IOT Based Real-Time Drowsy Driving Detection System for the Prevention of Road Accidents

Hossain, Md. Yousuf; George, Fabian Parsia

doi:10.1109/iciibms.2018.8550026

Cited by 36 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the literature study that has been conducted in 20 articles, it can be found out that the construction and development of behaviour-based automatic driver drowsiness detection have mostly been conducted using some of the methods such as Vander Lugt Correlator [5], Haar Cascade [6,12,17], Eye Aspect Ratio [11,12,18,22], and even machine learning methods [11] such as Support Vector Machine [11,13], Neural Networks [4,6,7,8,10,14,15,16,18,20,22]. Recurrent Neural Networks like Long Short Term Memory have also been used in some of the research [4,16,22].…”

Section: Resultsmentioning

confidence: 99%

Driver Drowsiness Detection Based on Drivers’ Physical Behaviours: A Systematic Literature Review

Caryn

Rahadianti

2021

ComEngApp

View full text Add to dashboard Cite

One of the most common causes of traffic accidents is human error. One such factor involves the drowsy drivers that do not focus on the road before them. Driver drowsiness often occurs due to fatigue in long distances or long durations of driving. The signs of a drowsy driver may be detected based on one out of three types of tests; i.e., performance test, physiological test, and behavioural test. Since the physiological and performance tests are quite difficult and expensive to implement, the behavioural test is a good choice to use for detecting early drowsiness. Behaviour-based driver drowsiness detection has been one of the hot research topics in recent years and is still increasingly developing. There are many approaches for behavioural driver drowsiness detection, such as Neural Networks, Multi Layer Perceptron, Support Vector Machine, Vander Lugt Correlator, Haar Cascade, and Eye Aspect Ratio. Therefore, this study aims to conduct a systematic literature review to elaborate on the development and research trends regarding driver drowsiness detection. We hope to provide a good overview of the current state of research and offer the research potential in the future.

show abstract

Section: Resultsmentioning

confidence: 99%

Driver Drowsiness Detection Based on Drivers’ Physical Behaviours: A Systematic Literature Review

Caryn

Rahadianti

2021

ComEngApp

View full text Add to dashboard Cite

show abstract

“…An automatic road accident detection and prevention system was proposed by Khalil et al, [9], the system is deployed in the individual car and only the simulation is tested. Driver fatigue and drowsy detection system is been designed and the system was able to detect only the driver drowsiness and it will not intimate about the approaching vehicle from a blind spot or curve [8]. Image processing based traffic control and accident detection system is designed [13] the processing in real time is slow and incurs high deployment cost.…”

Section: Existing Systemsmentioning

confidence: 99%

Accident Prevention and Traffic Pattern Analysis System for Hilly Regions

2019

IJITEE

View full text Add to dashboard Cite

In hilly regions, there will be a number of curves and hairpin bends. The roadway is one of the often-used modes of transport in these regions. Accident rate and death rate in hilly regions are increasing day by day. The roads in this region will definitely have bends and steep curves; hence, it is difficult to see the vehicles coming from the opposite side. The proposed system aims in reducing the risk of driving vehicle in the terrain region with hairpin bends and steep curves. The deployed controller with ultrasonic sensor senses the vehicle coming towards the bend and intimates it to the other side of the bend or curve; it gives three stages of LED alerts to the driver driving the vehicle from the opposite side of the hairpin bend or curve. It also senses the speed of the vehicle, if the vehicle speed is high, it will alert the drivers through the buzzer. These alerts will indirectly convey the drivers to slow down the speed of the vehicle. The foremost focus of the proposed system is to prevent accidents for the drivers and passengers in order to decrease the death rates in hilly regions. This system also provides a way for analyzing the number of uphill and downhill vehicles in the hill stations by storing the data in the cloud. The analyzed data is be viewed over the internet through a web application. The web application serves as a traffic pattern analyzer for people who wish to travel by that road.

show abstract

“…Image data-based methods acquire data by installing cameras inside the vehicle. To detect drowsy driving, information is generated by characteristics such as the percentage of eyelid closure (PERCLOS), eye movement, and face direction through an image processing method [11][12][13][14][15][16][17]. Since image data directly represents the behavior of the driver during drowsy driving, studies employing image data generally display excellent performance.…”

Section: Introductionmentioning

confidence: 99%

Ensemble CNN to Detect Drowsy Driving with In-Vehicle Sensor Data

Jeon

Kim²,

Baek

2021

Sensors

View full text Add to dashboard Cite

Drowsy driving is a major threat to the safety of drivers and road traffic. Accurate and reliable drowsy driving detection technology can reduce accidents caused by drowsy driving. In this study, we present a new method to detect drowsy driving with vehicle sensor data obtained from the steering wheel and pedal pressure. From our empirical study, we categorized drowsy driving into long-duration drowsy driving and short-duration drowsy driving. Furthermore, we propose an ensemble network model composed of convolution neural networks that can detect each type of drowsy driving. Each subnetwork is specialized to detect long- or short-duration drowsy driving using a fusion of features, obtained through time series analysis. To efficiently train the proposed network, we propose an imbalanced data-handling method that adjusts the ratio of normal driving data and drowsy driving data in the dataset by partially removing normal driving data. A dataset comprising 198.3 h of in-vehicle sensor data was acquired through a driving simulation that includes a variety of road environments such as urban environments and highways. The performance of the proposed model was evaluated with a dataset. This study achieved the detection of drowsy driving with an accuracy of up to 94.2%.

show abstract

IOT Based Real-Time Drowsy Driving Detection System for the Prevention of Road Accidents

Cited by 36 publications

References 22 publications

Driver Drowsiness Detection Based on Drivers’ Physical Behaviours: A Systematic Literature Review

Driver Drowsiness Detection Based on Drivers’ Physical Behaviours: A Systematic Literature Review

Accident Prevention and Traffic Pattern Analysis System for Hilly Regions

Ensemble CNN to Detect Drowsy Driving with In-Vehicle Sensor Data

Contact Info

Product

Resources

About