期刊论文

Chen, Jingying

英文

Neurocomputing

0925-2312

2016

173

P1

42-53

10.1016/j.neucom.2015.03.096

This work was supported by the National Key Technology Research and Development Program (no. 2013BAH18F02 ), Research funds from Ministry of Education and China Mobile ( MCM20130601 ), Research Funds of CCNU from the Colleges׳ Basic Research and Operation of MOE ( CCNU13B001 ), Research funds from the Humanities and Social Sciences Foundation of the Ministry of Education (no. 14YJAZH005 ), Central China Normal University Research Start-up funding (no. 120005030223 ), The Scientific Research Foundation for the Returned Overseas Chinese Scholars (no. (2013)693 ), Research Funds of CCNU from the Colleges׳ Basic Research and Operation of MOE (no. CCNU14A05020 , no. CCNU14A05019 ), National Natural Science Foundation of China (no. 61272206 ), National Key Technology Research and Development Program (no. 2014BAH22F01 ).

本校为第一且通讯机构

Head pose estimation (HPE) is important in human-machine interfaces. However, various illumination, occlusion, low image resolution and wide scene make the estimation task difficult. Hence, a Dirichlet-tree distribution enhanced Random Forests approach (D-RF) is proposed in this paper to estimate head pose efficiently and robustly in unconstrained environment. First, positive/negative facial patch is classified to eliminate influence of noise and occlusion. Then, the D-RF is proposed to estimate the head pose in a coarse-to-fine way using more powerful combined texture and geometric features o...