scholarly journals Convolutional Two-Stream Network Using Multi-Facial Feature Fusion for Driver Fatigue Detection

2019 ◽  
Vol 11 (5) ◽  
pp. 115 ◽  
Author(s):  
Weihuang Liu ◽  
Jinhao Qian ◽  
Zengwei Yao ◽  
Xintao Jiao ◽  
Jiahui Pan
Keyword(s):  
Traffic Accidents ◽  
Road Traffic ◽  
Feature Fusion ◽  
Facial Feature ◽  
Detection Algorithm ◽  
Facial Features ◽  
Dynamic Features ◽  
Driver Fatigue ◽  
Stream Network ◽  
Fatigue Detection

Road traffic accidents caused by fatigue driving are common causes of human casualties. In this paper, we present a driver fatigue detection algorithm using two-stream network models with multi-facial features. The algorithm consists of four parts: (1) Positioning mouth and eye with multi-task cascaded convolutional neural networks (MTCNNs). (2) Extracting the static features from a partial facial image. (3) Extracting the dynamic features from a partial facial optical flow. (4) Combining both static and dynamic features using a two-stream neural network to make the classification. The main contribution of this paper is the combination of a two-stream network and multi-facial features for driver fatigue detection. Two-stream networks can combine static and dynamic image information, while partial facial images as network inputs can focus on fatigue-related information, which brings better performance. Moreover, we applied gamma correction to enhance image contrast, which can help our method achieve better results, noted by an increased accuracy of 2% in night environments. Finally, an accuracy of 97.06% was achieved on the National Tsing Hua University Driver Drowsiness Detection (NTHU-DDD) dataset.

Driver Fatigue Detection Based On Facial Feature Analysis

2021 ◽  
pp. 2150034
Author(s):  
Yimin Zhang ◽  
Xianwei Han ◽  
Wei Gao ◽  
Yunliang Hu
Keyword(s):  
Traffic Accidents ◽  
Detection System ◽  
Recognition Rate ◽  
Ccd Camera ◽  
Facial Feature ◽  
The State ◽  
Driver Fatigue ◽  
Eyelid Closure ◽  
Fatigue Driving ◽  
Fatigue Detection

Fatigue driving is one of the main causes of traffic accidents. In recent years, considerable attention has been paid to fatigue detection systems, which is an important solution for preventing fatigue driving. In order to prevent and reduce fatigue driving, a driver fatigue detection system based on computer vision is proposed. In this system, an improved face detection method is used to detect the driver’s face from the image obtained by a charge coupled device (CCD) camera. Then, the feature points of the eyes and mouth are located by an ensemble of regression trees. Next, fatigue characteristic parameters are calculated by the improved percentage of eyelid closure over the pupil over time algorithm. Finally, the state of drivers is evaluated by using a fuzzy neural network. The system can effectively monitor and remind the state of drivers so as to significantly avoid or decrease the occurrence of traffic accidents. The experimental results show that the system is of wonderful real-time performance and accurate recognition rate, so it meets the requirements of practicality in driver fatigue detection greatly.

MULTISCALE DYNAMIC FEATURES BASED DRIVER FATIGUE DETECTION

2009 ◽  
Vol 23 (03) ◽  
pp. 575-589 ◽  
Author(s):  
BAO-CAI YIN ◽  
XIAO FAN ◽  
YAN-FENG SUN
Keyword(s):  
Traffic Accidents ◽  
Learning Algorithm ◽  
Real Life ◽  
Local Binary Patterns ◽  
Image Sequences ◽  
Dynamic Features ◽  
Driver Fatigue ◽  
Novel Approach ◽  
Temporal Aspect ◽  
Fatigue Detection

Driver fatigue is a significant factor in many traffic accidents. We propose a novel approach for driver fatigue detection from facial image sequences, which is based on multiscale dynamic features. First, Gabor filters are used to get a multiscale representation for image sequences. Then Local Binary Patterns are extracted from each multiscale image. To account for the temporal aspect of human fatigue, the LBP image sequence is divided into dynamic units, and a histogram of each dynamic unit is computed and concatenated as dynamic features. Finally a statistical learning algorithm is applied to extract the most discriminative features from the multiscale dynamic features and construct a strong classifier for fatigue detection. The proposed approach is validated under real-life fatigue conditions. The test data includes 600 image sequences with illumination and pose variations from 30 people's videos. Experimental results show the validity of the proposed approach, and a correct rate of 98.33% is achieved which is much better than the baselines.

Head motion coefficient-based algorithm for distracted driving detection

2019 ◽  
Vol 53 (2) ◽  
pp. 171-188 ◽  
Author(s):  
Kwok Tai Chui ◽  
Wadee Alhalabi ◽  
Ryan Wen Liu
Keyword(s):  
Traffic Accidents ◽  
Road Traffic ◽  
Video Stream ◽  
Detection Algorithm ◽  
Distracted Driving ◽  
Head Motion ◽  
Content Type ◽  
Cell Phone Use ◽  
The Road ◽  
Video Frames

PurposeConcentration is the key to safer driving. Ideally, drivers should focus mainly on front views and side mirrors. Typical distractions are eating, drinking, cell phone use, using and searching things in car as well as looking at something outside the car. In this paper, distracted driving detection algorithm is targeting on nine scenarios nodding, head shaking, moving the head 45° to upper left and back to position, moving the head 45° to lower left and back to position, moving the head 45° to upper right and back to position, moving the head 45° to lower right and back to position, moving the head upward and back to position, head dropping down and blinking as fundamental elements for distracted events. The purpose of this paper is preliminary study these scenarios for the ideal distraction detection, the exact type of distraction.Design/methodology/approachThe system consists of distraction detection module that processes video stream and compute motion coefficient to reinforce identification of distraction conditions of drivers. Motion coefficient of the video frames is computed which follows by the spike detection via statistical filtering.FindingsThe accuracy of head motion analyzer is given as 98.6 percent. With such satisfactory result, it is concluded that the distraction detection using light computation power algorithm is an appropriate direction and further work could be devoted on more scenarios as well as background light intensity and resolution of video frames.Originality/valueThe system aimed at detecting the distraction of the public transport driver. By providing instant response and timely warning, it can lower the road traffic accidents and casualties due to poor physical conditions. A low latency and lightweight head motion detector has been developed for online driver awareness monitoring.

scholarly journals Overview of approaches to driver fatigue recognition and existing technical solutions

2020 ◽  
Vol 1 (3) ◽  
pp. 48-58
Author(s):  
Ya.D. Saprykin ◽  
◽  
V.I. Ryazantsev ◽  
A.A. Smirnov ◽  
◽  
...  
Keyword(s):  
Traffic Accidents ◽  
Road Traffic ◽  
Physiological State ◽  
Steering Wheel ◽  
Driver Fatigue ◽  
The Road ◽  
Advantages And Disadvantages ◽  
Falling Asleep ◽  
On The Road ◽  
Technical Solutions

The article analyzes the existing methods for determining the driver's condition. Driving in a state of fatigue, according to various statistics, is the cause of a large number of road traffic accidents (RTA). The percentage of accidents in Russia associated with the driver falling asleep while driving in 2018 is about 20%, in the USA the number of accidents for the same reason reaches 100,000 per year. The aim of the work is to review existing approaches to recognizing driver fatigue and existing technical solutions in this area. The article discusses such approaches as fatigue recognition based on the physiological state of the driver, recognition based on the driver's behavior, namely his speech and visual signs while driving, fatigue determination based on the nature of the vehicle's movement on the road and based on the driver's actions on the controls, the approaches based on the subjective assessment of the driver's condition. The advantages and disadvantages of each of the approaches were analyzed. The paper also provides an overview of existing fatigue recognition systems from various manufacturers that are currently used on vehicles and are designed to warn the driver of impending fatigue. It was revealed that in modern conditions of road transport operation, the most optimal approaches to fatigue recognition are based on an assessment of the driver's impact on the steering wheel, visual signs of driver fatigue and the nature of the vehicle's movement on the road, therefore, it is proposed to further focus on these methods.

scholarly journals Near-Infrared Road-Marking Detection Based on a Modified Faster Regional Convolutional Neural Network

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Junping Hu ◽  
Shitu Abubakar ◽  
Shengjun Liu ◽  
Xiaobiao Dai ◽  
Gen Yang ◽  
...  
Keyword(s):  
Traffic Accidents ◽  
Near Infrared ◽  
Feature Fusion ◽  
Autonomous Driving ◽  
Detection Algorithm ◽  
Vital Role ◽  
Image Features ◽  
Fusion Technique ◽  
Detection Model ◽  
Road Marking

Pedestrians, motorist, and cyclist remain the victims of poor vision and negligence of human drivers, especially in the night. Millions of people die or sustain physical injury yearly as a result of traffic accidents. Detection and recognition of road markings play a vital role in many applications such as traffic surveillance and autonomous driving. In this study, we have trained a nighttime road-marking detection model using NIR camera images. We have modified the VGG-16 base network of the state-of-the-art faster R-CNN algorithm by using a multilayer feature fusion technique. We have demonstrated another promising feature fusion technique of concatenating all the convolutional layers within a stage to extract image features. The modification boosts the overall detection performance of the model by utilizing the advantages of the shallow layers and the deep layers of the VGG-16 network. The training samples were augmented using random rotation and translation to enhance the heterogeneity of the detection algorithm. We have achieved a mean average precision (mAP) of 89.48% and 92.83% for the baseline faster R-CNN and our modified method, respectively.

scholarly journals A Low-Cost Prototype for Driver Fatigue Detection

2019 ◽  
Vol 3 (1) ◽  
pp. 5
Author(s):  
Tiago Meireles ◽  
Fábio Dantas
Keyword(s):  
Traffic Accidents ◽  
Low Cost ◽  
Infrared Camera ◽  
Physiological Parameters ◽  
Physical Parameters ◽  
Total System ◽  
Driver Fatigue ◽  
Privacy Concerns ◽  
Detection Systems ◽  
Fatigue Detection

Driver fatigue and inattention accounts for up to 20% of all traffic accidents, therefore any system that can warn the driver whenever fatigue occurs proves to be useful. Several systems have been devised to detect driver fatigue symptoms, such as measuring physiological parameters, which can be uncomfortable, or using a video or infrared camera pointed at the driver’s face, which in some cases, may cause privacy concerns for the driver. Usually these systems are expensive, therefore a brief discussion on low-cost fatigue detection systems is presented, followed by a proposal for a non-intrusive low-cost prototype, that aims to detect driver fatigue symptoms. The prototype consists of several sensors that monitor driver physical parameters and vehicle behaviour, with a total system price close to 30 euros. The prototype is discussed and compared with similar systems, pointing out its strengths and weaknesses.

Driver Fatigue Detection Algorithm Research Based on the Characteristics of Eyes

2014 ◽  
Vol 701-702 ◽  
pp. 30-35 ◽  
Author(s):  
Qin Wang ◽  
Lan Tang ◽  
Kun Yang
Keyword(s):  
Warning System ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Driver Fatigue ◽  
Infrared Video ◽  
The Face ◽  
Eyes Open ◽  
Texture Detection ◽  
Opening And Closing ◽  
Fatigue Detection

In driver fatigue warning system, it is a very effective method for detecting Driver fatigue state through the driver's facial expressions and body movements. The main content of this article is to detect the two basic states of the eyes opening and closing and presents the LBP texture detection operator. Firstly we get the face image sequences using infrared video and extract the eye region using ADABOOST. The SVM is used in classifying feature vector of the eyes open and closed detecting of driver fatigue. A large number of experimental results show that the proposed method has high detection accuracy and timeliness.

Sign in / Sign up

Export Citation Format

Share Document