Gaze direction detection from thermal camera image
Sewoong Jun, Il-Kyun Jung · International Conference on Instrumentation, Measurement, Circuits and Systems · 2012
This paper presents a new system to estimate the head pose of human in interactive indoor environment that has dynamic illumination change and large working space. The main idea of this system is to suggest a new morphological feature for estimating head angle from Thermal Camera. When a thermal camera shows distribution of face heat, there are obviously some morphological distributions. Applying a threshold to the heat distribution, we also obtain the different morphology image from different head yaw pose. Therefore, we can obtain the morphological shape of heat distribution of face. Through the analysis of this morphological property, the head pose can be estimated. It is simple and significantly invariant from illumination in comparison with other algorithm which adopts normal camera as a sensor. Our system can automatically segment and estimate head pose in a wide range of head motion without manual initialization like other optical flow system. As the result of experiments, we obtained the reliable head orientation data under the real-time performance.