Method, device, equipment and medium for determining vehicle queuing length for sparse trajectories

Abstract

The invention relates to the technical field of artificial intelligence and data processing, and provides a method and a device for determining the vehicle queuing length of a sparse track, equipmentand a medium. According to the method, the longitudinal relative driving distance can be calculated by combining the coordinate data and the Link data, a vertical mapping mode is adopted, and the transverse drift error of low-speed driving of an estimation point in an intersection range can be eliminated to the greatest extent; non-queuing vehicles are used to correct the queuing length to obtaina corrected length, so that the error between an estimated queuing length and a real queuing length is eliminated; and the vehicle queuing length of the missing period is filled through Kalman filtering, so that the automatic determination of the vehicle queuing length is realized, and the determination of the vehicle queuing length is more accurate. In addition, the method can also be applied tosmart traffic, thereby promoting the construction of smart cities. The invention also relates to a block chain technology, and the vehicle queuing length can be stored in a block chain node.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence and data processing, in particular to a method, device, equipment and medium for determining the queue length of vehicles with sparse trajectories. Background technique [0002] With the continuous improvement of the informatization level of urban road traffic and the continuous advancement of smart traffic, various new types of traffic detection equipment and technologies are gradually being applied to the operation monitoring and control of the traffic system, including automatic vehicle identification equipment (such as bayonet , electric police, RFID (Radio Frequency Identification, radio frequency identification), etc.), vehicle navigation GPS (Global Positioning System, Global Positioning System) data, etc. These new traffic data sources can provide some vehicle IDs and their running trajectory information, providing new data support and opportunities for the control ...

AI Technical Summary

Problems solved by technology

Therefore, the estimation of queue length cannot be achieved during the missing period where two queuing vehicles are not captured

(2) The distance from the position of the last queuing vehicle to the stop line is taken as the queuing length. This assumption has a large error in the case of sparse vehicle trajectories; This assumption also has a large error in the case of low saturation and uneven traffic arrival

[0005] Secondly, although the queuing length estimation method based on the probability theory reflects the random process of queuing, it still fails to comprehensively analyze the uncertain factors of the traffic system. and other assumptions

[0006] Moreover, the above two types of methods are mostly based on simulation data or low-frequency floating car data for analysis and demonstration, and have not been verified by large-scale commercial vehicle trajectory data, and the estimation of queue length is not accurate enough.

Images