Driver Face Recognition and Sober Drunk Classification using Thermal Images

Menon, Sooraj; Swathi, J. N.; Anit, S K; Nair, Anu P; Sarath, S

doi:10.1109/iccsp.2019.8697908

Cited by 18 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A webcam has been used to record the video of the driver. The webcam is arranged in such a way that it captures the front facial image of the driver [8]. Once the video capturing is done, the recorded frames are then pulled out to get the 2-Dimensional images [9].…”

Section: Proposed Approachmentioning

confidence: 99%

Driver Drowsiness Detection and Monitoring System using Machine Learning

Chinthalachervu¹,

Teja²,

Kumar³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In the present world, lots of road accidents take place due to the lack of attention and alertness of driver. This is termed as driver drowsiness. This leads to a lot of unfortunate situations causing adverse damage to human lives. The main goal of this research is the detection of driver drowsiness and an appropriate response to the detection. There are many methods which are based on the motion of the vehicle or based on the driver’s behavior. One of the methods is the physiological method which helps in distracting the driver from drowsiness and making him alert. And few methods require expensive sensors and deals with a lot of data. Therefore, this paper develops a system for detecting drowsiness in real time with proper procedure and accuracy which is acceptable. In this system, the driver’s facial expressions are captured and recorded using a webcam. Every movement in each frame is detected using few techniques of image processing. The Eye Aspect Ratio, Mouth Opening Ratio, and Nose Length Ratio are calculated using the landmark points on the face. The calculated values are compared to the threshold values developed by the system and the difference in value leads to the detection. At the same time, the machine learning algorithms are also implemented in offline manner. Based on the classification, the system has successfully achieved 95.58% of sensitivity and 100% of specificity using Support Vector Machine. This model system is compatible with all kinds of vehicles.

show abstract

Section: Proposed Approachmentioning

confidence: 99%

Driver Drowsiness Detection and Monitoring System using Machine Learning

Chinthalachervu¹,

Teja²,

Kumar³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Recognizing whether drivers are DUI of alcohol can also be achieved using a camera that acquires IR images [ 242 , 243 , 244 ]. For an intoxicated person, vessels on the forehead become more active so that, in an IR image, the intensities of the pixels in this region are affected accordingly.…”

Section: State 5: Under the Influencementioning

confidence: 99%

“…For an intoxicated person, vessels on the forehead become more active so that, in an IR image, the intensities of the pixels in this region are affected accordingly. Menon et al [ 244 ] developed a system that uses IR images of the driver’s face in order to classify him/her as sober or drunk. The system successively (1) locates the face using a CNN, and (2) performs the binary classification based on differences in blood temperatures at 22 points on the face of the driver using a supervised-learning-classification algorithm based on a probabilistic model called Gaussian-mixture model.…”

Section: State 5: Under the Influencementioning

confidence: 99%

“…The above information allows one to fill the relevant cells of Table 5. Breathing Activity [77,206] Brain Activity Electrodermal Activity [208][209][210] Body Temperature [242][243][244] Pupil Diameter [139,228] Behavioral Gaze Parameters [116,123,140,144,145,166,167,170,171] Blink Dynamics [104,112,114,[116][117][118]123] PERCLOS [113,116,123] Facial Expressions [123,[203][204][205] Body Posture [115] [114,116-118,123] Hands Parameters [159][160][161][162][163] Speech [190,[211][212][213] Subjective Vehicle Wheel Steering [119,120,245,<...>…”

Section: Sensorsmentioning

confidence: 99%

See 1 more Smart Citation

Survey and Synthesis of State of the Art in Driver Monitoring

Halin

Verly

Droogenbroeck

2021

Sensors

View full text Add to dashboard Cite

Road vehicle accidents are mostly due to human errors, and many such accidents could be avoided by continuously monitoring the driver. Driver monitoring (DM) is a topic of growing interest in the automotive industry, and it will remain relevant for all vehicles that are not fully autonomous, and thus for decades for the average vehicle owner. The present paper focuses on the first step of DM, which consists of characterizing the state of the driver. Since DM will be increasingly linked to driving automation (DA), this paper presents a clear view of the role of DM at each of the six SAE levels of DA. This paper surveys the state of the art of DM, and then synthesizes it, providing a unique, structured, polychotomous view of the many characterization techniques of DM. Informed by the survey, the paper characterizes the driver state along the five main dimensions—called here “(sub)states”—of drowsiness, mental workload, distraction, emotions, and under the influence. The polychotomous view of DM is presented through a pair of interlocked tables that relate these states to their indicators (e.g., the eye-blink rate) and the sensors that can access each of these indicators (e.g., a camera). The tables factor in not only the effects linked directly to the driver, but also those linked to the (driven) vehicle and the (driving) environment. They show, at a glance, to concerned researchers, equipment providers, and vehicle manufacturers (1) most of the options they have to implement various forms of advanced DM systems, and (2) fruitful areas for further research and innovation.

show abstract

“…For an intoxicated person, vessels on the forehead become more active so that, in an IR image, the intensities of the pixels in this region are affected accordingly. Menon et al (143) developed a system that uses IR images of the driver's face in order to classify him/her as sober or drunk. The system successively (1) locates the face using a CNN, and (2) performs the binary classification based on differences in blood temperatures at 22 points on the face of the driver using a supervised-learning-classification algorithm based on a probabilistic model called Gaussian-mixture model.…”

Section: Sensorsmentioning

confidence: 99%

Survey and synthesis of state of the art in driver monitoring

Halin,

Verly,

Van Droogenbroeck

2021

Preprint

View full text Add to dashboard Cite

Road-vehicle accidents are mostly due to human errors, and many such accidents could be avoided by continuously monitoring the driver. Driver monitoring (DM) is a topic of growing interest in the automotive industry, and it will remain relevant for all vehicles that are not fully autonomous, and thus for decades for the average vehicle owner. The present paper focuses on the first step of DM, which consists in characterizing the state of the driver. Since DM will be increasingly linked to driving automation (DA), this paper presents a clear view of the role of DM at each of the six SAE levels of DA. This paper surveys the state of the art of DM, and then synthesizes it, providing a unique, structured, polychotomous view of the many characterization techniques of DM. Informed by the survey, the paper characterizes the driver state along the five main dimensions-called here "(sub)states"-of drowsiness, mental workload, distraction, emotions, and under the influence. The polychotomous view of DM is presented through a pair of interlocked tables that relate these states to their indicators (e.g., the eye-blink rate) and the sensors that can access each of these indicators (e.g., a camera). The tables factor in not only the effects linked directly to the driver, but also those linked to the (driven) vehicle and the (driving) environment. They show, at a glance, to concerned researchers, equipment providers, and vehicle manufacturers (1) most of the options they have to implement various forms of advanced DM systems, and (2) fruitful areas for further research and innovation.

show abstract

Driver Face Recognition and Sober Drunk Classification using Thermal Images

Cited by 18 publications

References 8 publications

Driver Drowsiness Detection and Monitoring System using Machine Learning

Driver Drowsiness Detection and Monitoring System using Machine Learning

Survey and Synthesis of State of the Art in Driver Monitoring

Survey and synthesis of state of the art in driver monitoring

Contact Info

Product

Resources

About