DocumentCode :
3499098
Title :
Rejection of Non-meaningful Activities
Author :
Xiao-Hui, Liu ; Chin-Seng, Chua
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ.
fYear :
2006
fDate :
2-6 April 2006
Firstpage :
189
Lastpage :
196
Abstract :
The rejection of non-meaningful activities is an important issue in human activity recognition (HAR) systems. This rejection is often operated as a hypothesis test based on a model representing all non-meaningful patterns. Such a ´non-meaningful´ model is often difficult to obtain in reality. This paper presents a new test, the pairwise likelihood ratio test (PLRT), to reject non-meaningful activities. The model for non-meaningful activities is not required in this test. Moreover, instead of using a fixed likelihood-ratio threshold, the distribution of the likelihood ratios is used as a measurement to improve the rejection accuracy. Two approaches to combine multiple PLRTs into a stronger classifier are also presented
Keywords :
gesture recognition; maximum likelihood detection; pattern classification; surveillance; human activity recognition systems; nonmeaningful activities; pairwise likelihood ratio test; rejection accuracy; Face recognition; Hidden Markov models; Humans; Light rail systems; Performance evaluation; Surveillance; Test pattern generators; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Automatic Face and Gesture Recognition, 2006. FGR 2006. 7th International Conference on
Conference_Location :
Southampton
Print_ISBN :
0-7695-2503-2
Type :
conf
DOI :
10.1109/FGR.2006.91
Filename :
1613019
Link To Document :
بازگشت