Driver's Drowsiness Detection
01 Oct 2019-pp 1622-1625
TL;DR: An algorithm is proposed that uses eye and mouth vertical distances, eye closure, yawning and other engineered facial features to detect driver drowsiness and the rate at which the driver is drowsy.
Abstract: The amelioration of technology from the past 50 years accommodated a good amount of succour to the driver by providing a great level of comfort and safety in the vehicles. The accidents may occur because of many reasons and one of the reason which we are going to portray and solve in this paper is driver fatigue. In this paper, we are going to use Artificial Intelligence-based advanced algorithms to detect driver fatigue and the rate at which the driver is drowsy. We propose an algorithm that uses eye and mouth vertical distances, eye closure, yawning and other engineered facial features to detect driver drowsiness.
Citations
More filters
01 Jan 2021
TL;DR: In this article, the authors proposed an algorithm for real-time and continuous driver authentication and drowsiness detection using face recognition with dlib face detector which is found to be robust compared to openCV face detector.
Abstract: Driver’s drowsiness is one of the main causes of the car collision, which raise fatality and wound count worldwide. This makes it necessary to develop a system that ensures the safety of the driver as well as co-passengers. Further, driver authentication plays an important role in preventing car robberies and fraudulent switching of designated drivers, thus ensuring the security of the vehicle and passengers. In this work, we propose an algorithm for real-time and continuous driver authentication and drowsiness detection. Driver authentication is implemented using face recognition with dlib’s face detector which is found to be robust compared to openCV face detector. The SMS regarding authentication of the driver is sent to the vehicle owner with details so that he can keep track of drivers. Further, if the driver is authenticated, then he is monitored continuously using the webcam to detect the early signs of drowsiness. Behavioral measures of the driver-like eyelid movements and yawning are considered for the detection. First, for face detection, we will apply facial landmark detection made using Histogram of Oriented Gradients (HOG) feature and then extract the eye and mouth regions using shape predictor with 68 salient points next to the eye aspect ratio and mouth aspect ratio, i.e., EAR and MAR, respectively, are computed in order to determine if these ratios indicate that the driver is drowsy, if so then he is alerted using speech message.
2 citations
01 Jan 2021
TL;DR: In this paper, a real-time monitoring of drowsiness of the driver, to forestall accidents is proposed, which consists of a small security camera pointing directly into the driver's face.
Abstract: This research paper is proposed a real-time monitoring of drowsiness of the driver, to forestall accidents. With the expansion in population, there has been an incredible increase in road accidents. In India, around 60% of the accidents are caused because of driver fatigue. So, this paper is proposed to detect drowsiness of drivers by capturing video frames of eye closure patterns. This system consists of a small security camera pointing directly into the driver's face. It monitors the eyes of the driver and their closure patterns. The face area and position of eyes are pinpointed by the Viola–Jones object detection algorithm. It uses a 6-coordinate of eye to seek out whether eyes are close or open, using a Haar cascade classifier. When 20 consecutive frames are detected with eyelids aspect ratio less than 0.25, then the system comes to a result that the driver is drowsy and issues an alert.
1 citations
01 Jan 2022
TL;DR: In this paper, the authors present a comprehensive analysis of the existing methods of drowsiness detection based on physiological parameter-based techniques which can be deployed as a convenient and feasible system.
Abstract: Drowsiness is generally defined as half-sleep caused mainly by fatigue or lack of complete sleep. In past decade, many researches have been conducted in support of drowsiness detection for drivers with main focus on facial expression recognition, vehicle’s movement and physiological signals such as Electroencephalogram (EEG), Electrooculography (EOG), and Electrocardiogram (ECG). This paper presents a comprehensive analysis of the existing methods of drowsiness detection based on physiological parameter-based techniques which can be deployed as a convenient and feasible system. The study also discusses the pros and cons of the diverse methods. Finally, an approach for the detection model is proposed, based on the research findings achieved after an extensive survey. As per the dataset used, the proposed model is able to achieve an accuracy of 90%. Also the proposed model is easy to wear because of its compact size. The system is also fast and starts generating results just after 10 s of its start.
Journal Article•
TL;DR: In this article, a nonintrusive framework was proposed to separate the facial landmarks spots of the driver using the Region of Interest and learn the eye perspective extent and sort the eyes as closed or open.
Abstract: Drowsiness can be depicted as a characteristic state where the body is encountering significant change from an attentive state to a napping state. At this stage, a driver can lose attention and will not be able to do activities, for instance, avoiding head-on accidents or slowing down fortunately. There are obvious signs that can suggest whether a driver is tired or not, like, frequent yawning, and inability to keep eyes open etc. Face composition also changes because of the blood circulation system. This research work aims to create a nonintrusive framework that can separate the facial landmarks spots of the driver using the Region of Interest and learn the eye perspective extent and sort the eyes as closed or open.
05 May 2023
TL;DR: In this paper , the authors used RNN and classifiers to extract the facial landmarks, and a 3D locator was used for estimation to determine the driver's drowsiness.
Abstract: Driver drowsiness is one of the leading causes of accidents and has become a hot research topic. This paper gives an overview of detecting the drowsiness of drivers using behavioral metrics and machine learning approaches. The face imparts a great deal of information (eye blinks, head motions, etc.) which can be utilized to deduce sleepiness. By recognizing the driver's drowsiness and notifying the driver, Computer vision techniques and Image processing technologies can minimize most accidents. This research addresses the issue by identifying key factors such as eye closure, yawning, and head orientation. To determine this, Recurrent Neural Network (RNN) and classifiers were used to extract the facial landmarks, and a 3D locator was used for estimation. In many ways, the culminating results suggest that the real-time approach's performance outperforms the older approach.
References
More filters
01 Feb 2014
TL;DR: A vision based intelligent algorithm to detect driver drowsiness makes use of features learnt using convolutional neural network so as to explicitly capture various latent facial features and the complex non-linear feature interactions.
Abstract: The advancement of computing technology over the years has provided assistance to drivers mainly in the form of intelligent vehicle systems. Driver fatigue is a significant factor in a large number of vehicle accidents. Thus, driver drowsiness detection has been considered a major potential area so as to prevent a huge number of sleep induced road accidents. This paper proposes a vision based intelligent algorithm to detect driver drowsiness. Previous approaches are generally based on blink rate, eye closure, yawning, eye brow shape and other hand engineered facial features. The proposed algorithm makes use of features learnt using convolutional neural network so as to explicitly capture various latent facial features and the complex non-linear feature interactions. A softmax layer is used to classify the driver as drowsy or non-drowsy. This system is hence used for warning the driver of drowsiness or in attention to prevent traffic accidents. We present both qualitative and quantitative results to substantiate the claims made in the paper.
158 citations
"Driver's Drowsiness Detection" refers background in this paper
...[9] Dwivedi, K., Biswaranjan, K., Sethi, A. (2014, February).”...
[...]
...Kartik Dwivedi[9] invented a new drivers fatigue detection by anchoring multi-layer convolutional neural networks....
[...]
20 Nov 2016
TL;DR: A novel hierarchical temporal Deep Belief Network (HTDBN) method for drowsy detection that first extracts high-level facial and head feature representations and then uses them to recognize drowsiness-related symptoms.
Abstract: Drowsy driver alert systems have been developed to minimize and prevent car accidents. Existing vision-based systems are usually restricted to using visual cues, depend on tedious parameter tuning, or cannot work under general conditions. One additional crucial issue is the lack of public datasets that can be used to evaluate the performance of different methods. In this paper, we introduce a novel hierarchical temporal Deep Belief Network (HTDBN) method for drowsy detection. Our scheme first extracts high-level facial and head feature representations and then use them to recognize drowsiness-related symptoms. Two continuous-hidden Markov models are constructed on top of the DBNs. These are used to model and capture the interactive relations between eyes, mouth and head motions. We also collect a large comprehensive dataset containing various ethnicities, genders, lighting conditions and driving scenarios in pursuit of wide variations of driver videos. Experimental results demonstrate the feasibility of the proposed HTDBN framework in detecting drowsiness based on different visual cues.
148 citations
"Driver's Drowsiness Detection" refers methods in this paper
...2019 IEEE Region 10 Conference (TENCON 2019) 1623 VI. EXPERIMENTAL SETUP A. dataset description and experimental setup The driver fatigue dataset possessed by NTHU Computer Vision Lab[12] is used....
[...]
...The driver fatigue dataset possessed by NTHU Computer Vision Lab[12] is used....
[...]
23 Oct 2006
TL;DR: An improved slope algorithm is presented in this paper that uses first order linear difference with five steps to calculate curve slope and boundaries of eyes can be obtained.
Abstract: Driver fatigue is a key factor of accident. To solve the problem, eye tracking method is used to alarm tired drivers. To finalize this procedure, we took driver face images first by using a digital camera, then the images are processed and segmented. Then the horizontal projections of the detected objects in the binary images are analyzed. In this way, eye locations are obtained based on the horizontal projection histogram (e.g. at high peak of projection charts). And horizontal boundaries of eyes are located at the valley points. To determine the valley points, an improved slope algorithm is presented in this paper. We use first order linear difference with five steps to calculate curve slope. As a result, boundaries of eyes can be obtained. And eye pixels can be counted in the eye region. Spirit status of drivers can be detected by analyzing the eye pixel numbers.
117 citations
30 Nov 2005
TL;DR: The chaos theory was applied to explain the change of steering wheel motion and a strange trajectory called attractor was found by applying the Takens' theory of embedding to find out the chaos characteristics which can indicate that a driver is fired of driving and he/she may feel fatigue.
Abstract: This paper discusses the method to estimate a driver's fatigue through steering motion. Several methods are known to estimate driver's fatigue. In this research, the chaos theory was applied to explain the change of steering wheel motion. If there is chaos in the motion, a strange trajectory called attractor can be found by applying the Takens' theory of embedding. Experiments were conducted on a driving simulator. Steering wheel angle signals were processed first by fast Fourier transform (FFT) and also by the wavelet transform to determine which is better. Then attractor was plotted to find out the chaos characteristics, which can indicate that a driver is fired of driving and he/she may feel fatigue.
105 citations
20 Aug 2006
TL;DR: The experimental results show that intelligent vehicle control based on driver fatigue detection will be availability in traffic and a new real time eye tracking method based on unscented Kalman filter is proposed.
Abstract: Driver fatigue problem is one of the important factors that cause traffic accidents. Therefore the vision-based driver fatigue detection is the most prospective commercial applications of HCI. However, it is a challenging issue due to a variety of factors such as head and eyes moving fast, external illuminations interference and realistic lighting conditions, etc. This tends to significantly limit its scope of application. In this paper, we present an intelligent vehicle control based on driver fatigue detection. Firstly, the face is located using Haar algorithm and eye location is found with projection technique. After finding eye templates, we propose a new real time eye tracking method based on Unscented Kalman Filter. Thirdly, driver fatigue can be detected whether the eyes are closed over 5 consecutive frames using vertical projection matching. Finally, if driver fatigue is confirmed, the vehicle Cruise Control is start-up with slow speed, and maintains set slow speed such as 5 km/h. The experimental results show that intelligent vehicle control based on driver fatigue detection will be availability in traffic.
71 citations
"Driver's Drowsiness Detection" refers background in this paper
...It is proved in Zutao zang[10] paper that if the person closes his/her eyes for 5 seconds then he is considered as drowsy but in reality, we need more time to decide drowsiness of a person and the rate at which the person is drowsy is also not considered....
[...]