Using Haar classifiers to detect driver fatigue and provide alerts

Ibrahim, Lamiaa Fattouh; Abulkhair, Maysoon F.; Alshomrani, Amal D.; Al-Garni, Manal; Al-Mutiry, Ameerah; Al-Gamdi, Fadiah; Kalenen, Roa'a

doi:10.1007/s11042-012-1308-5

Cited by 22 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The changes in the head and face features are more obvious and most easily detected, thus the research hotspot at present also gathered in this part. The major methods of detection include PERCLOS, head position detection, gaze direction detection, blink frequency detection and mouth state detection [21][22][23].…”

Section: Driver Facial Features Based Detection Methodsmentioning

confidence: 99%

A Review on Fatigue Driving Detection

Shi

Wang

2017

ITM Web Conf.

View full text Add to dashboard Cite

Abstract:The socialization of automobile development has brought great convenience to people's travel. However, the rapid increase in the number of vehicles has also caused a series of problems. The increase in traffic accidents has brought great social casualties and economic losses. Fatigue driving, which is an important factor in the traffic accident, has aroused people's attention. This paper reviews all kinds of fatigue driving detection methods at present; compares various fatigue driving detection methods in terms of accuracy, real-time and cost; analyses the advantages and disadvantages of various methods; introduces the application of fatigue detection system in automobile; summarizes the current deficiencies and future development trends in the field of fatigue driving detection. The future research of this field will be more to the data fusion, computer vision and deep learning.

show abstract

Section: Driver Facial Features Based Detection Methodsmentioning

confidence: 99%

A Review on Fatigue Driving Detection

Shi

Wang

2017

ITM Web Conf.

View full text Add to dashboard Cite

show abstract

“…Pada penelitian sebelumnya, hasil deteksi kantuk dengan menggunakan EKG dengan analisa RR Interval (RRI) pada subjek, dengan hasil yang didapatkan memiliki nilai keberhasilan rata-rata penghitungan sebesar 87,5% [3]. Sedangkan, pada penelitian sistem peringatan dan deteksi lelah pada pengemudi menggunakan Haar classifiers menunjukkan persentase akurasi yang dihasilkan sebesar 89% [4].…”

Section: Pendahuluanunclassified

Sistem Pemantauan Kantuk Menggunakan Instrumentasi Elektrokardiografi dan Visual Haar Classifier pada Pengemudi

Sanjaya¹,

Setiawan²,

Hikmah³

2020

JTITS

View full text Add to dashboard Cite

Menurut data dari Polisi Lalu Lintas (Polantas) pada tahun 2013 menunjukkan bahwa selama periode tahun 2012 dan 2013 angka kecelakaan lalu lintas yang terjadi di Indonesia cenderung menurun, tetapi angka jumlah kecelakaan yang terjadi masih tergolong tinggi jika dibandingkan dengan negara lain. Data tersebut menunjukkan bahwa kantuk pada pengemudi merupakan penyebab kedua terbesar terjadinya kecelakaan lalu lintas. Oleh karena itu dibutuhkan sebuah sistem yang mampu mendeteksi kantuk. Keadaan kantuk dapat dideteksi dengan memonitor kondisi pengemudi dengan menggunakan dua metode pendekatan yaitu pengambilan sinyal biomedis dan menggunakan teknik visual. Salah satu metode pengambilan sinyal biomedis menggunakan elektrokardiograf (EKG) dan visual menggunakan kamera. EKG merupakan alat yang digunakan untuk merekam sinyal jantung. Perancangan instrumentasi EKG menggunakan surface electrode yang dipasang menggunakan metode segitiga eithoven. Instrumentasi EKG terdiri dari penguat instrumentasi yang menggunakan IC AD620 dan melewati filter low pass dengan frekuensi cutoff 0.05Hz dan filter high pass dengan cutoff 50Hz. Sinyal EKG akan dikirimkan melalui komunikasi serial ke miniPC. Berdasarkan data dapat diperoleh detak jantung dan rasio LF/HF. Penggunaan satu modalitas tidak cukup untuk menyatakan kondisi dari pengemudi, sehingga perlu ditambahkan metode visual haar classifier untuk mendeteksi kantuk. Perancangan metode visual menggunakan kamera untuk mengambil data frame. Data frame pertama video berupa height dari kelopak mata sebagai threshold. Threshold digunakan sebagai pembanding dengan height frame ke-n untuk mengklasifikasikan kondisi pengemudi sebagai parameter kedua. Penggabungan kedua parameter menggunakan metode if then rule. Melalui pengujian dengan lima subjek didapatkan bahwa sistem pemantauan kantuk menggunakan instrumentasi EKG dan visual haar classifier dapat mendeteksi kantuk satu dari lima subjek yang diuji.

show abstract

“…Driver Fatigue Detection System (called FDS) has been proposed by the author in a recent work [26]. The FDS aims to monitor the driver and the alertness to prevent them from falling asleep at the wheel.…”

Section: Design and Implementation Of The Systemmentioning

confidence: 99%

“…It is "the task of learning a target function (classification model) that maps each attribute set to one of the predefined class label". The classification model can serve as an explanatory tool to distinguish between object of different classes " [26]. Figure 1 illustrates the face detection procedure used in the WakeApp system.…”

Section: Face Detection Using Haar-like Classifier Cascadesmentioning

confidence: 99%

Using Mobile Platform to Detect and Alerts Driver Fatigue

Abulkhair¹,

Salman²,

Ibrahim³

2015

IJCA

View full text Add to dashboard Cite

When driver is in the state of drowsiness he can cause accidents. This state is the state between being awake and asleep. In this state driver reaction time is slower, his attentiveness is reduced, and his information processing is less efficient. Driver Fatigue Detection System (called FDS) has been proposed by the authors in a recent work. The FDS aims to monitor the driver and the alertness to prevent them from falling asleep at the wheel. FDS is very hard to fix in a car. In the present paper, the FDS software is modified and new system WakeApp is developed to be run in smartphone instead of Laptop and use all advantages of smartphone like camera and late weight. The WakeApp will solve this problem by using a mobile phone camera; the phone will be put on a stand in the car to make the driver feels comfortable. The WakeApp has hardware and software components such as mobile camera and Android SDK. Both components are integrated together to record real video for the driver, and then processing it for real-time eye tracking. WakeApp has reserve all advantages in FDS like fast and real-time face and eye tracking, external illumination interference is limited, more robustness and accuracy allowance for fast head/face movement. The Main goals of WakeApp are to ensure that the driver is staying awake during his drive, make the driver feels comfortable and to help decrease the number of accidents.

show abstract

Using Haar classifiers to detect driver fatigue and provide alerts

Cited by 22 publications

References 13 publications

A Review on Fatigue Driving Detection

A Review on Fatigue Driving Detection

Sistem Pemantauan Kantuk Menggunakan Instrumentasi Elektrokardiografi dan Visual Haar Classifier pada Pengemudi

Using Mobile Platform to Detect and Alerts Driver Fatigue

Contact Info

Product

Resources

About