Vehicle route prediction method and device, and computer readable storage medium
By obtaining the identification and current position of the controlled vehicle on the highway, and combining historical trajectory data to calculate the probability of the vehicle's possible exit, the problem of vehicle line prediction errors caused by human judgment in the prior art is solved, and the success rate of vehicle interception and prediction accuracy are improved.
CN114330907BActive Publication Date: 2025-04-01SHANGHAI XINYI INTELLIGENT TECH CO LTD
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202111674423.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-31
- Publication Date
- 2025-04-01
- Estimated Expiration
- 2041-12-31
AI Technical Summary
Technical Problem
When the prior art is deployed at highway checkpoints, human judgment leads to errors in predicting the forward route of the suspect vehicle, resulting in failed vehicle interception and waste of human resources.
Method used
By obtaining the identification and current driving position of the vehicle, multiple candidate lines are determined, and the probability of the vehicle driving out from each candidate line is calculated based on the historical trajectory data, and the target lines are sorted and selected.
Benefits of technology
It improves the accuracy of vehicle line prediction and the success rate of vehicle interception, saving users time to analyze the vehicle's forward route by themselves.
✦ Generated by Eureka AI based on patent content.
Abstract
The present invention discloses a vehicle route prediction method and device, and a computer-readable storage medium, wherein the vehicle route prediction method comprises: obtaining the identification and current driving position of a controlled vehicle, wherein the current driving position is located on a first route, and the first route has a unique entrance and exit; determining multiple candidate routes, wherein the multiple candidate routes are connected to the first route through the exit of the first route; calculating the probability of the controlled vehicle exiting from each candidate route based on historical trajectory data, wherein the historical trajectory data includes the historical trajectory information of each vehicle on each route; and sorting each candidate route based on the probability of the controlled vehicle exiting from each candidate route, and selecting at least one candidate route with a higher ranking as the target route. The use of the above technical solution can more scientifically and accurately predict the forward route of the vehicle, thereby improving the success rate of vehicle interception.
Need to check novelty before this filing date? Find Prior Art