Smart driver assistance system using raspberry pi and sensor networks

Driver fatigue and drowsiness is an ever-rising issue that could place a lot of entities at risk. The associated problems are not only dangerous for the driver and the passenger but they pose a negative image on an industry that functions using drivers that work long hours in tough road conditions. In this work, proposed to develop a driver drowsiness detector based on image processing. The system created will work based on vehicle details received from the OBD-II and the camera mounted on the dashboard to monitor the driver. The system is developed with the aim to provide a novel solution to driver drowsiness detection on-board whilst the car is being driven. The mechanism provided is both non-intrusive and involves the use of machine learning that will provide an accurate result that averts the major cause of road-based accidents.

Smart driver monitoring system

An embedded intelligence engine for driver drowsiness detection

This chapter provides a contemporary solution to driver drowsiness and fatigue detection on-board whilst the driver is driving the car. The mechanism provided is both non-intrusive relatively and involves the use of artificial intelligence networks. This would aid in providing accurate and desired results thereby avoiding damage generally caused due to negligence and imposters in vulnerable industries that involve massive manpower and inventory. The system created will work based on vehicle details received from the OBD-II and the camera mounted on the dashboard to monitor the driver. As the driver enters the car, he initiates the authentication process when he turns the ignition knob or presses the start stop button in an attempt to start the car, and the on-board camera is turned on. Such efficient management could save the responsible company damages caused and the subsequent dent in their capital.

Smart Driver Monitoring System Using AI

/pdf/silat-the-curriculum-of-seni-silat-malaysia-19lqxmdj0o.pdf

Silat: The curriculum of Seni Silat Malaysia

Driver’s drowsiness is one of the leading contributing factors to the increasing accidents statistics in Malaysia. Therefore, the design and development of driver drowsiness detection based on image processing using Raspberry Pi camera module sensor interfacing with Raspberry Pi 3 board are proposed in this paper. To achieve the aim of the research, the Haar Cascade Classifier algorithm is implemented for eyes and face detection whereas for eyes blink (open and close) detection, the Eye Aspect Ratio (EAR) algorithm is employed. From several experiments conducted on six recruited subjects, the findings revealed that the accuracy of Haar Cascade classifier to detect the eyes and faces was subjected to correct sitting position (head must facing to the camera) as well as the eyes must not be covered with glasses or shades. Meanwhile, the range of average EAR value detected by the system was between 0.141 (eyes closed) and 0.339 (eyes opened). In conclusion, the image processing-based Haar Cascade and EAR algorithms utilized on Raspberry Pi platform have been successfully executed. For future improvement, the current board can be replaced with Raspberry Pi Touch Screen to minimize the hardware setup and the physiological based analysis using alcohol and heart rate sensors can be added.

/pdf/implementation-of-haar-cascade-classifier-and-eye-aspect-525085gay9.pdf

Implementation of Haar Cascade Classifier and Eye Aspect Ratio for Driver Drowsiness Detection Using Raspberry Pi

In this paper, a wearable front kicking angle monitoring device using flex sensor and Internet of Things (IoT) platform has been successfully developed and tested. The Arduino NodeMCU microcontroller processes and converts the input received from the flex sensor and transmits the real time front kicking angle and corresponding resistance data to the two main outputs; the ThingSpeak IoT platform and the LCD display for real monitoring. Thirty participants were recruited from two different backgrounds; silat athletes (n=20) and non-athlete participants (n=10). The participants were distributed into six weight categories: 50-55 kg, 55-60 kg, 60-65 kg, 65-70 kg, 70-75 kg and 75-80 kg. Based on the average angle measured from three trials, it can be observed that different participants had different averages and standard deviations for front kicking angle independently of weight category. Moreover, the background factor of the subjects involved did not greatly contribute in this research, as the participants from non-athlete background had the highest mean of front kicking angle (73.89 ± 17.41°). This situation is probably due to a lack of standard kicking styles set for all participants at the beginning of the experiment. Nonetheless, one conclusive remark that can be derived from the findings is the front kicking angle of an individual is greatly influenced by body weight, since the (75-80 kg) weight category achieved the lowest mean angle of front kicking for both backgrounds; non-athlete (14.00± 1.33°) and athlete (23.89± 6.44°) subjects. In the future, additional sensors such as accelerometer can be used to predict the stability of the body for better evaluation of front kicking angle.

http://www.mohejournal.com/index.php/mohe/article/download/MoHE%20Vol%209%281%29_14%20ID397/157

Ng Chun Keat

Papers

Implementation of Haar Cascade Classifier and Eye Aspect Ratio for Driver Drowsiness Detection Using Raspberry Pi

Development of wearable IoT-based front kicking's angle monitoring device