A pedestrian group crossing intention prediction model integrating spatiotemporal features

Background Among the largest Italian Regions, Piedmont (Northern Italy) had in 2017 a crude rate of road traffic accidents (RTA) deaths greater than the national average. RTA injuries remain a leading cause of injury deaths in Italy. Among them in both Piedmont and Italy many victims are vulnerable road users (VRU): pedestrians, cyclists and users of motorcycles or motorpeds. The study was aimed to describe their mechanisms of injury. Methods Observational study of the resident population in Piedmont from 2003 to 2015. Transportation Injuries (ICD-10: V01-V99) were considered, because of their greater comparability rate in bridge coding studies. A number of 5,185 RTA deaths was observed. Role, type of vehicle of the victim and collision were studied. Results Piedmont in 2017 had a RTA mortality rate (6.35 deaths per 100,000 inhabitants) greater than Italy (IRR = 1.13, 95% CI: 1.00 - 1.29; p < 0.02), 48.4% of the victims were VRU similarly to national data (49.8%). In the period the proportion of VRU on RTA deaths steadily increased from 25.6% in 2003 to 49.1% in 2015, in a significant way (z = 2.79; p = 0.005), because in a context of marked reduction of RTA mortality (-54.5%), the regional trend for VRU shows only a slight decrease (-12,6%). The VRU were: pedestrians (47.0%), motorized two-wheels users (37.4%) and cyclists (15.6%). Among pedestrians 63.9% deaths were caused by collisions with mainly automobiles (82.1%) and heavy vehicles (12.7%). In case of collision the prevalent causes of death were head injuries (41.5%) and multi-trauma (31.8%). Similar patterns were observed for cyclists, while in motorcyclists 56.5% of deaths were due to loss of control or fixed object. Conclusions VRU injuries remain a public health and social concern. Yet despite their extent, this problem is still not adequately considered in public health prevention programs. The observed mechanisms of injury evidence the importance to enhance the protection of VRU in road traffic circulation. Key messages In Italy, vulnerable road users are becoming a major group among road traffic injury deaths, because they not follow the general trend of large decrease of RTA injuries. Largest VRU group are pedestrians such as cyclists they are hit by cars or heavy vehicles with major trauma, in the motorized two-wheels loss of control and collision with fixed object are important.

:Background:It is a known fact that road traffic accidents are responsible for nearly 1.3 million deaths and another 50 million injuries in a year around the globe. Depending on the economic development of the country, victim category may change. In countries like Sri Lanka Vulnerable Road Users (VRU) are more susceptible for road traffic accidents. According to police records pedestrian involved accidents were top the list among other victim categories up to 2015. At present motor cycle riders are recorded as the highest number of victims due to road traffic accidents and pedestrians are at the second place. This paper is about pedestrians involved road traffic accidents reported to Kandy Police station in Sri Lanka to investigate and report a comparison of accidents recorded. Data Collection By law it is mandatory to report all the road traffic accidents to the police station concerned. For this study, road traffic accidents reported to Kandy police station during the period 29.08.2017 to 31.12.2018 were considered. Kandy is the second largest city in Sri Lanka and Kandy has nearly 10% of total traffic related incidents reporting compared to rest of the Country. As explained by Ming Sun et al it is very important pay detailed information about the pedestrian involved accidents to find an acceptable solution to ensure their safety. As a start, summary of accident categories are summarized in the table 1. Table 1: Summary of victim categories reported to Kandy Police Station Severity Gender of the Victim Female Male Grand Total Pedestrian Others Pedestrian Others Fatal 13 2 10 10 35 Grievous 30 19 36 63 148 Grand Total 43 21 46 73 183 According to the table 1, it is evident that pedestrians are highly vulnerable to road traffic accidents in the study area concerned. Further, Table 2 is representation of the same data set in percentages. Table 2 : Percentages of road traffic accidents for Pedestrians and others Pedestrian Others Pedestrian Others Fatal 37.14% 5.71% 28.57% 28.57% 100.00% Grievous 20.27% 12.84% 24.32% 42.57% 100.00% It is important to check whether the accidents are prominent in weekdays or weekends. Table 3 is a summary of accidents summarized according to the day of the week; Table 3 Accident variation according to the day of the week Pedestrian Involved accident Other Accidents Weekdays 70 70 Weekends 19 23 Accident / day (Weekday) 14 14 Accident/ Day (Weekend) 9.5 11.5 According to the dataset considered, there is no difference of accidents per day for weekdays for pedestrian involved and others. But for Weekends, there is a difference of accidents per day on weekends. This may be due to more pedestrians travel during weekdays due to official commitments, schooling etc. Table4. Vehicles involved in Accidents Vehicle Category Victim Category Pedestrian others Motor cycle 31 17 Three wheelers 9 37 Other Vehicles 49 39 Grand Total 89 93 According to the table 4, Motor Cycles and Three wheelers are responsible for most of the Pedestrian involved accidents. Since Motor cycles and three wheelers also categorized as vulnerable road users similar to pedestrians, they should be educated about the importance of sharing facilities with their fellow road users. Table 5 Accident locations Female Male Pedestrian Others Pedestrian Others Fatal Pedestrian crossing 6 0 2 0 others 7 2 8 10 Grievous Pedestrian crossing 9 0 11 1 Others 21 19 25 62 Grand Total 43 21 46 73 as per the information collected and analyzed, pedestrian involved accidents are high at pedestrians crossings compared to other locations. It is a known fact that pedestrian movements, especially across roads are higher at pedestrian crossings, but making such places safer also an important responsibility of the authorities.Conclusions:Pedestrian involved accidents are at a very high percentage. This may be because of low property damage and minor injury relate accidents also considered. Due to various uncertainties and possible underreporting, only fatal accidents and accidents categories as grievous are considered. According to the dataset considered, pedestrians are at high risk on roads compared to other road users. Main culprits in making pedestrian related accidents are other groups of vulnerable road users namely Motorcycle riders and Three-wheeler drivers. Pedestrian related accidents are more prominent during weekends compared to other victim categories.Keywords:Traffic Accidents, Pedestrian accidents, Vulnerable road users

Principal objectives of the Intelligent Transportation Systems (ITS) are to improve traffic safety, facilitate informed traffic decision making, and enhance quality of life and services in a smart traffic environment. Vehicle crashes at urban traffic intersections are among the rudimentary sources of injuries and fatalities in the cities. According to the report of the World Health Organization (WHO), in every 25 seconds, one vulnerable road-user is being killed by a vehicle crash. Therefore, it is necessary to take a novel and smart approach for improving the safety and reducing vehicle crashes. This leads to a contextual perception and spatial awareness of driver to increase security and safety for the driver, vehicle, and road users. Autonomous vehicles collects the information from the environment through equipped sensors on the vehicle such as camera, laser, radar, and Global Navigation Satellite Systems (GNSS). The main challenge arises when the person or objects are located beyond the driver’s Field of View (FOV) and cannot be detected by embedded sensors on the vehicles. This paper proposes an Advanced Driver Assistance System (ADAS) to increase the safety on road intersections by taking advantage of existing infrastructures (e.g road camera) being used for traffic control. The aim of this research is improving the driver’s FOV using a computer vision approach (e.g background subtraction algorithm) and Location Based Service (LBS). The case study results at Tehran metropolitan demonstrate the reduction in traffic collision risk and improvement of pedestrian safety using the proposed system.

In metropolitan areas, common traffic issues include traffic congestion, traffic accidents, air pollution, and energy consumption occur. To resolve this issues, Intelligent Transportation Systems (ITS) have been evolved by many researchers. One of the important sub-systems in the development of ITS is a Traffic Management System (TMS) which attempts to reduce a traffic congestion. In fact, TMS itself relies on the estimation of traffic flow, therefore providing such an accurate traffic flow prediction is needed. For this reason, we aim to provide an accurate traffic flow prediction to facilitate this system. In this works, a Supervised Deep Learning Based Traffic Flow Prediction (SDLTFP) was proposed which is a type of fully-connected deep neural network (FC-DNN). Timely prediction is also a major issue in guaranteeing reliable traffic flow prediction. However, training a deep network could be time-consuming, and overfitting is might be happening, especially when feeding small data into the deep architecture. The network is learned perfectly during the training, but in testing with the new data, it could fail to generalize the model. We adopt the Batch Normalization (BN) and Dropout techniques to help the network training. SGD and momentum are carried out to update the weight. We then take advantage of open data as historical traffic data which are then used to predict future traffic flow with the proposed method and model above. Experiments show that the Mean Absolute Percentage Error (MAPE) for our traffic flow prediction is within 5 % using sample data and between 15% to 20% using out of the sample data. Training a deep network faster with BN and Dropout reduces the overfitting.

The introduction to autonomous vehicles and intelligent transportation systems, as well as related work on autonomous vehicles and intelligent transportation systems, are described in this chapter. Aside from that, it has a chapter on autonomous intelligent vehicles and autonomous vehicles. Issues and challenges in autonomous intelligent vehicles, as well as the framework of an intelligent transportation system. In addition, the chapter discusses research opportunities in autonomous intelligent vehicles, IPv4 and IPv6 issues, and the future of IPv9 for vehicles, as well as a survey on autonomous vehicles in highway scenarios. During the last century, the automobile industry has excelled at producing cars that are both safe and affordable. Because of significant advancements in the Internet of things (IoT), the programmable logic controller (PLC), and other aspects of computing, autonomous vehicles (AVs) are becoming a reality. Cars, trucks, and other vehicles that don’t need to be plugged in to get power are referred to as self-sufficient vehicles. The multi-agent-based transportation system, which demonstrates how vehicles, drivers, roads, infrastructure, and vehicles all work together, is one of the most important intelligent transportation systems because it demonstrates how all of these things work together. To solve and manage traffic problems, an intelligent transportation systems (ITS) system employs a variety of technologies. Communication and control, vehicle sensing, and electronics are among these technologies. ITS has been used in the developed world for the past two decades. It is still a novel concept in the developing world. Sensors and computers work together in the Internet of things to store and process data, and data analytics is used to make the traffic system run more smoothly.KeywordsAutonomous vehicle (AV)Intelligent transportation system (ITS)Autonomous intelligent vehicle (AIV)Advanced driver assistance system (ADAS)Advanced driving system (ADS)

Ensuring the safety of vulnerable road users (VRUs), including pedestrians, cyclists, electric scooter riders, and motorcyclists, remains a major challenge for advanced driver assistance systems (ADAS) and connected and automated vehicles (CAV) technologies. Real-world VRU tests are expensive and sometimes cannot capture or repeat rare and hazardous events. In this paper, we present a lightweight, configurable simulation framework that follows European New Car Assessment Program (Euro NCAP) VRU testing protocols. A rule-based finite-state machine (FSM) is developed as a motion planner to provide vehicle automation during the VRU interaction. We also integrate ego-vehicle perception and idealized Vehicle-to-Everything (V2X) awareness to demonstrate safety margins in different scenarios. This work provides an extensible platform for rapid and repeatable VRU safety validation, paving the way for broader case-study deployment in diverse, user-defined settings, which will be essential for building a more VRU-friendly and sustainable intelligent transportation system.

With development of computer vision (CV) and Artificial Intelligent (AI) the domains like object detection, object tracking their development from 2D to 3D tracking and human pose estimation have gained a lot of popularity and demand in the field of Advanced Driver Assistance Systems (ADAS) and Autonomous Driving (AD). Basically, these systems are designed with an objective to increase the safety and avoid road accidents while driving. These systems develop the ability of car driver to react to various types of hazards and dangers on the road. If it is possible to know the intentions of Vulnerable Road Users (VRUs) like pedestrian, cyclist or motorbike riders then the probability of road accidents can be reduced to great extents. The ADAS systems are able to warn the car driver through automatic systems and thus provide high safety. This paper proposes Convolutional neural Networks (CNN) based VRUs hand signal recognition system based on Region Multi-Person Pose Estimation (RMPE) [1] framework for human pose estimation to know the hand signals given by the bicyclist, scooter, e-scooter and motorbike riders to warn the car driver. The VRUs are well aware of the traffic rules and regulations and also follow them. Based on the signal given by bicyclist the ego-vehicle can stop or reduce its speed. The focus of this novel algorithm proposed in this paper is that it is capable of recognizing all the six hand signals of bicyclists left, right, stop, give way, slow down and road hazard which are not addressed before in any previous works. Also, this algorithm can recognize arm signals of scooter, e-scooter riders and motorbike riders efficiently. The dataset used for testing is the self-captured dataset for VRUs Arm Signal Recognition and to generalize it Cyclist Arm Signal Recognition (CASR) [2] dataset is also used. The proposed work provides state-of-the-art (SOTA) results for VRUs hand signal recognition and frame rate of 10 FPS and 92% acuuracy.

EXPERT ASSESSMENTS IN DECISION MAKING: RISKS AND SAFETY The aim of research, based on the results of which this article was prepared, is the analysis of the main methodological provisions of providing an expert assessment (audit) of engineering and planning decisions, organizational and management measures to ensure road safety (RS) for vulnerable road users, as well as determining ways to improve it in Ukraine taking into account the specific features of the movement of the specified categories of the population and progressive world practices. Since the current level of mortality and injuries due to traffic accidents (TA) in Ukraine significantly exceeds the average European indicators, and the level of effectiveness of scientific and methodological support of activities in the field of road safety is insufficient, the relevance and social significance of the research topic are obvious. The research results are presented in the form of the authors' opinions regarding the following problems (areas of activity) in the RS field, which should be subject to expert assessment: – the actual level of traffic accidents among the main categories of vulnerable road users in Ukraine; – modern domestic and foreign scientific– methodical and engineering– planning approaches to the formation of individual elements of an effective and safe transport infrastructure, as well as progressive traffic management systems (TS); –  the possibilities and expediency of implementing engineering and planning solutions, organizational and management measures to improve RS in Ukraine in accordance with the principles of sustainable mobility, taking into account the interests of certain types of vulnerable traffic participants (pedestrians, low- mobility population groups, children, cyclists).

Preparing drivers for the future: Evaluating the effects of training on drivers’ performance in an autonomous vehicle landscape

This article presents a methodological framework for scenario-driven safety verification in automotive systems, with specific emphasis on its integration within the ISO 26262 functional safety standard. It focuses on advanced driver assistance systems (ADAS) and autonomous driving functions, detailing how diverse driving scenarios—including varied road conditions, traffic situations, weather conditions, and potential vehicle faults—are defined and simulated to ensure comprehensive safety validation. The framework leverages virtual simulation and hardware-in-the-loop environments to implement key processes including scenario definition, safety analysis, and risk mitigation. By establishing robust links between test scenarios and specific ISO 26262 safety goals, the approach enables rigorous risk assessment and seamless integration into verification and validation workflows. While addressing challenges such as scenario complexity, coverage analysis, and computational overhead, this article demonstrates how early hazard identification and thorough validation strengthen automotive functional safety assurance. This provides practical insights for implementing scenario-driven verification within the ISO 26262 context, contributing to enhanced safety validation practices in autonomous vehicle development.

The advanced driver assistance system (ADAS) for adaptive cruise control and collision avoidance is strongly dependent upon the robust image recognition technology such as lane detection, vehicle/pedestrian detection, and traffic sign recognition. However, the conventional ADAS cannot realize more advanced collision evasion in real environments due to the absence of intelligent vehicle/pedestrian behavior analysis. Moreover, accurate distance estimation is essential in ADAS applications and semiglobal matching (SGM) is most widely adopted for high accuracy, but its system-on-chip (SoC) implementation is difficult due to the massive external memory bandwidth. In this paper, an ADAS SoC with behavior analysis with Artificial Intelligence functions and hardware implementation of SGM is proposed. The proposed SoC has dual-mode operations of highperformance operation for intelligent ADAS with real-time SGM in D-Mode (d-mode) and ultralow-power operation for black box system in parking-mode. It features: 1) task-level pipelined SGM processor to reduce external memory bandwidth by 85.8%; 2) region-of-interest generation processor to reduce 86.2% of computation; 3) mixed-mode intention prediction engine for dualmode intelligence; and 4) dynamic voltage and frequency scaling control to save 36.2% of power in d-mode. The proposed ADAS processor achieves 862 GOPS/W energy efficiency and 31.4GOPS/ mm(2) area efficiency, which are 1.53x and 1.75x improvements than the state of the art, with 30 frames/s throughput under 720p stereo inputs.

The automotive industry is more concerned about vehicle and road safety. Nowadays the Govt. has introduced new safety regulations to improve the vehicle and road safety. Most of the accidents are happening because of human errors, violation of traffic rules, etc. To avoid or reduce these accidents and to meet the Govt. safety regulations the automotive industries started implementing new technologies like Advanced Driver Assistance System (ADAS), Passive and Active safety system in vehicles. ADAS is the most important safety feature in modern automobiles. The key functionality of ADAS is to provide more comfort to the driver and to improve road and vehicle safety by minimizing human errors. To achieve these functionalities the system use sensors like Radar (Radio Detection and Ranging), Camera, Light Detection and Ranging (LIDAR), and Ultrasonic sensors. Based on sensor input Electronic Control Unit (ECU) delivers the information to driver in terms of warnings, alarms, etc. or system takes the longitudinal and lateral control to bring the vehicle to safer zone. Focus of this paper is to discuss the hardware and software technologies used for the development of ADAS systems and its challenges.

ABSTRACTInformation and communication technologies are being massively applied in the automotive field as the basis of the new generation of active safety systems. In this extensive field of technologies, vehicular communications will constitute the core of a large set of advanced driving assistance systems for improving road safety as well as helping to reduce the environmental impact of transport. These communication technologies are currently under deployment, but their mandatory installation in newly manufactured cars is foreseen in the next 5 years. This equipment will enable the new Advanced Driver Assistance Systems (ADAS) system to be installed in these vehicles. Many of these safety applications are currently under development. However, there are some road users who are not commonly included in this vehicular communication ecosystem, specifically, vulnerable road users, such as pedestrians, cyclists, and motorcyclists. Current assistance systems focused on reducing crashes with this user group are based on sensors installed in the vehicles but do not include vehicular communications. In this article, we present a novel Vulnerable Road User (VRU) warning system based on Vehicle-to-Vehicle (V2V) communications, which is capable of detecting a motorcycle circulating in the vicinity of the connected vehicles, launching sound and visual warnings, and using a smartphone as human-machine interface. The system has been designed, implemented, and tested in the laboratory as well as on real roads in real traffic flow.

Vehicle to vehicle (V2V) communications allow to sharing real-time information among the vehicles that circulate on the nearby road areas. These communications systems are today in an early stage of development and the effort are focused into two directions, on one hand, the development of the communications infrastructure to support the information exchange. On the other hand, the development of Advanced Driver Assistance Systems (ADAS) as well as safety systems that takes advantages of these communications. Additionally, the V2V communications systems are mainly focused to cars and trucks, showing less concern for Vulnerable Road Users, pedestrians, motorcyclists and cyclists. In this paper a novel ADAS is presented, focused to avoid accidents that involve motorcyclist and cyclists using V2V communications, incorporating them to the vehicular networking taking into account the intrinsic features of each collective and adapting to increase their safety.

<div class="section abstract"><div class="htmlview paragraph">The current approach for new Advanced Driver Assistance System (ADAS) and Connected and Automated Driving (CAD) function development involves a significant amount of public road testing which is inefficient due to the number miles that need to be driven for rare and extreme events to take place, thereby being very costly also, and unsafe as the rest of the road users become involuntary test subjects. A new development, evaluation and demonstration method for safe, efficient, and repeatable development, demonstration and evaluation of ADAS and CAD functions called Vehicle-in-Virtual –Environment (VVE) was recently introduced as a solution to this problem. The vehicle is operated in a large, empty, and flat area during VVE while its localization and perception sensor data is fed from the virtual environment with other traffic and rare and extreme events being generated as needed. The virtual environment can be easily configured and modified to construct different testing scenarios on demand. This paper focuses on the VVE approach and introduces the coordinate transformations needed to sync pose (location and orientation) in the virtual and physical worlds and handling of localization and perception sensor data using the highly realistic 3D simulation model of a recent autonomous shuttle deployment site in Columbus, Ohio as the virtual world. As a further example that uses multiple actors, the use of VVE for Vehicle-to-VRU communication based Vulnerable Road User (VRU) safety is presented in the paper using VVE experiments and real pedestrian(s) in a safe and repeatable manner. VVE experiments are used to demonstrate the efficacy of the method.</div></div>