caa a22 4500 605446881 CHVBK 20210128100129.0 cr unu---uuuuu 210128e20151101xx s 000 0 eng 10.1007/s11042-014-2110-3 doi (NATIONALLICENCE)springer-10.1007/s11042-014-2110-3 Fast and robust head detection with arbitrary pose and occlusion [Elektronische Daten] [Tao Zhang, Zhijie Yang, Wenjing Jia, Qiang Wu, Jie Yang, Xiangjian He] Head detection in images and videos plays an important role in a wide range of computer vision and surveillance applications. Aiming to detect heads with arbitrarily occluded faces and head pose, in this paper, we propose a novel Gaussian energy function based algorithm for elliptical head contour detection. Starting with the localization of head and shoulder by an improved Gaussian Mixture Model (GMM) approach, the precise head contour is obtained by making use of the Omega shape formed from the head and shoulder. Experimental results on several benchmark datasets demonstrate the superiority of the proposed idea over the state-of-the-art in both detection accuracy and processing speed, even though there are various types of severe occlusions in faces. Springer Science+Business Media New York, 2014 Head detection nationallicence Gaussian energy function nationallicence Omega shape nationallicence Improved GMM nationallicence Arbitrary pose and occlusion nationallicence Zhang Tao Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, 800 Dongchuan Road, 200000, Shanghai, China aut Yang Zhijie Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, 800 Dongchuan Road, 200000, Shanghai, China aut Jia Wenjing Faculty of Engineering and Information Technology, University of Technology, Sydney, PO Box 123, 2007, Broadway, NSW, Australia aut Wu Qiang Faculty of Engineering and Information Technology, University of Technology, Sydney, PO Box 123, 2007, Broadway, NSW, Australia aut Yang Jie Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, 800 Dongchuan Road, 200000, Shanghai, China aut He Xiangjian Faculty of Engineering and Information Technology, University of Technology, Sydney, PO Box 123, 2007, Broadway, NSW, Australia aut Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/21(2015-11-01), 9365-9385 1380-7501 74:21<9365 2015 74 11042 https://doi.org/10.1007/s11042-014-2110-3 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s11042-014-2110-3 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Zhang Tao Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, 800 Dongchuan Road, 200000, Shanghai, China aut NATIONALLICENCE 700 1- Yang Zhijie Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, 800 Dongchuan Road, 200000, Shanghai, China aut NATIONALLICENCE 700 1- Jia Wenjing Faculty of Engineering and Information Technology, University of Technology, Sydney, PO Box 123, 2007, Broadway, NSW, Australia aut NATIONALLICENCE 700 1- Wu Qiang Faculty of Engineering and Information Technology, University of Technology, Sydney, PO Box 123, 2007, Broadway, NSW, Australia aut NATIONALLICENCE 700 1- Yang Jie Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, 800 Dongchuan Road, 200000, Shanghai, China aut NATIONALLICENCE 700 1- He Xiangjian Faculty of Engineering and Information Technology, University of Technology, Sydney, PO Box 123, 2007, Broadway, NSW, Australia aut NATIONALLICENCE 773 0- Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/21(2015-11-01), 9365-9385 1380-7501 74:21<9365 2015 74 11042