Robust Detection of Fatigue Parameters Based on Infrared Information

Abstract

Driver fatigue is one of the major causes of traffic accidents, and this need has increased the amount of driver fatigue detection systems in vehicles in order to reduce human and material losses. This work puts forward an approach based on capturing near-infrared videos from a camera mounted inside the vehicle. Then, from the captured images and using image-processing techniques the eyes are detected. Next, features are extracted from eye images using several transforms and finally, the system detects if there is fatigue or not using a SVM as classifier. Throughout the recording, eye position is tracked with a low computational time and fatigue is analysed based on the percentage of eyelid closure. This approach has been developed on two public datasets. Our experiments were able to reach an eye recognition rate of up to 96.87% and our results showed that SVM with RBF kernel were 99.66% accurate on one of the databases used for the system training. This approach shows promising results in comparison with the state of the art and deep learning approaches in order to be implemented in real conditions.INDEX TERMS Eye detection and identification, infrared imaging, fatigue parameters, pattern recognition.

Comparison of Potential Road Accident Detection Algorithms for Modern Machine Vision System

“…-improvement of data mining approaches for extracting essential for road safety information from the data outdoor cameras [19,20]; -investigation of methods for complex analysis of data mentioned before [21,22].…”

Smart education case: a detection method of the driver's smoking behavior

“…Traditional smoking detection methods include smoke detection, temperature detection, bright spot detection, and parallel line detection, among others [1]. Among them, the smoke detection method mainly uses computer vision object detection algorithms to detect the smoke area generated by the driver's smoking, and performs morphological processing on suspected smoke areas, analyzing their characteristics such as area growth and morphological changes to distinguish and determine whether the driver is smoking [2]. The bright spot detection method detects bright spots, namely cigarette butts, in the driver's facial area to determine whether the driver is smoking.…”

Development of Drivers’ Psychophysiological State Detection Measures and Relevant Machine Learning Methods

“…Drivers' fatigue, drowsiness or distraction can be detected using eye indicators such as eye aspect ratio (EAR), eye blinking duration, PERCLOS, eye status recognition (open or closed), red eyes, longer duration of closed eyes (Boucetta et al 2021;Lim et al 2021;Nosseir and El-sayed 2020;Quddus, Zandi et al 2021;Ryan et al 2021;Travieso-González et al 2021;Victoria and Mary 2021;Xiang et al 2021;Xue-Da SHANG 2021). Usually, mouth features are combined with eye features to ensure drivers' psychophysiological states.…”

“…It has a wide range of usage especially in face and image recognition, speech recognition and text categorization. In addition, the method has proven significance in validating, detecting and classifying facial features (Karamizadeh et al 2014;Travieso-González et al 2021;Valsan et al 2021;Zhongwei et al 2021). Moreover, it was used to detect diver's psychophysiological state by classifying EEG (Ahmadi et al 2021) and sEMG (Lu et al 2021).…”