TY - GEN
T1 - Partially occluded head posture estimation for 2D images using pyramid HOG features
AU - Wu, Jun
AU - Shang, Zongjiang
AU - Wang, Kaiwei
AU - Zhai, Jiarong
AU - Wang, Yiting
AU - Xia, Fang
AU - Li, Wenyuan
AU - Zhang, Jiajia
AU - Zhang, Fan
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - Automatic head posture recognition is essential in the human-centered AI applications such as counting watching people in a bus or lift advertising system. A partially-occluded head posture estimation algorithm based on a histogram of gradient orientation (HoG) in a pyramid setting is proposed. We first apply face detection to a 2D image, and then divide the detected face region into two sub-regions, mouth and eye areas, to predict whether there is an occlusion in these two sub-regions individually. According to the predicted occlusion status, pyramid HoG features are extracted from non-occluded face sub-region. Finally, a support vector machine is applied for model training. Experimental results show that our proposed method has high accuracy, speed, and robustness in terms of illumination, shadow, occlusion, and complex background. The average recognition accuracy on the CMU-PIE dataset is 95.24% (94.22% with full mouth area occlusion), and that on the CAS-PEAL-R1 dataset is 95.61%. In addition, the contribution of the eye area is significantly bigger than that of the mouth area. Our method has potential commercial values and broad application prospects for intelligent human-machine interaction.
AB - Automatic head posture recognition is essential in the human-centered AI applications such as counting watching people in a bus or lift advertising system. A partially-occluded head posture estimation algorithm based on a histogram of gradient orientation (HoG) in a pyramid setting is proposed. We first apply face detection to a 2D image, and then divide the detected face region into two sub-regions, mouth and eye areas, to predict whether there is an occlusion in these two sub-regions individually. According to the predicted occlusion status, pyramid HoG features are extracted from non-occluded face sub-region. Finally, a support vector machine is applied for model training. Experimental results show that our proposed method has high accuracy, speed, and robustness in terms of illumination, shadow, occlusion, and complex background. The average recognition accuracy on the CMU-PIE dataset is 95.24% (94.22% with full mouth area occlusion), and that on the CAS-PEAL-R1 dataset is 95.61%. In addition, the contribution of the eye area is significantly bigger than that of the mouth area. Our method has potential commercial values and broad application prospects for intelligent human-machine interaction.
KW - Head Posture Estimation
KW - Partially Occluded
KW - Pyramid HOG
KW - Support Vector Machine
UR - http://www.scopus.com/inward/record.url?scp=85071451598&partnerID=8YFLogxK
U2 - 10.1109/ICMEW.2019.00093
DO - 10.1109/ICMEW.2019.00093
M3 - 会议稿件
AN - SCOPUS:85071451598
T3 - Proceedings - 2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019
SP - 507
EP - 512
BT - Proceedings - 2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019
Y2 - 8 July 2019 through 12 July 2019
ER -