Method and apparatus for identifying bifurcated intersection

Abstract

The embodiment of the invention discloses a method and device for identifying a divergence intersection. One specific embodiment of the method comprises the following steps: acquiring the position ofa vehicle and the position of a branch intersection, and judging whether the vehicle is within the detection range of the branch intersection or not according to the position of the vehicle and the position of the branch intersection; if so, inputting an image, obtained in real time, in front of the vehicle into a pre-trained detection model to obtain a candidate flow guide region; inputting the candidate flow guide regions into a pre-trained post-processing model to obtain a classification result and key points of the candidate flow guide regions; if the classification result is the flow guide area, fitting a lane line according to the key points of the candidate flow guide area. According to the embodiment, the performance of the lane line recognition and navigation algorithm at the divergence intersection can be optimized, and the user experience of the navigation system is improved.

Description

technical field [0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to methods and devices for identifying divergent intersections. Background technique [0002] As a key point in map navigation, diverging intersections often require AR navigation algorithms to accurately draw lane lines and provide correct guidance. [0003] The existing lane line recognition technology is based on traditional image techniques such as edge detection and parallel line detection. [0004] Existing technical scheme mainly has the following deficiencies: [0005] 1) Based on basic features such as image edge information and artificially set rules, it cannot adapt well to the complex environment in real driving scenes, and is easily disturbed, and the lane line recognition results at divergent intersections are inaccurate. [0006] 2) There is no optimization for divergent intersections, and it is impossible to judge whether it is yaw or n...

AI Technical Summary

Problems solved by technology

[0005] 1) Based on basic features such as image edge information and artificially set rules, it cannot adapt well to the complex environment in real driving scenes, and is easily disturbed, and the lane line recognition results at divergent intersections are inaccurate

[0006] 2) There is no optimization for divergent intersections, and it is impossible to judge whether it is yaw or not, and the guiding effect is not enough

Images