Driver fatigue has been attributed to traffic accidents; therefore, fatigue-related traffic accidents have a higher fatality rate and cause more damage to the surroundings compared with accidents where the drivers are alert. Recently, many automobile companies have installed driver assistance technologies in vehicles for driver assistance. Third party companies are also manufacturing fatigue detection devices; however, much research is still required for improvement. In the field of driver fatigue detection, continuous research is being performed and several articles propose promising results in constrained environments, still much progress is required. This paper presents state-of-the-art review of recent advancement in the field of driver fatigue detection. Methods are categorized into five groups, i.e., subjective reporting, driver biological features, driver physical features, vehicular features while driving, and hybrid features depending on the features used for driver fatigue detection. Various approaches have been compared for fatigue detection, and areas open for improvements are deduced.

Vehicular ad hoc networks (VANETs) are vital to many Intelligent Transportation System (ITS)-enabled technologies, including efficient traffic control, media applications, and encrypted financial transactions. Due to an increase in traffic, vehicular network topology is constantly changing, and sparse vehicle distribution (on highways) hinders network scalability. Thus, there is a challenge for all vehicles (in the network) to maintain a stable route, which would increase network instability. Concerning IoT-based network transportation, this study proposes a bio-inspired, cluster-based algorithm for routing, i.e., the intelligent, probability-based, and nature-inspired whale optimization algorithm (p-WOA), which produces cluster formation in vehicular communication. Various parameters, such as communication range, number of nodes, velocity, and route along the highway were considered, and their probaabilities were incorporated into the fitness function, hence resulting in randomness reduction. Results were compared to existing methods such as Ant Lion Optimizer (ALO) and Grey Wolf Optimization (GWO), demonstrating that the developed p-WOA technique produces an optimal number of cluster heads (CH). The results achieved by calculating the Packet Delivery Ratio (PDR), average throughput, and latency demonstrate the superiority of the proposed method over other well-established methodologies (ALO and GWO). This study confirms statistically that VANETs employing ITS applications optimize their clusters by a factor of 75, which has the twin benefits of decreasing communication costs and routing overhead and extending the life of the cluster as a whole.

Fatigue has been attributed to traffic accident with higher fatality rate and causes severe damage to the surroundings compared to accidents where drivers are alert. This study presents and demonstrates an innovative driver fatigue detection method based on fatigue related facial action units' (AU) identification employing a photometric stereo (PS) testbed for 3D AU reconstruction. Initially, normal vectors were extracted for 3D AUs, subsequently, łq Quiver/Bump map' were constructed from the normal vectors. The quiver maps were further utilized for training deep neural networks. The findings exhibit that the proposed method outperforms 2D image based classification in terms of validation accuracy, for AU1, AU15 and AU41 detection. A novel method incorporating machine vision for intelligent transportation has been developed and demonstrated for driver's fatigue detection. The proposed method is also compared to other established methods and significant (95%) improvement in terms of accuracy is achieved.

In recent years, intelligent vehicles with cutting-edge vehicular applications have grown in popularity, enabling the growth of Vehicular Ad hoc Networks (VANETs). Vehicular Ad hoc Networks (VANETs) are a network of vehicles that share and analyze real-time data and require a well-organized and efficient data delivery method. The stability of clusters and dynamic topology change in VANETs are the major issues in finding an optimal route amongst the vehicles. The cooperative approach and surprise pounce chasing technique of Harris Hawks in nature serve as the main sources of inspiration for Harris Hawks Optimization. In this technique, several hawks work together to attack a victim from various angles to surprise it. Due to the unpredictable nature of situations and the prey’s fleeing movements, Harris Hawks can exhibit a variety of intelligent strategies. This study proposes a novel route clustering optimization technique that takes into account communication range, the number of nodes, velocity, orientations, and grid size. To create and evaluate ideal cluster head (CH), the proposed method is based on Harris Hawks Intelligent Optimization Algorithm for route Clustering (iCHHO) which finds optimal and reliable routes amongst the vehicles. Other state-of-the-art methods, such as the Grasshopper Optimization Algorithm (GOA), Gray Wolf Optimization (GWO), and Whale Optimization Algorithm (WOACNET), are utilized to evaluate and validate the proposed method. Our findings show that the developed method outperforms other current methods in terms of number of clusters, variable communication ranges, network size, and the number of vehicles. Furthermore, the statistical analysis concludes that the proposed method improves cluster optimization by 79% and increases cluster stability by an adjusted -squared of 91.22.

Fatigue detection has many applications, one of them is intelligent transportation for accident prevention. It is challenging to detect driver fatigue adopting photometric stereo and 3D fatigue-related facial action unit identification. During 3D reconstruction shadows are encountered, causing reconstruction error, therefore, for accurate fatigue detection shadow removal is crucial. This study presents a novel snake based approach for shadow handling in photometric stereo. Seven light sources were employed and region visibility of the light source for each region of interest (ROI) was deduced. Surface normal estimation enhancement was achieved via snake model based shadow labeling. Discrepancies measured among shadowed regions and ROIs were recorded. Light sources having high intersection with the shadow map were excluded from the reconstruction process at pixel level. This results in an automatic driver fatigue related action unit detection employing uncalibrated Lambertian surface under shadow conditions. The developed method was tested and compared with other established driver fatigue detection methods and higher performance in terms of accuracy ( i.e. 97.85%) was achieved. The developed method proves to be well suited for driver fatigue detection under uncalibrated conditions.

Road user categorization is essential for autonomous driving perception. In challenging traffic situations including unfavorable weather (such as fog, snow, and rain) and dim lighting. There are several kinds of sensors that need to be researched in order to achieve the precision and resilience that autonomous systems demand. Currently, to create a depiction of the environment surrounding the vehicle, principally cameras and laser scanners (LiDAR) are commissioned. Despite their enticing qualities, Radar sensors are currently underutilized for autonomous driving, even though, they have been employed in the automobile industry for a long time. Radar’s ability to measure the relative speed of obstacles and to operate even in adverse weather conditions makes it a front line contender for road user detection. This study proposes F-ROADNET, a multi-object classification method for vulnerable road users based on raw Radar data. The model is trained on Range Angle and Range Doppler maps based on a late fusion architecture. F-ROADNET has a detection accuracy of 99.01%, precision of 99.3% and recall of 99% on the CARRADA dataset and detection accuracy of 91.62%, precision of 87.2% and recall of 90.2% on the RADDet dataset. The findings exhibit that F-ROADNET outperforms established methods in terms of average precision.