Real-Time Head Action Recognition Based on HOF and ELM

Tie HONG  Yuan Wei LI  Zhi Ying WANG  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.1   pp.206-209
Publication Date: 2019/01/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDL8191
Type of Manuscript: LETTER
Category: Pattern Recognition
Keyword: 
action recognition,  head action recognition,  histograms of flow orientations (HOF),  extreme learning machine (ELM),  

Full Text: PDF(797.9KB)
>>Buy this Article


Summary: 
Head action recognition, as a specific problem in action recognition, has been studied in this paper. Different from most existing researches, our head action recognition problem is specifically defined for the requirement of some practical applications. Based on our definition, we build a corresponding head action dataset which contains many challenging cases. For action recognition, we proposed a real-time head action recognition framework based on HOF and ELM. The framework consists of face detection based ROI determination, HOF feature extraction in ROI, and ELM based action prediction. Experiments show that our method achieves good accuracy and is efficient enough for practical applications.