Eye detection based on rectangle features and pixel-pattern-based texture features

Datasets are crucial when training a deep neural network. When datasets are unrepresentative, trained models are prone to bias because they are unable to generalise to real world settings. This is particularly problematic for models trained in specific cultural contexts, which may not represent a wide range of races, and thus fail to generalise. This is a particular challenge for driver drowsiness detection, where many publicly available datasets are unrepresentative as they cover only certain ethnicity groups. Traditional augmentation methods are unable to improve a model's performance when tested on other groups with different facial attributes, and it is often challenging to build new, more representative datasets. In this paper, we introduce a novel framework that boosts the performance of detection of drowsiness for different ethnicity groups. Our framework improves Convolutional Neural Network (CNN) trained for prediction by using Generative Adversarial networks (GAN) for targeted data augmentation based on a population bias visualisation strategy that groups faces with similar facial attributes and highlights where the model is failing. A sampling method selects faces where the model is not performing well, which are used to fine-tune the CNN. Experiments show the efficacy of our approach in improving driver drowsiness detection for under represented ethnicity groups. Here, models trained on publicly available datasets are compared with a model trained using the proposed data augmentation strategy. Although developed in the context of driver drowsiness detection, the proposed framework is not limited to the driver drowsiness detection task, but can be applied to other applications.

Smartphone applications became very popular nowadays as they provide useful functionalities to our daily lives over ordinary voice services. They offer a small but powerful computing platform where intelligent algorithms can be coded into some live‐saving products which profoundly impact our daily lifestyles. A mobile fatigue detection system which is proposed in this study is an important life‐saving application running on smartphone. Mobile detection system faces technological challenges such as: (i) embracing relatively low‐resolution images in image recognition; (ii) supporting fast response time given a low‐power CPU in comparison to a desktop computer; and (iii) demanding for high prediction accuracy by light‐weight machine learning algorithms, as the software programs embedded in smartphones is resource constrained. Solutions with respect to indoor facial profiling system which are mainly based on progressive locating method for eye detection are discussed in this study. Acceptable experimental results in terms of eye detection rate and driver fatigue detection in different situations are presented.

Image based eye detection and gaze estimation have a wide range of potential applications, such as medical treatment, biometrics recognition, human-computer interaction. Though a large number of researchers have attempted to solve the two problems, they still exist some challenges due to the variation in appearance and lack of annotated images. In addition, most related work perform eye detection first, followed by gaze estimation via appearance learning. In this paper, we propose a unified framework to execute the gaze estimation and the eye detection simultaneously by learning the cascade regression models from appearance around the eye related key points. Intuitively, there is coupled relationship among location of eye center, shape of eye related key points, appearance representation and gaze information. To incorporate these information, at each cascade level, we first learn a model to map the shape and appearance around current eye related key points to the three dimension gaze update. Then, with the help of estimated gaze, we further learn a regression model to map the gaze, shape and appearance information to eye location update. By leveraging the power of cascade learning, the proposed method can alternatively optimize the two tasks of eye detection and gaze estimation. The experiments are conducted on benchmarks of GI4E and MPIIGaze. Experimental results show that our proposed method can achieve preferable results in gaze estimation and outperform the state-of-the-art methods in eye detection.

Face and eye detection is one of the most challenging problems in computer vision area. The goal of this paper is to present a study over the existing literature on face and eye detection and gaze estimation. With the uptrend of systems based on face and eye detection in many different areas of life in recent years, this subject has gained much more attention by academic and industrial area. Many different studies have been performed about face and eye detection. Besides having many challenging problems like, having different lighting conditions, having glasses, facial hair or mustache on face, different orientation pose or occlusion of face, face and eye detection methods performed great progress. In this paper we first categorize face detection models and examine the basic algorithms for face detection. Then we present methods for eye detection and gaze estimation.

Nowadays, drowsiness is a serious cause of traffic accidents, a problem of major concern to society. Driver fatigue or sleepiness decreases the driver’s reaction time, reduces attention, and affects the quality of decision making which impairs the driving experience. Therefore, in this paper, a drowsiness detection system is designed based on computer vision, using a cascade of classifiers based on Haar-like features. The system is able to detect the face and eyes of the driver and determine the eyes closure or opening, which concludes the drowsiness of the driver. The paper presents the five primary steps involves which are: video acquirement, frame separation, face detection, eyes detection and drowsiness detection.

Abstract: Because of its close connection to road safety, driver fatigue detection has become a major area of study in intelligent transportation systems. Drivers who are tired or distracted cause hundreds of accidents each year. This review research looks closely at the methods, difficulties, and most recent developments in the field of real-time sleepiness detection. Recent developments like as Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) are contrasted with more conventional physiological, behavioural, and vehicle-based approaches. The study evaluates sensor modalities, comparative studies, performance measures, and real-world applications, highlighting both current inadequacies and accomplishments. In order to increase resilience, the study also looks into hybrid.

Road accidents usually have many causes, but one that is very common around the world is driver drowsiness. The development of an artificial intelligence-based driver drowsiness detection system has been proposed as a means to prevent these incidents and protect the lives of drivers and other road users. The main objective of this project is to develop a driver drowsiness detection system using artificial intelligence techniques capable of detecting drowsiness in real time and alerting the driver in order to prevent traffic accidents. This system will make it possible to warn drivers and take preventative action before an accident occurs. It will use an approach based on artificial intelligence techniques, in particular machine learning. This AI-based driver drowsiness detection system has the potential to significantly reduce the number of road accidents caused by drowsiness, thereby improving road safety and protecting human life. In order to carry out the development of this project, the XP (Extreme Programming) methodology was used in order to have better management and communication development among the working team.

Drowsy driving causes many accidents. Driver alertness and automobile control are challenged. Thus, a driver drowsiness detection system is becoming a necessity. In fact, invasive approaches that analyze electroencephalography signals with head electrodes are inconvenient for drivers. Other non-invasive fatigue detection studies focus on yawning or eye blinks. The analysis of several facial components has yielded promising results, but it is not yet enough to predict hypovigilance. In this paper, we propose a “non-invasive” approach based on a deep learning model to classify vigilance into five states. The first step is using MediaPipe Face Mesh to identify the target areas. This step calculates the driver’s gaze and eye state descriptors and the 3D head position. The detection of the iris area of interest allows us to compute a normalized image to identify the state of the eyes relative to the eyelids. A transfer learning step by the MobileNetV3 model is performed on the normalized images to extract more descriptors from the driver’s eyes. Our LSTM network entries are vectors of the previously calculated features. Indeed, this type of learning allows us to determine the state of hypovigilance before it arrives by considering the previous learning steps, classifying the levels of vigilance into five categories, and alerting the driver before the state of hypovigilance’s arrival. Our experimental study shows a 98.4% satisfaction rate compared to the literature. In fact, our experimentation begins with the hyperparameter preselection to improve our results.

The fatigue driving detection and warning system based on EEG signals aims to use EEG technology to monitor the mental state of drivers in real time, so as to identify and warn fatigue driving behavior in time, so as to improve road safety. The design of the system is based on a deep understanding of the connection between EEG signals and the fatigue state, by analyzing the changes in frequency bands such as α wave, β wave, θ wave and δ wave, which are closely related to the alert state and fatigue in humans. The development of the system first considers the main factors induced by fatigue, such as sleep deprivation, long work hours and environmental monotony, which can significantly affect the activity of brain waves. From these physiological and environmental factors, the system requirements analysis emphasizes the need for real-time data processing and high accuracy, as well as a user interface design that provides clear and intuitive feedback to users (drivers and regulators). In terms of implementation, the system integrates EEG monitoring equipment for data acquisition, uses advanced signal processing algorithm to extract fatigue-related features, and uses machine learning model for real-time analysis and fatigue state determination. In addition, the system design includes an emergency response mechanism, once signs of fatigue are detected, it can automatically trigger an alarm, issue a warning to the driver, and if necessary through the vehicle control system to ensure driving safety. This comprehensive system not only improves driving safety, but also provides strong data support for traffic management departments.

This research presents a method for human detection at night in video surveillance camera. The process of detecting human at night is very challenging due to certain factors such as radiance, silhouette and low external light. A comparative study between three texture features that are Discrete Wavelet Transform (DWT), Histogram of Oriented Gradient (HOG) and Speeded Up Robust Feature (SURF) using Support Vector Machine (SVM), Naive Bayes and Adaboost classifiers are investigated using primary data extracted from a video surveillance camera at the faculty. The results show that HOG feature with Naive Bayes detect human in video surveillance better compared to DWT and SURF with SVM and AdaBoost classifiers.

While accuracy provides quality, detection speed is paramount when it comes to usability. Several recently developed technologies have high accuracy eye detection; however, artificial intelligence technologies are moving away from fast detection. We focus on low computational loads and high speed for cases where eye detection is used. Therefore, a low brightness color threshold was applied to the existing projection function method, and an eyebrow removal operation was added. All of these operations were configured in parallel to operate in real time.

With the development of technology and society, cars have become an indispensable part of people's daily life and business. As a result, the problem of traffic accidents has also become a considerable cause of casualties in society today. Driver fatigue detection is considered a promising technology to reduce traffic accidents. Cars can remind drivers or make corresponding actions when noticing that drivers are tired through the data transmitted by the detection system. Machine learning is the essential part of driver fatigue detection, which has the advantages of high performance and accuracy. Most driver fatigue detection Systems will use machine learning to get a better result. This article will analyze the Machine Learning currently used in driver fatigue detection, including Hidden Markov Model, Support Vector Machine, Gradient Boosting Decision Tree, Convolutional Neural Network, Deep Belief Networks, Recurrent neural network, and Radial Basic Function Network.

Research on autonomous and smart vehicles technology has been growing exponentially in recent years by integrating more and more smart software inside, those intelligent vehicles have several functionalities such as environment recognition, driver drowsiness detection and communication with other cars, etc. Thus, a supervisor is needed to control sensors and actuators, to manage the network and to process data tasks. In most of smart automobiles, embedded RTOS (Real Time Operating System) are used as supervisor to control all data coming from the different sensors, and to meet the real time requirements. In this paper, we investigate the real time software control in smart/autonomous through the design and prototyping of an ADAS (Advanced Driver Assistant System) real time application for vehicle environment recognition and objects detection. On one hand, we port the real time operating system FreeRTOS on the top of Multi/CPU-FPGA platform, and then we point out the advantages of the FreeRTOS to develop a real smart embedded system for environment car detection within a hardware prototype on a top of the FPGA Zynq hardware platform. On the other hand, a deep comparison between FreeRTOS and standard operating embedded Linaro/Linux, is presented. The entry point of our real time ADAS application system is a point cloud coming from LIDAR sensors as an input, and then several steps are defined in the application: data segmentation, objects searching, features extracts and classification. As a first step of validation, our ADAS application detects pedestrians using High-Definition range data.

This paper presents a novel algorithm to detect face and eyes in a reliable manner with a stereo camera. With the combination of stereo tracking method for object detection and tracking and structure-based method and example-based learning approach for face detection a real time and robust system is built. Human head detection is implemented with a stereo vision system, where a layered scenery is obtained from the depth image. With head-shoulder contour model applied to the disparity image, a fast head detection algorithm is developed. On the head detected, which also tells the rough scale of it, a hybrid face detection algorithm is proposed for face pattern detection and eyes location. By applying the face structure model and facial components model, face candidates in images are obtained for the later validating of face pattern. The support vector machine (SVM) is adopted here to select the good samples that form a classification boundary to classify face and non-face patterns.

With the rapid development of urban rail transit in my country, the safety inspection of subway tunnel infrastructure is in urgent need of automated and intelligent theory and technology research and development. The subway tunnel lining environment is bad, there are a lot of noise and uneven illumination, and the texture features are complex. The traditional manual and image detection and recognition methods have gradually been replaced by more intelligent and effective deep learning algorithms. Therefore, this paper proposes a subway tunnel lining image recognition and detection algorithm that combines image processing and deep convolutional networks, which can quickly and accurately distinguish between cracked images and non-cracked images, and can realize intelligent target search and category labeling in complex images. In this experiment, a total of 4000 original images of subway tunnels were selected, and pixel-level shallow processing operations such as batch preprocessing, hierarchical feature analysis, and extraction of the circumscribed rectangle of the connected area were carried out. For the training sample library of crack images, pixel-level image processing experiments and classification and recognition experiments are carried out for the training sample library to obtain the optimal database processing results, and then the image recognition algorithm for complex cracks in subway tunnels is studied. Experiments show that there are more point noises and block noises in the results of the subway tunnel crack images, and the segmentation results of the crack images have relatively less noise residues. Due to the wall material, some cement materials are a little off, resulting in noise retention. This shows that the algorithm in this paper has a certain application value in the intelligent identification of actual subway tunnel diseases, and provides technical support and research ideas for the application of subsequent deep learning in subway tunnel disease detection.