Roadway safety research indicates a correlation between drivers’ behavior, the demographics, and the local environment affecting the risk perception and roadway crashes. This research examines these issues in an Egyptian context by addressing three groups: private cars drivers, truck drivers, and public transportation drivers. A Driver Behavior Questionnaire (DBQ) was developed to capture information about drivers’ behavior, personal characteristics, risk perception, and involvement in crashes. The risk perception was captured subjectively by exposing participants to various visual scenarios representing specific local conditions to rank their perception of the situation from a safety perspective.Results indicated that the human factor, in particular, failure of keeping a safe following distance, was a major cause of crashes. The analyzed data was used to predict expected crash frequency based on personal attributes, such as age, driving experience, personality traits, and driving behavior, using negative binomial models. The study recommends that the DBQ technique, combined with risk perception scenarios, can be used to understand drivers’ characteristics and behaviors and collect information on the crashes they experience.Practically the study findings could provide series of recommendations to the local authorities about the introduction of the traffic management and noise control act; raising awareness of driving etiquette; setting and enforcing driving hours’ regulations, and consider specific training programs for beginners drivers.

A key to better geometric design of highways is designing horizontal curves conforming to driver behaviour. The values of side friction factors in the point mass formula, used for the design of the minimum radius of a horizontal curve, are based on the upper threshold of driver comfort. In the current guidelines, these driver comfort levels were established in research work carried out back in the 1930s. Recently, it was found that faster drivers tend to accept higher comfort thresholds to maintain their speed and minimize speed reduction between curve and tangent. An experiment was designed at Carleton University to collect newer data on driver behaviour including speed and lateral acceleration. The results confirmed the need to revise the values of side friction demand especially for sharp curves. In addition, a model was developed to determine the side friction factor to be used in design or in consistency evaluation of horizontal curves on rural roads and ramps.

Egypt is a middle-income country, belonging to the Eastern Mediterranean Region (EMR). Egypt used to be the worst performing EMR country, with over 45 fatalities per 100,000 population. It is considered an example case of many EMR countries in the region where there is a need for quantitative assessment of safety on its roads. The Highway Safety Manual (HSM) offers several functions to calculate safety performance (SPFs), which can estimate crash frequency on a highway network according to its geometric and traffic characteristics. The HSM was developed in the United States using road and crash data specific to its environment. Jurisdictions and other non-U.S. regions were encouraged to develop locally derived models suitable for the local characteristics of roads and crashes. The objective of this paper is to assess the suitability of using the HSM models on rural multi-lane divided highways in Egypt. The calibrated SPFs considering Egyptian road factors were compared with the actual crash events. The results showed that there was a need to develop locally derived SFPs using negative binomial models. The modeling approach and a validation procedure were presented and are applicable when developing local SPFs to compare how well the model performs to the actual data, and to HSM calibrated models. The models were created using 90% of the data and tested on the remaining 10% of the data. The study found that the results relating to driver behavior would help designers in regions other than the United States to benefit from the HSM.

Designing horizontal curves conforming to driver behavior is key to creating better-designed, safer highways. Doing so is assisted by a clear, quantitative understanding of driver behavior in a real highway environment. This study is concerned with collecting driver behavior data pertaining to steering behavior and using it to find desirable spiral lengths for horizontal curves. To realize this objective, a comparison between driver steering behavior and actual geometric alignment was performed. The profiles showed that drivers, in approaching horizontal curves, changed their behavior gradually to follow a natural spiral-curve-spiral path. Desirable spiral lengths were also related to geometric characteristics of the curve and were found to correlate well with the radius of curvature for two-lane highways and freeways with high coefficients of determination. In addition, the desirable spiral lengths were compared with the different controls of spiral length found in the North American design guides. The comparison revealed discrepancies in the design procedure of the spiral length. It was found that the minimum criteria found in these guides should be revised to better describe true driver behavior. In addition, the paper showed how new recommended values for the spiral parameter and rate of change of lateral acceleration would achieve spiral lengths that conform well to driver steering behavior.

Extensive research efforts have been devoted to identify and improve roadway features that impact safety. Maintaining roadway safety features relies on costly manual operations of regular road surveying and data analysis. This paper introduces an automatic roadway safety features detection approach, which harnesses the potential of artificial intelligence (AI) computer vision to make the process more efficient and less costly. Given a front-facing camera and a global positioning system (GPS) sensor, the proposed system automatically evaluates ten roadway safety features. The system is composed of an oriented (or rotated) object detection model, which solves an orientation encoding discontinuity problem to improve detection accuracy, and a rule-based roadway safety evaluation module. To train and validate the proposed model, a fully-annotated dataset for roadway safety features extraction was collected covering 473 km of roads. The proposed method baseline results are found encouraging when compared to the state-of-the-art models. Different oriented object detection strategies are presented and discussed, and the developed model resulted in improving the mean average precision (mAP) by 16.9% when compared with the literature. The roadway safety feature average prediction accuracy is 84.39% and ranges between 91.11% and 63.12%. The introduced model can pervasively enable/disable autonomous driving (AD) based on safety features of the road; and empower connected vehicles (CV) to send and receive estimated safety features, alerting drivers about black spots or relatively less-safe segments or roads.