US 12,347,310 B2
Method for short-term traffic risk prediction of road sections using roadside observation data
Nengchao Lyu, Wuhan (CN); Jiaqiang Wen, Wuhan (CN); Lingfeng Peng, Wuhan (CN); Wei Hao, Wuhan (CN); Haoran Wu, Wuhan (CN); and Yugang Wang, Wuhan (CN)
Assigned to WUHAN UNIVERSITY OF TECHNOLOGY, Wuhan (CN)
Filed by Wuhan University of Technology, Wuhan (CN)
Filed on Sep. 10, 2021, as Appl. No. 17/471,212.
Claims priority of application No. 202110562845.X (CN), filed on May 24, 2021.
Prior Publication US 2022/0383738 A1, Dec. 1, 2022
Int. Cl. G08G 1/01 (2006.01); G06F 18/2411 (2023.01); G06F 18/2413 (2023.01); G08G 1/052 (2006.01); G08G 1/16 (2006.01)
CPC G08G 1/0145 (2013.01) [G06F 18/2411 (2023.01); G06F 18/24147 (2023.01); G08G 1/0116 (2013.01); G08G 1/052 (2013.01); G08G 1/166 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A method for short-term traffic risk prediction of road sections using roadside observation data, including the following steps:
1) a vehicle trajectory of each vehicle in a detection area is obtained by the roadside observation data;
basic information of vehicles in the detection area is collected by roadside detection equipment; the basic information includes a timestamp, vehicle ID, vehicle position and speed;
based on the basic information of the vehicles stored in radar, position information and speed information of the vehicles are extracted frame by frame according to the vehicle ID, and finally the vehicle trajectory of each vehicle in the detection area is obtained;
2) according to the vehicle trajectory of each vehicle in the detection area, traffic flow indicators are counted and surrogate safety indicators between vehicles are calculated; the surrogate safety indicators include: deceleration, distance headway, time headway, time to collision, modified time to collision, and stopping distance;
the traffic flow indicators include: traffic flow, occupancy rate, vehicle speed, congestion index and a number of lane changes;
3) the time to collision and the deceleration are selected as identification indicators to identify conflict events with collision risk in the detection area;
4) traffic flow indicators and surrogate safety indicators within a set time before occurrence of the identified conflict events are extracted, and classification algorithms are used to perform feature screening on the extracted traffic flow indicators and surrogate safety indicators;
5) based on selected feature indicators, the selected feature indicators with a highest importance ranking are selected as input to construct a short-term traffic risk prediction model, and the identified conflict events are used to complete the model training and testing;
6) With the support of the constructed short-term traffic risk prediction model, the selected feature indicators are selected as input to predict a traffic risk configured for traffic safety control.