In this work we propose AlertnessScanner, a computer-vision based system that collects in-situ pupil information to model alertness in the wild. Based on previous work that shows that pupil size can be used to infer alertness, we developed an Android application that measures pupil size from pictures captured by the front-facing camera of a smartphone. We conducted two in-the-wild studies to evaluate the effectiveness of our solution and found that AlertnessScanner can passively and unobtrusively assess alertness.
