Human activity encoding and recognition using low-level visual features

Zheshen Wang, Baoxin Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

Automatic recognition of human activities is among the key capabilities of many intelligent systems with vision/perception. Most existing approaches to this problem require sophisticated feature extraction before classification can be performed. This paper presents a novel approach for human action recognition using only simple low-level visual features: motion captured from direct frame differencing. A codebook of key poses is first created from the training data through unsupervised clustering. Videos of actions are then coded as sequences of super-frames, defined as the key poses augmented with discriminative attributes. A weighted-sequence distance is proposed for comparing two super-frame sequences, which is further wrapped as a kernel embedded in a SVM classifier for the final classification. Compared with conventional methods, our approach provides a flexible non-parametric sequential structure with a corresponding distance measure for human action representation and classification without requiring complex feature extraction. The effectiveness of our approach is demonstrated with the widely-used KTH human activity dataset, for which the proposed method outperforms the existing state-of-the-art.

Original languageEnglish (US)
Title of host publicationIJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence
PublisherInternational Joint Conferences on Artificial Intelligence
Pages1876-1882
Number of pages7
ISBN (Print)9781577354260
StatePublished - Jan 1 2009
Event21st International Joint Conference on Artificial Intelligence, IJCAI 2009 - Pasadena, United States
Duration: Jul 11 2009Jul 16 2009

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823

Conference

Conference21st International Joint Conference on Artificial Intelligence, IJCAI 2009
CountryUnited States
CityPasadena
Period7/11/097/16/09

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Human activity encoding and recognition using low-level visual features'. Together they form a unique fingerprint.

  • Cite this

    Wang, Z., & Li, B. (2009). Human activity encoding and recognition using low-level visual features. In IJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence (pp. 1876-1882). (IJCAI International Joint Conference on Artificial Intelligence). International Joint Conferences on Artificial Intelligence.