DRIVER DROWSINESS DETECTION USING MACHINE LEARNING IMAGE PROCESSING
Abstract : Drowsiness of drivers is one of the significant cause of road accidents. Every year, there is an increase in the amount of deaths and fatal injuries globally. By detecting the driver’s drowsiness, road accidents can be reduced. This paper describes a machine learning approach for drowsiness detection. Face detection is employed to locate the regions of the driver’s eyes, which are used as the templates for eye tracking in subsequent frames. Finally, the tracked eye’s images are used for drowsiness detection in order to generate warning alarms. This proposed approach has three stages: detecting Face, detecting Eyes and detecting drowsiness. Image processing is used to recognize the face of the driver and then its extracts the image of the eyes of the driver for detection of drowsiness. The HAAR face detection algorithm takes as captured frames of image and then the detected face is considered as output. Next, CHT is used for tracking eyes from the detected face. Using EAR (Eye Aspect Ratio) the eye state is detected. The proposed system was tested by implementing the proposed approach on a Raspberry pi 3 Model B with 1GB RAM with use of Logitech HD Webcam C270. The system uses frames for face and eye tracking, and the average correct rate for eye location and tracking could achieve 95.0% based on some test videos. Thus, the proposed approach for a real-time of driver drowsiness detection is a low cost and effective solution method.
• Drowsiness or lack of attention of the driver is considered the primary cause for such mishaps. Driver drowsiness monitoring research can help minimize accidents.
• This focused on the localization of the eyes and mouth, which involves looking at the entire image of the face, and determining the position of the eyes and mouth, by applying the existing methods in imageprocessing algorithm.
• After gone through the research papers and the existing methods, this project proposed that eyes and yawning detection method will be used.
• A thorough observation was done on the existing method to detect the drowsiness. Different parameters have been used by previous researches.
• Heavy traffic, increasing automotive population, adverse driving conditions, tight commute time requirements and the work loads are few major reasons behind such fatigue.
• The deep learning approaches, especially the Convolutional Neural Networks (CNNs) methods, has gained prominence in resolving challenging classifications problems.
• Although these approaches have proven relatively effective for examining physiological and cognitive states in humans, issues with wearability, have limited the feasibility of using these systems in real-world driving conditions.
• The movement of the camera shows a great impact as it varies at certain points (Speed brakers) on the roads.
• This problem will increase day by day. So, there is a requirement of designing detection systems for the driver drowsiness or inattention and can produce some warning alarms to alert the driver and the further people in the vehicle.
• Although it can be trained to detect a variety of object classes, it was motivated primarily by the problem of face detection.
• In such a case when fatigue is detected, a warning signal is issued to alert the driver.
• DL has been broadly applied recently to overcome problematic issues that cannot be properly solved using conventional methods.
• This paper proposes a drowsiness detection system based on multilayers perceptron classifiers.
• The open eye is detected using the proposed iris–sclera pattern analysis(ISPA) method.
• In the proposed system a nonintrusive driver drowsiness monitoring system has been developed using computer vision techniques.
• In this paper, they propose a DriCare, approach whereby drivers are identified with video images without using devices like yawning, blinking, and closure of the eyes.
• The proposed model will improve the test and validation accuracy and reduce the overfitting problem. The problem will overcome with the help 14 layers deep neural.
• In this field, we are analyzed different experimentation for Real-Time DDD System. In a practical simulation setting, we took careful care to carry out our test testing.
• While certain traditional models can detect the positions of several facials, the eyes and mouth areas of the driver cannot be established. However, the driver will practically have diverse and complex facial expressions that distort their detection.
• Convolutional Neural Networks (CNNs) methods have largely produced an outlandish performance in the drowsiness detecting area and are also a powerful aid to various classification tasks.
• The use of these new technologies and methodologies can be an effective way to not only increase the efficiencies of the existing real-time driver drowsiness detection system but also provide a tool that can be widely used by drivers.
• Moreover, it has been established that the efficiency of the model drops in the cases of wearing sunglasses because the algorithm is not able to detect the driver's eyes.
• The performance of the algorithm is tested on Zhejiang University (ZJU) Database and achieved successful results is identify the height of the iris.
• For enhancing the classification performance of drowsiness detection in a complex background, a multi-objective machine learning classifier is to be designed.
• The performance is greatly affected by the frame rate used to capture images of the driver’s face.
• For enhancing the accuracy of drowsiness classification, an efficient dimensionality reduction approach and a combination of both high-level and low-level features are to be used.
|