Intelligent Fatigue Detection System Based on Image Processing

Daza A.; Ramirez-Coria J.; Alarcón Y. · Lecture Notes in Networks and Systems (2026) · DOI: 10.1007/978-3-032-12882-9_15

Resumen

It is a fact that many traffic accidents are caused by fatigue, the main objective of this paper was to develop a system with the possibility of alerting the driver if there is the presence of fatigue in which image processing tools and methods were used. Developed for the Python programming language, the Haar Cascade classifier was considered for the detection of frontal faces, libraries such as OpenCV and Dlib to locate landmaks in eyes and lips, which were used to find the EAR and Yawn parameters. or the training, 20 videos were used in real time and for the test, 40 videos in real time in front of a camera connected to a computer, as results an eye closure accuracy of 92.5%, a yawning accuracy of 95%, Additionally, a fatigue detection accuracy of 90% was obtained. In conclusion, it was determined that the proposed system is highly effective in detecting the presence of fatigue and, as a consequence, being able to mitigate accidents on the roads. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Instituciones: Universidad César Vallejo