Human Action Segmentation via Controlled Use of Missing Data in HMMs

Authors:
Patrick Peursum;Hung H. Bui;Svetha Venkatesh;Geoff West
Affiliations:
Curtin University of Technology, Western Australia;SRI International, USA;Curtin University of Technology, Western Australia;Curtin University of Technology, Western Australia
Venue:
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Year:
2004

Citing 0
Cited 5

Robust recognition and segmentation of human actions using HMMs with missing observations

EURASIP Journal on Applied Signal Processing
Activity recognition via user-trace segmentation

ACM Transactions on Sensor Networks (TOSN)
Recognising online spatial activities using a bioinformatics inspired sequence alignment approach

Pattern Recognition
Activity recognition through goal-based segmentation

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 1
A survey of vision-based methods for action representation, segmentation and recognition

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

Segmentation of individual actions from a stream of human motion is an open problem in computer vision. This paper approaches the problem of segmenting higher-level activities into their component sub-actions using Hidden Markov Models modified to handle missing data in the observation vector. By controlling the use of missing data, action labels can be inferred from the observation vector during inferencing, thus performing segmentation and classification simultaneously. The approach is able to segment both prominent and subtle actions, even when subtle actions are grouped together. The advantage of this method over sliding windows and Viterbi state sequence interrogation is that segmentation is performed as a trainable task, and the temporal relationship between actions is encoded in the model and used as evidence for action labelling.