A novel intelligent vehicle risk assessment method combined with multi-sensor fusion in dense traffic environment

Abstract

Purpose-The purpose of this paper is to accurately capture the risks which are caused by each road user in time. Design/methodology/approach-The authors proposed a novel risk assessment approach based on the multi-sensor fusion algorithm in the real traffic environment. Firstly, they proposed a novel detection-level fusion approach for multi-object perception in dense traffic environment based on evidence theory. This approach integrated four states of track life into a generic fusion framework to improve the performance of multi-object perception. The information of object type, position and velocity was accurately obtained. Then, they conducted several experiments in real dense traffic environment on highways and urban roads, which enabled them to propose a novel road traffic risk modeling approach based on the dynamic analysis of vehicles in a variety of driving scenarios. By analyzing the generation process of traffic risks between vehicles and the road environment, the equivalent forces of vehicle-vehicle and vehicle-road were presented and theoretically calculated. The prediction steering angle and trajectory were considered in the determination of traffic risk influence area. Findings-The results of multi-object perception in the experiments showed that the proposed fusion approach achieved low false and missing tracking, and the road traffic risk was described as a field of equivalent force. The results extend the understanding of the traffic risk, which supported that the traffic risk from the front and back of the vehicle can be perceived in advance. Originality/value-This approach integrated four states of track life into a generic fusion framework to improve the performance of multi-object perception. The information of object type, position and velocity was used to reduce erroneous data association between tracks and detections. Then, the authors conducted several experiments in real dense traffic environment on highways and urban roads, which enabled them to propose a novel road traffic risk modeling approach based on the dynamic analysis of vehicles in a variety of driving scenarios. By analyzing the generation process of traffic risks between vehicles and the road environment, the equivalent forces of vehicle-vehicle and vehicle-road were presented and theoretically calculated.

A probabilistic risk assessment framework considering lane-changing behavior interaction

“…Driving risks cannot exist independently; therefore, to evaluate the risk level of the traffic environment, we adopt the risk field and define driving risk as the interaction of potential fields among various traffic participants in the traffic environment. Referring to the previous researches [31,32], by analyzing the relationship between force and energy transformation in the collision process, we propose the theory of the equivalent force [32]. If traffic participant j drives freely at a constant velocity in the traffic environment and is considered as a particle, the traffic risk caused by the vehicle in the environment meets the isotropy on the plane because traffic participant j can drive in any direction.…”

A Multisource Situation Information Fusion Method Based on Dynamic Evidence Combination

“…e method proposed by Liu has poor fusion accuracy in a complex network environment, with large resource consumption and low fusion efficiency [12]. Zheng et al used the Pignistic distance to measure the similarity between different pieces of evidence based on sampling past evidence using a sliding window [13]. is established an uncertain state evidence model of the Markov chain and obtained the fusion results using a Murphy combination.…”

“…. }; //initialize the alert records in time t (5) q � 1; //set the counter (6) While (q ≤ n) (7) GetAlert (Ak); //select the q th alert (8) d � Calculate S (); //calculate the similarity using equation ( 7)-( 11) (9) If (d > S) (10) S � d; (11) Else (12) q � q+1; (13) End if (14) End while (15) If (S < T) then ( 16)…”

A Review of Vehicle Detection Methods Based on Computer Vision

“…The intelligent transportation system (ITS) (Dimitrakopoulos and Demestichas, 2010) is an innovative transportation system that integrates information, automation, intelligence, and socialization, while building upon the traditional transportation systems. It utilizes various sensor devices to collect traffic information and incorporates advanced technologies such as data transmission, big data analysis, and artificial intelligence (AI) to obtain relevant information swiftly and accurately for traffic management and the maintenance of transportation infrastructure, such as roads and bridges (Zheng et al, 2018). Object recognition plays a significant role in intelligent transportation systems, serving as both a crucial technical method and a fundamental link between high-level tasks such as target tracking and behavior recognition.…”