Deep Learning for Traffic Sign Recognition Based on Spatial Pyramid Pooling with Scale Analysis

In the area of traffic sign detection (TSD) methods, deep learning has been implemented and achieves outstanding performance. The detection of a traffic sign, as it has a dual function in monitoring and directing the driver, is a big concern for driver support systems. A core feature of autonomous vehicle systems is the identification of the traffic sign. This article focuses on the prohibitive sign. The objective is to detect in real-time and reduce processing time considerably. In this study, we implement the spatial pyramid pooling (SPP) principle to boost Yolo V3’s backbone network for the extraction of functionality. Our work uses SPP for more comprehensive learning of multiscale object features. Then, perform a comparative investigation of Yolo V3 and Yolo V3 SPP across various scales to recognize the prohibitory sign. Comparisons with Yolo V3 SPP models reveal that their mean average precision (mAP) is higher than Yolo V3. Furthermore, the test accuracy findings indicate that the Yolo V3 SPP model performs better than Yolo V3 for different sizes.

Measuring Driver Perception: Combining Eye-Tracking and Automated Road Scene Perception

Objective To investigate how well gaze behavior can indicate driver awareness of individual road users when related to the vehicle’s road scene perception. Background An appropriate method is required to identify how driver gaze reveals awareness of other road users. Method We developed a recognition-based method for labeling of driver situation awareness (SA) in a vehicle with road-scene perception and eye tracking. Thirteen drivers performed 91 left turns on complex urban intersections and identified images of encountered road users among distractor images. Results Drivers fixated within 2° for 72.8% of relevant and 27.8% of irrelevant road users and were able to recognize 36.1% of the relevant and 19.4% of irrelevant road users one min after leaving the intersection. Gaze behavior could predict road user relevance but not the outcome of the recognition task. Unexpectedly, 18% of road users observed beyond 10° were recognized. Conclusions Despite suboptimal psychometric properties leading to low recognition rates, our recognition task could identify awareness of individual road users during left turn maneuvers. Perception occurred at gaze angles well beyond 2°, which means that fixation locations are insufficient for awareness monitoring. Application Findings can be used in driver attention and awareness modelling, and design of gaze-based driver support systems.

Long-Term Evaluation of Drivers’ Behavioral Adaptation to an Adaptive Collision Avoidance System

Objective Taking human factors approach in which the human is involved as a part of the system design and evaluation process, this paper aims to improve driving performance and safety impact of driver support systems in the long view of human–automation interaction. Background Adaptive automation in which the system implements the level of automation based on the situation, user capacity, and risk has proven effective in dynamic environments with wide variations of human workload over time. However, research has indicated that drivers may not efficiently deal with dynamically changing system configurations. Little effort has been made to support drivers’ understanding of and behavioral adaptation to adaptive automation. Method Using a within-subjects design, 42 participants completed a four-stage driving simulation experiment during which they had to gradually interact with an adaptive collision avoidance system while exposed to hazardous lane-change scenarios over 1 month. Results Compared to unsupported driving (stage i), although collisions have been significantly reduced when first experienced driving with the system (stage ii), improvements in drivers’ trust in and understanding of the system and driving behavior have been achieved with more driver–system interaction and driver training during stages iii and iv. Conclusion While designing systems that take into account human skills and abilities can go some way to improving their effectiveness, this alone is not sufficient. To maximize safety and system usability, it is also essential to ensure appropriate users’ understanding and acceptance of the system. Application These findings have important implications for the development of active safety systems and automated driving.

Evaluation of Effectiveness of Speed Reduction Markings on Driving Speed in Highway Tunnel Entrance and Exit Areas

Tunnels are critical areas for highway safety because the severity of crashes in tunnels tends to be more serious. Controlling vehicle speed is regarded as a feasible measure to reduce the accident rate in the tunnel entrance and exit areas. This paper aims to evaluate the effectiveness of three types of speed reduction markings (SRMs) in tunnel entrance and exit zones by conducting a driving simulation experiment. For this study, 25 drivers completed the driving tasks in the day and night scenarios. The vehicle speed and acceleration data were collected for analysing and the relative speed contrast, time mean speed and acceleration were adopted as indices to evaluate the effectiveness of SRMs. The repeated ANOVA test results revealed that SRMs have a significant effect in reducing vehicle speed, especially in the exit zone. Colour Anti-skid Markings (CASMs) produced a more obvious deceleration in the entrance zone. In the entrance zone, a similar downward trend was performed in the situation of NSRMs and SRMs, but a lower speed occurred in case of SRMs. Besides, CASMs work better and cause an obvious gap of 10 km/h in daytime and 5 km/h at night compared to the speed without SRMs. In the exit zone, the present study supports the conclusion that the drivers are prone to accelerate. Our results showed that the drivers accelerated in case of NSRMs, while they slowed down in case of SRMs. Thus, SRMs are necessarily implemented in the highway tunnel entrance and exit zones. Our study also indicates that though CASMs result in lower speed at night, the Transverse Speed Reduction Markings(TSRMs) have a better performance than CASMs in daytime. The investigation provides essential information for developing a new marking design criterion and intelligent driver support systems in the highway tunnel zones.

Modelling Eco-Driving Support System for Microscopic Traffic Simulation

Microscopic traffic simulation is an ideal tool for investigating the network level impacts of eco-driving in different networks and traffic conditions, under varying penetration rates and driver compliance rates. The reliability of the traffic simulation results however rely on the accurate representation of the simulation of the driver support system and the response of the driver to the eco-driving advice, as well as on a realistic modelling and calibration of the driver’s behaviour. The state-of-the-art microscopic traffic simulation models however exclude detailed modelling of the driver response to eco-driver support systems. This paper fills in this research gap by presenting a framework for extending state-of-the-art traffic simulation models with sub models for drivers’ compliance to advice from an advisory eco-driving support systems. The developed simulation framework includes among others a model of driver’s compliance with the advice given by the system, a gear shifting model and a simplified model for estimating vehicles maximum possible acceleration. Data from field operational tests with a full advisory eco-driving system developed within the ecoDriver project was used to calibrate the developed compliance models. A set of verification simulations used to illustrate the effect of the combination of the ecoDriver system and drivers’ compliance to the advices are also presented.