Application of Face Recognition Based on CNN in Fatigue Driving Detection

Xing, Jianju; Fang, Guoxin; Zhong, Juping; Li, Jun

doi:10.1145/3358331.3358387

Cited by 14 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN took the lead in a large number of successful applications in the fields of image recognition and speech processing [69,70]. Xing et al [23] built a CNN model for fatigue driving recognition to automatically extract features from drivers' facial images and identify fatigue state, with an accuracy rate of 87.5%. Jabbar et al [71] built the CNN model to automatically extract the depth features of the driver's face in the two states of wearing glasses or not to identify the fatigue state of the driver, with a recognition accuracy of 88% and 85%, respectively.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…Meanwhile, it can be organically integrated with the classifier to realize end-to-end data learning and significantly improve the recognition accuracy. Some researchers try to adopt deep neural network (DNN) [20,21], convolutional neural network (CNN) [22][23][24][25][26][27][28][29], and recurrent neural network (RNN) [30][31][32][33][34][35][36][37] to construct a driving behavior recognition model, which has achieved good results. In recent years, with the widespread application of on-board sensors and CAN bus technology in cars, driving behavior data in the natural driving process have been collected and stored, which provides massive data samples for the construction of deep learning model, and the recognition methods of driving behavior are gradually evolving to deep learning model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Review for the Driving Behavior Recognition Methods Based on Vehicle Multisensor Information

Zhao

Zhong

Zhi-jun

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

The frequent traffic accidents lead to a large number of casualties and large related financial losses every year; this serious state is owed to several factors; among those, driving behavior is one of the most imperative subjects to discuss. Driving behaviors mainly include behavior characteristics such as car-following, lane change, and risky driving behavior such as distraction, fatigue, or aggressive driving, which are of great help to various tasks in traffic engineering. An accurate and reliable method of driving behavior recognition is of great significance and guidance for vehicle driving safety. In this paper, the vehicle multisensor information, vehicle CAN bus data acquisition system, and typical feature extraction methods are summarized at first. And then, several driving behavior recognition models based on machine learning and deep learning are reviewed. Through a detailed analysis of the features of random forests, support vector machines, convolutional neural networks, and recurrent neural networks used to build driving behavior recognition models, the following findings are obtained: the driving behavior model constructed by traditional machine learning model is relatively mature but it is greatly affected by feature extraction, data scale, and model structure, which affects the accuracy of the final driving behavior recognition. Deep learning model based on a neural network has achieved high accuracy in identifying driving behavior, and it may gradually become the mainstream of constructing the driving behavior model with the development of big data, artificial intelligence technology, and computer hardware. Finally, this paper points out some content that needs to be further explored, to provide reference and inspiration for scholars in this field to continue to study the driving behavior recognition model in depth.

show abstract

Section: Convolutional Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Review for the Driving Behavior Recognition Methods Based on Vehicle Multisensor Information

Zhao

Zhong

Zhi-jun

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Network (CNN), which is a mult ilayered feed-forward artificial neural network, is one of the most frequently used methods in image processing [17]. CNN, which has an important place in the field of deep learning, also shows success in various applications such as face recognition [18], object classification [19], speech detection [20], and sign language recognition [21,22]. The most preferred CNN for dealing with computer vision problems is architecturally formed by adding convolution, pooling (sampling), and fully connected layers to the basic layers [23,24].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Motion Control of the Robot Arm Manufactured with a Three-Dimensional Printer and Hardness Detection of Objects

Aksoy

Özsoy

YÜCEL>

et al. 2022

Bilişim Teknolojileri Dergisi

View full text Add to dashboard Cite

Çalışmada 3D baskı teknolojilerinden Fused Deposition Modeling (FDM) yazıcı kullanılarak robotik kol üretilmiştir. Üretilen robot kolun görüntü işleme teknikleri ve makine öğrenme algoritmaları kullanarak dokunsal algılama ve hareket planlaması araştırılmıştır. Bu çalışmanın amacı, robotik kolun kontrolsüz kuvvet uygulamasını engellemek ve dokunsal kavrama sorunlarını çözmek için görüntü işleme teknikleri ve derin öğrenme algoritmaları kullanılarak yenilikçi yaklaşımların araştırılması ve uygulanmasıdır. Bu çalışmada, CAD programı ile tasarımı gerçekleştirilmiş parçaların FDM tipi üç boyutlu yazıcı kullanılarak katı modelleri alınmış ve montaj için uygun hale getirilmiştir. Montajı tamamlanan robotik elin kontrol sistemi ise temel olarak Raspberry Pi kontrol kartı, servo motorlar, basınç sesörleri ve kameradan oluşmaktadır. Robotik kola ait her parmak ucuna yerleştirilen basınç sensörleri ile ürünün sertliği ölçülerek dokunsal algılama işlemi gerçekleştirilmiştir. Raspberrry pi kontrol kartı kullanılarak sensörlerden alınan veriler işlenmekte ve servo motorlara uygun hareket ve kavrama basınç bilgisi gönderilmektedir. Kamera kullanılarak elde edilen insan elinin olası hareketleri ile robotik kol için referans bir veri seti hazırlanmıştır. Veri setine ait görüntüler üzerinde Gaussian filtreleme yöntemi kullanılarak görüntü işleme sağlanmıştır. Bununla birlikte veri seti üzerinde makine öğrenme algoritmaları kullanarak robotik kolun hareket açısal konumu optimize edilmiş ve HitNet, CNN, Kapsül Ağları ve Naive Bayes derin öğrenme modelleri kullanılarak robot kolun hareket planlanması %90 doğruluk oranı ile sınıflandırılmıştır. Performans değerlendirme kriterlerine göre başarıları kıyaslanan derin öğrenme modelleri arasında, robotik kolun hareket planlaması için; HitNET algoritması ile 97.23%, CNN ile 97.48%, Capsnet algoritması ile %98,58 ve Naive Bayes modeli ile %98.61 doğruluk oranı elde edilmiştir. Performans değerlendirme kriterleri sonucunda; Naive Bayes modelinin %98.61 doğruluk, %98.63 özgüllük, %98.65 duyarlılık, 1.39 hata oranı ve %68.64 F-ölçüsü değeri ile diğer modellere göre daha başarılı sonuç verdiği gözlemlenmiştir.

show abstract

“…Liu [ 6 ] presented a fatigue detection algorithm based on facial expression analysis. Xing [ 7 ] applied a convolutional neural network to face recognition, implementing a straightforward eye state judgment method using the PERCLOS algorithm to determine a driver’s fatigue state, with experimental results demonstrating an 87.5% fatigue recognition rate. Moujahid [ 8 ] introduced a face monitoring system based on compact facial texture descriptors, capable of encompassing the most discriminative drowsy features.…”

Section: Introductionmentioning

confidence: 99%

Remote Photoplethysmography and Motion Tracking Convolutional Neural Network with Bidirectional Long Short-Term Memory: Non-Invasive Fatigue Detection Method Based on Multi-Modal Fusion

Kong,

Xie,

Niu

et al. 2024

Sensors

View full text Add to dashboard Cite

Existing vision-based fatigue detection methods commonly utilize RGB cameras to extract facial and physiological features for monitoring driver fatigue. These features often include single indicators such as eyelid movement, yawning frequency, and heart rate. However, the accuracy of RGB cameras can be affected by factors like varying lighting conditions and motion. To address these challenges, we propose a non-invasive method for multi-modal fusion fatigue detection called RPPMT-CNN-BiLSTM. This method incorporates a feature extraction enhancement module based on the improved Pan–Tompkins algorithm and 1D-MTCNN. This enhances the accuracy of heart rate signal extraction and eyelid features. Furthermore, we use one-dimensional neural networks to construct two models based on heart rate and PERCLOS values, forming a fatigue detection model. To enhance the robustness and accuracy of fatigue detection, the trained model data results are input into the BiLSTM network. This generates a time-fitting relationship between the data extracted from the CNN, allowing for effective dynamic modeling and achieving multi-modal fusion fatigue detection. Numerous experiments validate the effectiveness of the proposed method, achieving an accuracy of 98.2% on the self-made MDAD (Multi-Modal Driver Alertness Dataset). This underscores the feasibility of the algorithm. In comparison with traditional methods, our approach demonstrates higher accuracy and positively contributes to maintaining traffic safety, thereby advancing the field of smart transportation.

show abstract

Application of Face Recognition Based on CNN in Fatigue Driving Detection

Cited by 14 publications

References 3 publications

A Review for the Driving Behavior Recognition Methods Based on Vehicle Multisensor Information

A Review for the Driving Behavior Recognition Methods Based on Vehicle Multisensor Information

Motion Control of the Robot Arm Manufactured with a Three-Dimensional Printer and Hardness Detection of Objects

Remote Photoplethysmography and Motion Tracking Convolutional Neural Network with Bidirectional Long Short-Term Memory: Non-Invasive Fatigue Detection Method Based on Multi-Modal Fusion

Contact Info

Product

Resources

About