Drowsy Driver Alerting System
01 Mar 2018-
TL;DR: The software simulation is done through a witty MATLAB code to implement image processing methods for edge detection and determining the complexity value for the image, which gives the modeled hardware architecture which can be integrated as co-processor along with Nios II processor controlling the whole system flow, on a system based on Altera FPGA device.
Abstract: In this speeding world, the fatigue level of people has increased and their sleeping time has decreased. Various studies have registered that 20 % of all the road accidents are fatigue related. The drowsy driver alerting system is a vehicular safety system which will help to prevent accidents that are caused by drivers getting drowsy. This paper aims to use the behavior of the driver, including eye closure and head position. They are monitored by a camera and the driver is alerted if any of these drowsiness symptoms are detected. The software simulation is done through a witty MATLAB code to implement image processing methods for edge detection and determining the complexity value for the image. This code is converted into Simulink block which is further converted into a Verilog code using HDL coder. This gives the modeled hardware architecture which can be integrated as co-processor along with Nios II processor controlling the whole system flow, on a system based on Altera FPGA device. Altera FPGA processes the data in parallel and pipelined manner.
Citations
More filters
TL;DR: The design and implementation of a driver drowsiness detection (DDD) system using a modified RiscV processor on a field-programmable gate array (FPGA) and written C code for the trained CNN is optimized in numerous ways due to FPGA memory limitations.
Abstract: This paper describes the design and implementation of a driver drowsiness detection (DDD) system using a modified RiscV processor on a field-programmable gate array (FPGA). To detect drowsiness, Convolutional Neural Network (CNN) is implemented on a RiscV processor. The CNN is trained to classify four primary driver’s expressions, including distraction, natural, sleep, and yawn. The trained CNN accuracy is 81.07% on validation data. Furthermore, due to FPGA memory limitations, written C code for the trained CNN is optimized in numerous ways. Optimizations include the usage of dynamic fixed-point data types and dynamic memory allocations. On the other hand, the processor is modified by adding three custom instructions, including custom store, conv2d(2 × 2), and multiply and accumulation (MAC) to enhance the computation rate. As a result, the processor with custom store, conv2d(2 × 2), and MAC as custom instructions achieved the best result in terms of latency, with an improvement factor of 1.7 over the base processor and 1.25 over the processor with only custom store and multiply and accumulation (MAC) in exchange of slight increase in area.
2 citations
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.
References
More filters
TL;DR: The system was tested in a simulating environment with subjects of different ethnic backgrounds, different genders, ages, with/without glasses, and under different illumination conditions, and it was found very robust, reliable and accurate.
Abstract: This paper describes a real-time prototype computer vision system for monitoring driver vigilance. The main components of the system consists of a remotely located video CCD camera, a specially designed hardware system for real-time image acquisition and for controlling the illuminator and the alarm system, and various computer vision algorithms for simultaneously, real-time and non-intrusively monitoring various visual bio-behaviors that typically characterize a driver's level of vigilance. The visual behaviors include eyelid movement, face orientation, and gaze movement (pupil movement). The system was tested in a simulating environment with subjects of different ethnic backgrounds, different genders, ages, with/without glasses, and under different illumination conditions, and it was found very robust, reliable and accurate.
601 citations
TL;DR: This paper intends to perform the drowsiness prediction by employing Support Vector Machine (SVM) with eyelid related parameters extracted from EOG data collected in a driving simulator provided by EU Project SENSATION.
Abstract: Various investigations show that drivers' drowsiness is one of the main causes of traffic accidents. Thus, countermeasure device is currently required in many fields for sleepiness related accident prevention. This paper intends to perform the drowsiness prediction by employing Support Vector Machine (SVM) with eyelid related parameters extracted from EOG data collected in a driving simulator provided by EU Project SENSATION. The dataset is firstly divided into three incremental drowsiness levels, and then a paired t-test is done to identify how the parameters are associated with drivers' sleepy condition. With all the features, a SVM drowsiness detection model is constructed. The validation results show that the drowsiness detection accuracy is quite high especially when the subjects are very sleepy.
272 citations
TL;DR: A support vector machine-based posterior probabilistic model (SVMPPM) aimed at transforming the drowsiness level to any value of 0~1 instead of discrete labels is proposed, indicating that the combination of the proposed SVMPPM, the EEG headband, and the wrist-worn smart device constitutes an effective, simple, and inexpensive wearable solution for DDD.
Abstract: Driver drowsiness is a major cause of mortality in traffic accidents worldwide. Many physiological signals have been proposed to detect driver drowsiness. Among these signals, an electroencephalographic (EEG) signal, which reflects the brain activities, is more directly related to drowsiness. Thus, many EEG-based driver drowsiness detection (DDD) models gained more and more attention in recent years. However, one limitation of these studies is that these models merely estimate discrete labels and, thus, did not allow for estimating the relative severity of driver drowsiness. This paper proposes a support vector machine-based posterior probabilistic model (SVMPPM) for DDD, aimed at transforming the drowsiness level to any value of $0\sim 1$ instead of discrete labels. A fully wearable EEG system which consists of a Bluetooth-enabled EEG headband and a commercial smartwatch was used to evaluate the proposed model in a real-time way. Twenty subjects who participated in a 1-h monotonous driving simulation experiment were used to develop this model with fifteen subjects for a building model and five subjects for a testing model. According to a video-based reference, the proposed system obtained an accuracy of 91.25% for an alert group (73 out of 80 data sets), 83.78% for an early-warning group (93 out of 111 data sets), and 91.92% for a full-warning group (91 out of 99 data sets). These results indicate that the combination of the proposed SVMPPM, the EEG headband, and the wrist-worn smart device constitutes an effective, simple, and inexpensive wearable solution for DDD.
151 citations
05 Nov 2007
TL;DR: An real-time eye state detection system to identify driver's drowsy state is proposed and makes better balance between accuracy and efficiency than lots of other methods.
Abstract: Real time eye state detection is a key problem in driver drowsiness detection. This paper proposes an real-time eye state detection system to identify driver's drowsy state. The system optimize several image processing techniques to get better performance to reach the criteria of the drowsiness detection methods. Firstly, face region is detected using the optimized Haar-like feature detection scheme; secondly, we apply horizontal projection of the detected face and geometrical position of the eye on the face to get the eye region; finally, a new complexity function with dynamic threshold to identify the eye state. The method in our paper makes better balance between accuracy and efficiency than lots of other methods. The system is optimized with Intel IPP (Integrated Performance Primitives) and experiment results show that it can meet the acquisition of real time.
44 citations
"Drowsy Driver Alerting System" refers background in this paper
...If the driver’s eyes are open, the binary image will have both the interior boundaries within the eye and boundary between the eyes and the eyelids, thus giving more complexity through the complexity function [10]....
[...]
27 Dec 2005
TL;DR: Several well-known image processing algorithms like gray scale projection, edge detection with Prewitt operator and complexity function are combined together to judge whether the driver has his eyes closed to meet the basic requirements of drowsiness detection.
Abstract: A large number of traffic accidents are caused by the driver fatigue or drowsiness. These misfortunes can be avoided by keeping a close watch on tired characters of the driver and making a warning signal immediately. This function is implemented by a FPGA based vehicle driver surveillance system presented in this paper. Several well-known image processing algorithms like gray scale projection, edge detection with Prewitt operator and complexity function are combined together to judge whether the driver has his eyes closed. Their hardware architectures have been modeled using the Altera DSPBuilder and integrated as a co-processor to the main Nios II processor which controls the whole system. All of the algorithm hardware implementations have been achieved in a parallel and pipelined way and discussed in detail. The final system is based on the Altera Stratix II EP2S60 FPGA devices and has been proved to meet the basic requirements of drowsiness detection.
35 citations
"Drowsy Driver Alerting System" refers background in this paper
...These modules make use of several well-known image processing algorithms and tools to detect the face of the driver, extract the eye location of the driver and then make a decision about the driver’s drowsiness based on the complexity of the eyes [2]....
[...]