TY - GEN
T1 - Synthesis-based low-cost gaze analysis
AU - Chang, Zhuoqing
AU - Qiu, Qiang
AU - Sapiro, Guillermo
N1 - Publisher Copyright:
© Springer International Publishing Switzerland 2016.
PY - 2016
Y1 - 2016
N2 - Gaze analysis has gained much popularity over the years due to its relevance in a wide array of applications, including humancomputer interaction, fatigue detection, and clinical mental health diagnosis. However, accurate gaze estimation from low resolution images outside of the lab (in the wild) still proves to be a challenging task. The new Intel low-cost RealSense 3D camera, capable of acquiring submillimeter resolution depth information, is currently available in laptops, and such technology is expected to become ubiquitous in other portable devices. In this paper, we focus on low-cost, scalable and real time analysis of human gaze using this RealSense camera. We exploit the direct measurement of eye surface geometry captured by the RGB-D camera, and perform gaze estimation through novel synthesis-based training and testing. Furthermore, we synthesize different eye movement appearances using a linear approach. From each 3D eye training sample captured by the RealSense camera, we synthesize multiple novel 2D views by varying the view angle to simulate head motions expected at testing. We then learn from the synthesized 2D eye images a gaze regression model using regression forests. At testing, for each captured RGB-D eye image, we first repeat the same synthesis process. For each synthesized image, we estimate the gaze from our gaze regression model, and factor-out the associated camera/head motion. In this way, we obtain multiple gaze estimations for each RGB-D eye image, and the consensus is adopted. We show that this synthesis-based training and testing significantly improves the precision in gaze estimation, opening the door to true low-cost solutions.
AB - Gaze analysis has gained much popularity over the years due to its relevance in a wide array of applications, including humancomputer interaction, fatigue detection, and clinical mental health diagnosis. However, accurate gaze estimation from low resolution images outside of the lab (in the wild) still proves to be a challenging task. The new Intel low-cost RealSense 3D camera, capable of acquiring submillimeter resolution depth information, is currently available in laptops, and such technology is expected to become ubiquitous in other portable devices. In this paper, we focus on low-cost, scalable and real time analysis of human gaze using this RealSense camera. We exploit the direct measurement of eye surface geometry captured by the RGB-D camera, and perform gaze estimation through novel synthesis-based training and testing. Furthermore, we synthesize different eye movement appearances using a linear approach. From each 3D eye training sample captured by the RealSense camera, we synthesize multiple novel 2D views by varying the view angle to simulate head motions expected at testing. We then learn from the synthesized 2D eye images a gaze regression model using regression forests. At testing, for each captured RGB-D eye image, we first repeat the same synthesis process. For each synthesized image, we estimate the gaze from our gaze regression model, and factor-out the associated camera/head motion. In this way, we obtain multiple gaze estimations for each RGB-D eye image, and the consensus is adopted. We show that this synthesis-based training and testing significantly improves the precision in gaze estimation, opening the door to true low-cost solutions.
UR - http://www.scopus.com/inward/record.url?scp=84978259221&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84978259221&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-40542-1_15
DO - 10.1007/978-3-319-40542-1_15
M3 - Conference contribution
AN - SCOPUS:84978259221
SN - 9783319405414
T3 - Communications in Computer and Information Science
SP - 95
EP - 100
BT - HCI International 2016 – Posters’ Extended Abstracts - 18th International Conference, HCI International 2016, Proceedings
A2 - Stephanidis, Constantine
PB - Springer Verlag
T2 - 18th International Conference on Posters’ Extended Abstracts, HCI International 2016
Y2 - 17 July 2016 through 22 July 2016
ER -