The article has two goals. The first one is to present an original benchmark database for testing methods and algorithms for driver fatigue detection. Blinking eyes – opening and closing, squinting eyes, rubbing eyes, yawning, lowering the head and shaking the head are considered. The database includes recordings acquired from a thermal, depth map and visible light cameras. The imaging environment mimicked the conditions characteristic for driver's place of work. The second goal is to present a part of collected data. As an example of driver fatigue the eye rubbing motion was selected and the detection was made using contemporary TensorFlow-based detector, known to be accurate when working in visible lighting conditions. The results of driver's drowsiness detection in thermal and depth map imagery are compared with the detector's efficiency in the visible spectrum.
CITATION STYLE
Małecki, K., Forczmański, P., Nowosielski, A., Smoliński, A., & Ozga, D. (2020). A new benchmark collection for driver fatigue research based on thermal, depth map and visible light imagery. In Advances in Intelligent Systems and Computing (Vol. 977, pp. 295–304). Springer Verlag. https://doi.org/10.1007/978-3-030-19738-4_30
Mendeley helps you to discover research relevant for your work.