Graduate project

Driver Drowsiness Detection on Raspberry Pi 4

Motor vehicle crashes involving drowsy driving are huge in numbers all over the world. Many studies revealed that 10 to 30% of crashes are due to drowsy driving. Fatigue has costly effects on the safety, health, and quality of life. We can detect this drowsiness of driver using various methods, e.g., algorithms based on behavioral gestures, physiological signals and vitals. Also, few of them are vehicle based. Drowsiness of driver was detected based on steering wheel movement and lane change patterns. A pattern is derived based on slow drifting and fast corrective steering movement. We developed a prototype that detects the drowsiness of an automobile driver using artificial intelligence techniques, precisely using open-source tools like TensorFlow Lite on a Raspberry Pi development board. The TensorFlow model is trained on images captured from the video with the help of object detection using Cascade Classifier. In order to have a better accuracy, an Inception v3 architecture is used in pre-training the model with the image dataset. We create and train the final model using long short-term memory (LSTM) and then convert the final TensorFlow model to TensorFlow Lite model and use this lite model on Raspberry Pi board to detect the drowsiness of driver.