. We provide initial results from investigating two distinct problems - classification of the overall task being performed, and the more difficult problem of classifying individual frames over time into specific actions. We explore first-person sensing through a wearable camera and Inertial Measurement Units (IMUs) for temporally segmenting human motion into actions and performing activity classification in the context of cooking and recipe preparation in a natural environment. We present baseline results for supervised and unsupervised temporal segmentation, and recipe recognition in the CMU-Multimodal activity database (CMU-MMAC).

BibTeX

@workshop{Spriggs-2009-10239,
author = {Ekaterina H. Spriggs and Fernando De la Torre Frade and Martial Hebert},
title = {Temporal Segmentation and Activity Classification from First-person Sensing},
booktitle = {Proceedings of CVPR '09 Workshop on Egocentric Vision},
year = {2009},
month = {June},
pages = {17 - 24},
keywords = {first-person vision, activity recognition, multi-modal data, CMU-MMAC},
}