An effective eye states detection method based on the projection of the gray interval distribution

Eye state estimation has been widely applied in many real-world systems, e.g., driver monitoring and smart television. However, it is still an open issue towards accurate and realtime estimation, especially under the scenario of uncontrolled scenes, for instance severely occlusion, viewpoint change, and illumination variances. In this paper, we introduce a robust eye state estimation algorithm, the core of which is a novel discriminative and fast feature encoding scheme to represent the eye state. To further improve the robustness, we also introduce a brightness adjustment algorithm to overcome the variances of environmental illumination. The experimental results demonstrate that our algorithm is extremely effective under various illumination conditions. The proposed algorithm has also been integrated into the next-generation AOC intelligent TV systems.