Real-time intelligent alarm system of driver fatigue based on video sequences

Rezaee, Khosro; Alavi, Shahryar; Madanian, Maede; Ghezelbash, Mohammad Rasegh; Khavari, Hassan; Haddadnia, Javad

doi:10.1109/icrom.2013.6510137

Cited by 18 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several eye-based systems have been proposed in the literature which use the percent of closeness (PERCLOSE) and average eye closure speed (AECS) measures for different decisions, such as drowsiness detection where PER-CLOSE increases [8,10,28,30,21,9,26,7,5] and AECS decreases [12,3,4], for a drowsy driver. Existing eye-based approaches mostly use eye and face detectors, such as Viola Jones algorithm [33], and detect the eye state using classical computer vision techniques.…”

Section: Related Workmentioning

confidence: 99%

Weakly-Supervised Degree of Eye-Closeness Estimation

Mequanint

Zhang

Forutanpour

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Following recent technological advances there is a growing interest in building non-intrusive methods that help us communicate with computing devices. In this regard, accurate information from eye is a promising input medium between a user and computing devices. In this paper we propose a method that captures the degree of eye closeness. Although many methods exist for detection of eyelid openness, they are inherently unable to satisfactorily perform in real world applications. Detailed eye state estimation is more important, in extracting meaningful information, than estimating whether eyes are open or closed. However, learning reliable eye state estimator requires accurate annotations which is cost prohibitive. In this work, we leverage synthetic face images which can be generated via computer graphics rendering techniques and automatically annotated with different levels of eye openness. These synthesized training data images, however, have a domain shift from real-world data. To alleviate this issue, we propose a weakly-supervised method which utilizes the accurate annotation from the synthetic data set, to learn accurate degree of eye openness, and the weakly labeled (open or closed) real world eye data set to control the domain shift. We introduce a data set of 1.3M synthetic face images with detail eye openness and eye gaze information, and 21k real-world images with open/closed annotation. The dataset will be released online upon acceptance. Extensive experiments validate the effectiveness of the proposed approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Weakly-Supervised Degree of Eye-Closeness Estimation

Mequanint

Zhang

Forutanpour

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

show abstract

“…The face expressions will be separated, and the eye-blink intervals will be thresholded using K-means clustering. The research gives accuracy results with an average accuracy of 93,18% and the detection rate of 92,71% from 35000 image frames [5]. [6] has used EEG to determine the fatigue driver state using the comparisons between the left prefrontal attention and meditation from EEG with 18 participants (12 males and six females) in noninvasive real-time.…”

Section: Introductionmentioning

confidence: 99%

Real Time Fatigue-Driver Detection from Electroencephalography Using Emotiv EPOC+

Sarno

Nugraha

Munawar

2016

IRECOS

View full text Add to dashboard Cite

The fatigue driving detection has been developed with many kinds of approaches, such as video using face expressions and Electroencephalography (EEG) that uses the brainwave signals of the driver. This paper proposes a method to implement the driving fatigue detection in real time using Python and Emotiv EPOC+ with 14 channels. The EEG recorded database will extract their features per-30 seconds. The prediction process gets the EEG recorded data from the driver doing the driving simulation and trains it using the extracted features data from the database. The results print as Fit and Alert, or Fatigue and Sleepy. The contributions of the authors in this paper are as follows: i) the reduction of the processing time, such as reading input and output files and communicating among different programming languages; ii) the analysis and comparison of the dynamics of prediction results and significant channels from the results of the previous research, and iii) the development of the system from semi real-time to real-time forecasting.

show abstract

“…3 describes the MP classifier, comprising two modules, where the first module is an IT2FS neural net with outputs C 1 , C 2 , C 3 and C 4 . This neural net is realized with IT2FS neurons, the symbol and architecture of which are given but k C =0 for any [1,3]. k  This is given in Fig.…”

Section: B It2fs-based Classifier Designmentioning

confidence: 99%

“…Among the well-known brain signal acquisition techniques, electroencephalography (EEG) [1] is most popular for its prompt time-response [2], non-invasive characteristic [3], [4] portability and cost-effectiveness. Because of the above merits, the paper attempts to employ EEG-signal processing and classification to detect VA failure (VAF), MP failure (MPF) and ME failure (MEF).…”

mentioning

confidence: 99%