A Low-Cost Vehicle Assistance System for Detection of Critical Driving Situations

Ahmed M.I., Alabdulkarem H., Alomair F., Aldossary D., Alahmari M., Alhumaidan M., Alrassan S., Rahman A., Youldash M., Zaman G.

Drowsy driving is a widespread cause of traffic accidents, especially on highways. It has become an essential task to seek an understanding of the situation in order to be able to take immediate remedial actions to detect driver drowsiness and enhance road safety. To address the issue of road safety, the proposed model offers a method for evaluating the level of driver fatigue based on changes in a driver’s eyeball movement using a convolutional neural network (CNN). Further, with the help of CNN and VGG16 models, facial sleepiness expressions were detected and classified into four categories (open, closed, yawning, and no yawning). Subsequently, a dataset of 2900 images of eye conditions associated with driver sleepiness was used to test the models, which include a different range of features such as gender, age, head position, and illumination. The results of the devolved models show a high degree of accountability, whereas the CNN model achieved an accuracy rate of 97%, a precision of 99%, and recall and F-score values of 99%. The VGG16 model reached an accuracy rate of 74%. This is a considerable contrast between the state-of-the-art methods in the literature for similar problems.

Zhang H., Ni D., Ding N., Sun Y., Zhang Q., Li X.

Fatigue is always accompany with the driving task, which have been extensively investigated for driver monitoring and traffic safety. While many scholars dedicate to the study of fatigue detection methods with higher accuracy, but the basic correlation between detection methods and fatigue cause or prevention receive relatively little attention. This study systematically reviews the authors’ studies of fatigue influential factors, fatigue identification and measurement, and fatigue prediction; and then structurally and comparably describes the research of driver fatigue behavior from the above three components within the literature of interest. Time-related indicators are usually considered as the main driver fatigue influential factors, and driving environment and vehicle performance are also found to be contributive to driver fatigue. The elastic control of driving time and rest time is an effective measure for the prevention of driver fatigue. Sensitivity analysis can test the correlation between measurements of fatigue identification and fatigue level, and then ensure the performance of measurements. Models that consider time-related factors based on bio-mathematic model theory can be used for real-time fatigue level prediction and characterizing the fatigue dynamics in the planned travel time. Driver individual differences should be considered for the fatigue behavior research as the performance of fatigue detection model and prediction models could vary greatly within drivers from different population. This review described the structure of driver fatigue behavior studies, and the link between fatigue influential indicators, fatigue identification, prediction. The effect of fatigue identification should be further explored, not just for detection or high accuracy.

El-Nabi S.A., El-Shafai W., El-Rabaie E.M., Ramadan K.F., Abd El-Samie F.E., Mohsen S.

There are several factors for vehicle accidents during driving such as drivers’ negligence, drowsiness, and fatigue. These accidents can be avoided, if drivers are warned in time. Moreover, recent developments in computer vision and artificial intelligence (AI) have helped to monitor drivers and alert them in case they are not concentrating on driving. The AI techniques can extract relevant features from expressions of driver’s face, such as eye closure, yawning, and head movements to infer the level of sleepiness. In addition, they can acquire biological signals from the driver’s body, and indications from the vehicle behavior. This paper provides a comprehensive review of the detection techniques of drowsiness and fatigue of drivers using machine learning (ML) and deep learning (DL). The current techniques for this application are classified into four categories: image- or video-based analysis during the driving, biological signal analysis for drivers, vehicle movement analysis, and hybrid techniques. A review of supervised techniques is presented for detecting fatigue and drowsiness on different datasets, with a comparison of the various techniques in terms of pros and cons. Results are presented in terms of accuracy of detection for each technique. The results are discussed according to the recent problems and challenges in this field. The paper also highlights the applicability and reliability of the different techniques. Furthermore, some suggestions are presented for the future work in the field of driver drowsiness detection (DDD).

Mishra A.

Abstract The Friction Stir Welding process usually produces weld members of good quality compared to composite weld made with a standard welding process. However, there is a possibility of the formation of various defects if the input parameters are not properly selected. In the recent case study, an image-based feature recognition system using the Fourier conversion method which is a computer visual recognition tool is developed. Five types of filters like Ideal Filter, Butterworth Filter, Low Filter, Gaussian Filter, and High Pass Filter. The results showed that the high pass filter has more ability to detect surface defects compared to the other four filters. It has also been observed that the Ideal filter has a lot of distortions compared to the Gaussian Filter and the Butterworth Filter.

Ferkova Z., Matula P.

While current landmark detection algorithms offer a good approximation of the landmark locations, they are often unsuitable for the use in biological research. We present multi-modal landmark detection approach, based on Point distribution model that detects a larger number of anthropologically relevant landmarks than the current landmark detection algorithms. At the same time we show that improving detection accuracy of initial vertices, using image information, to which the Point distribution model is fitted, increases both the overall accuracy and the stability of the detected landmarks.We show results on data from the public FIDENTIS Database, created for the anthropological research, and compare them to the state-of-the-art landmark detection algorithms that are based on statistical shape models.

Guede-Fernandez F., Fernandez-Chimeno M., Ramos-Castro J., Garcia-Gonzalez M.A.

Drowsy driving is a prevalent and serious public health issue that deserves attention. Recent studies estimate that around 20% of car crashes have been caused by drowsy drivers. Nowadays, one of the main goals in the development of new advanced driver assistance systems is trustworthy drowsiness detection. In this paper, a drowsiness detection method based on changes in the respiratory signal is proposed. The respiratory signal, which has been obtained using an inductive plethysmography belt, has been processed in real time in order to classify the driver's state of alertness as drowsy or awake. The proposed algorithm is based on the analysis of the respiratory rate variability (RRV) in order to detect the fight against to fall asleep. Moreover, a method to provide a quality level of the respiratory signal is also proposed. Both methods have been combined to reduce false alarms due to the changes of measured RRV associated not with drowsiness but body movements. A driving simulator cabin has been used to perform the validation tests and external observers have rated the drivers' state of alertness in order to evaluate the algorithm performance. It has been achieved a specificity of 96.6%, a sensitivity of 90.3%, and Cohen's Kappa agreement score of 0.75 on average across all subjects through a leave-one-subject-out cross-validation. A novel algorithm for driver's state of alertness monitoring through the identification of the fight against to fall asleep has been validated. The proposed algorithm may be a valuable vehicle safety system to alert drowsiness while driving.

Ying X.

Overfitting is a fundamental issue in supervised machine learning which prevents us from perfectly generalizing the models to well fit observed data on training data, as well as unseen data on testing set. Because of the presence of noise, the limited size of training set, and the complexity of classifiers, overfitting happens. This paper is going to talk about overfitting from the perspectives of causes and solutions. To reduce the effects of overfitting, various strategies are proposed to address to these causes: 1) “early-stopping” strategy is introduced to prevent overfitting by stopping training before the performance stops optimize; 2) “network-reduction” strategy is used to exclude the noises in training set; 3) “data-expansion” strategy is proposed for complicated models to fine-tune the hyper-parameters sets with a great amount of data; and 4) “regularization” strategy is proposed to guarantee models performance to a great extent while dealing with real world issues by feature-selection, and by distinguishing more useful and less useful features.

Chai M., Li S., Sun W., Guo M., Huang M.

Drowsy driving is one of the main causes of road traffic accidents. It is of great significance to study the use of steering wheel status to detect the drowsiness of the driver. In the studies of the steering wheel state, there is a general problem of the parameter selection being not comprehensive and individual differences in the way of the controlling of the steering wheel not being considered. A driving simulator was used to collect eleven parameters related to the steering wheel, where four parameters having significant correlations with driver status were selected using variance analysis. A multilevel ordered logit (MOL) model, support vector machine (SVM) model and BP neural network (BP) model were built based on the selection of the parameters. Under the same conditions of classification, the recognition accuracy of the MOL model was shown to be much higher than that of the two other models. It was concluded that the MOL model using the steering wheel parameters and considering differences among individuals outperforms the others in terms of driver's state recognition.

Kumar A., Kaur A., Kumar M.

With the marvelous increase in video and image database there is an incredible need of automatic understanding and examination of information by the intelligent systems as manually it is getting to be plainly distant. Face plays a major role in social intercourse for conveying identity and feelings of a person. Human beings have not tremendous ability to identify different faces than machines. So, automatic face detection system plays an important role in face recognition, facial expression recognition, head-pose estimation, human–computer interaction etc. Face detection is a computer technology that determines the location and size of a human face in a digital image. Face detection has been a standout amongst topics in the computer vision literature. This paper presents a comprehensive survey of various techniques explored for face detection in digital images. Different challenges and applications of face detection are also presented in this paper. At the end, different standard databases for face detection are also given with their features. Furthermore, we organize special discussions on the practical aspects towards the development of a robust face detection system and conclude this paper with several promising directions for future research.

Wu Y., Ji Q.

The locations of the fiducial facial landmark points around facial components and facial contour capture the rigid and non-rigid facial deformations due to head movements and facial expressions. They are hence important for various facial analysis tasks. Many facial landmark detection algorithms have been developed to automatically detect those key points over the years, and in this paper, we perform an extensive review of them. We classify the facial landmark detection algorithms into three major categories: holistic methods, Constrained Local Model (CLM) methods, and the regression-based methods. They differ in the ways to utilize the facial appearance and shape information. The holistic methods explicitly build models to represent the global facial appearance and shape information. The CLMs explicitly leverage the global shape model but build the local appearance models. The regression based methods implicitly capture facial shape and appearance information. For algorithms within each category, we discuss their underlying theories as well as their differences. We also compare their performances on both controlled and in the wild benchmark datasets, under varying facial expressions, head poses, and occlusion. Based on the evaluations, we point out their respective strengths and weaknesses. There is also a separate section to review the latest deep learning based algorithms. The survey also includes a listing of the benchmark databases and existing software. Finally, we identify future research directions, including combining methods in different categories to leverage their respective strengths to solve landmark detection “in-the-wild”.

Milesich T., Danko J., Bucha J.

Abstract This paper deals with the possibility of creating a vehicle model using a hierarchy of neural networks. Based on this model, it is possible to build an optimization cycle that looks for parameters which are influencing the driving of vehicles along given path. The given path must include a driving through the town, out of town and along the highway section, so the test track contains the greatest number of driving modes. Data for neural network are obtained from the CAN bus and the GPS sensor. Based on the built model and given route it is looking for such route drive, where it eventually came that the development of fuel consumption is lower than in unoptimized drive.

Wang N., Gao X., Tao D., Yang H., Li X.

This paper presents a comprehensive survey of facial feature point detection with the assistance of abundant manually labeled images. Facial feature point detection favors many applications such as face recognition, animation, tracking, hallucination, expression analysis and 3D face modeling. Existing methods can be categorized into the following four groups: constrained local model (CLM)-based, active appearance model (AAM)-based, regression-based, and other methods. CLM-based methods consist of a shape model and a number of local experts, each of which is utilized to detect a facial feature point. AAM-based methods fit a shape model to an image by minimizing texture synthesis errors. Regression-based methods directly learn a mapping function from facial image appearance to facial feature points. Besides the above three major categories of methods, there are also minor categories of methods which we classify into other methods: graphical model-based methods, joint face alignment methods, independent facial feature point detectors, and deep learning-based methods. Though significant progress has been made, facial feature point detection is limited in its success by wild and real-world conditions: variations across poses, expressions, illuminations, and occlusions. A comparative illustration and analysis of representative methods provide us a holistic understanding and deep insight into facial feature point detection, which also motivates us to explore promising future directions.

Chen Y., Yang J., Qian J.

Facial landmark detection is an important issue in many computer vision applications about faces. It is very challenging as human faces in wild conditions often present large variations in shape due to different poses, occlusions or expressions. Deep neural networks have been applied to learn the map from face images to face shapes. To the best of our knowledge, Recurrent Neural Network (RNN) has not been used in this issue yet. In this paper, we propose a method which utilizes RNN and Deep Neural Network (DNN) to learn the face shape. First, we build a global network using Long Short Term Memory (LSTM) architecture of RNN to get the initial landmark estimation of faces. Then, we use feed-forward neural networks for local search where a component-based searching method is explored. By using LSTM-RNN, the initial estimation is more reliable which makes the following component-based search feasible and accurate. Experiments show that the global network using LSTM-RNN gets better results than previous networks in both videos and single image. Our method outperforms the state-of-the-art algorithms especially in terms of fine estimation of landmarks.

Hatem H., Beiji Z., Majeed R.

Čolić A., Marques O., Furht B.