Vehicle Trajectory Clustering and Anomaly Detection at Freeway Off-Ramp Based on Driving Behavior Similarity

Abstract Human drivers have different driver behaviors when operating vehicles. These driving behaviors, including the driver’s preferred speed and rate of acceleration, impose a major impact on vehicle fuel consumption consequently. In this study, we proposed a feature-based driver behavior learning model from demonstrated driving data utilizing the Inverse Reinforcement Learning (IRL) approach to analyze various driver behaviors and their impacts on vehicle fuel consumption. The proposed approach models the individual driving style as cost function which is a linear combination of the features and their corresponding weights. The proposed IRL framework is used to find the model parameters that fit the observed driving style best. By using the learned driving behavior model, the most likely trajectories are computed and the optimized feature weights are used to analyze different driver behaviors. The different driver behaviors and their impacts on vehicle fuel consumption are then analyzed in real-world driving scenarios. Results show that the proposed IRL framework can successfully learn individual driver behaviors using vehicle trajectory data demonstrated by different real drivers. The learned driver behaviors promise a significant correlation between driving behavior and fuel consumption.

Download Full-text

Vehicle Trajectory Clustering in Urban Road Network Environment Based on Doc2Vec Model

10.1109/ijcnn52387.2021.9534341 ◽

2021 ◽

Author(s):

Jun Kang ◽

Haosen Ma ◽

Zongtao Duan ◽

Haojian He

Keyword(s):

Road Network ◽

Network Environment ◽

Trajectory Clustering ◽

Urban Road Network ◽

Urban Road ◽

Vehicle Trajectory

Download Full-text

Identifying Wrong-Way Driving Incidents from Regular Traffic Videos Using Unsupervised Trajectory-based Method

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/03611981211036378 ◽

2021 ◽

pp. 036119812110363

Author(s):

Qing Chang ◽

Jiaxiang Ren ◽

Huaguo Zhou ◽

Yang Zhou ◽

Yukun Song

Keyword(s):

Urban Areas ◽

Toll Roads ◽

Trajectory Clustering ◽

Vehicle Recognition ◽

Detection Systems ◽

Loop Detectors ◽

Trajectory Classification ◽

Thermal Cameras ◽

Vehicle Trajectory ◽

Transportation Agencies

Currently, transportation agencies have implemented different wrong-way driving (WWD) detection systems based on loop detectors, radar detectors, or thermal cameras. Such systems are often deployed at fixed locations in urban areas or on toll roads. The majority of rural interchange terminals does not have real-time detection systems for WWD incidents. Portable traffic cameras are used to temporarily monitor WWD activities at rural interchange terminals. However, it has always been a time-consuming task to manually review those videos to identify WWD incidents. The objective of this study was to develop an unsupervised trajectory-based method to automatically detect WWD incidents from regular traffic videos (not limited by mounting height and angle). The principle of the method includes three primary steps: vehicle recognition and trajectory generation, trajectory clustering, and outlier detection. This study also developed a new subtrajectory-based metric that makes the algorithm more adaptable for vehicle trajectory classification in different road scenarios. Finally, the algorithm was tested by analyzing 357 h of traffic videos from 14 partial cloverleaf interchange terminals in seven U.S. states. The results suggested that the method could identify all the WWD incidents in the testing videos with an average precision of 80%. The method significantly reduced person-hours for reviewing the traffic videos. Furthermore, the new method could also be applied in detecting and extracting other kinds of abnormal traffic activities, such as illegal U-turns.

Download Full-text

Traffic Flow Detection at Road Intersections Based on K-Means and NURBS Trajectory Clustering

Mathematical Problems in Engineering ◽

10.1155/2020/1383198 ◽

2020 ◽

Vol 2020 ◽

pp. 1-6

Author(s):

Jun-fang Song ◽

Shu-yu Wang ◽

Hai-li Zhao

Keyword(s):

Traffic Flow ◽

Traffic Congestion ◽

Simple Algorithm ◽

Trajectory Clustering ◽

End Points ◽

Nurbs Curve ◽

Flow Parameters ◽

Intersection Area ◽

Vehicle Trajectory ◽

Flow Detection

In view of the variety and occlusion of vehicle target motion on the urban intersection, it is difficult to accurately detect the traffic flow parameters in all directions and categories of the intersection, so an improved k-means trajectory clustering method based on NURBS curve fitting is designed to obtain the traffic flow parameters. Firstly, the B-spline quadratic interpolation function is used to fit the smooth NURBS curve of vehicle trajectory; secondly, K-means clustering is used to measure the minimum distance, and the location of the first and last end points of the vehicle trajectory is used to realize the automatic division of the intersection area; finally, according to the intersection area where the start and end points of vehicle trajectory belong, respectively, the moving mode of a vehicle is determined, and the traffic flow parameters are classified and counted. Experiments show that the method has high accuracy and simple algorithm, which can meet the application requirements of intelligent transportation. It can provide effective data for traffic congestion analysis and lane occupancy estimation, and it is an important parameter for dynamic time setting of intersection information lights.

Download Full-text