A lane line detection algorithm based on an instance segmentation neural network framework

Abstract

The invention discloses a lane line detection algorithm based on an instance segmentation neural network framework. The method comprises the following steps: firstly, establishing an instance segmentation model for lane line detection, wherein the instance segmentation model comprises a binary segmentation module branch and an embedded module branch; loading the original image information into a binary segmentation module branch, and segmenting lane line pixels from background pixels; Loading the original image information into an embedding module branch to obtain a pixel embedding vector of alane line; Then clustering the lane line pixels and the pixel embedding vectors; Transforming the original image by using a transformation matrix network module, outputting a projection transformation matrix of the aerial view, and projecting lane line pixels into the aerial view through the projection transformation matrix; and finally, performing lane line fitting on the pixel points projectedinto the aerial view, and outputting a lane line fitting result. According to the method, the calculated amount is reduced, and meanwhile the influence of environment change on the lane line detectioneffect is eliminated.

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, in particular to a lane line detection algorithm based on an instance segmentation neural network framework. Background technique [0002] Lane line detection is the basis of assisted driving and driverless driving. The effect of lane line detection will directly affect the realization of subsequent functions such as lane line keeping, lane changing, and overtaking. The basic idea of ​​lane line detection is to collect the current lane information through the sensor, analyze the image feature information of the lane line, such as color, edge, width, etc., segment and extract the road, and detect the passable area in the lane line and the surrounding environment area. . The current existing lane line detection hardware schemes are divided into two categories according to the number of sensors used: single sensor and multi-sensor. plus camera) two. Among these sensor solutions...

AI Technical Summary

Problems solved by technology

Generally, the perspective transformation matrix used in deep learning is fixed and has good applicability when the lane line is flat. However, when the scene changes, such as going up and down, the original perspective matrix cannot be accurately calculated. Projecting lane line pixels to the bird's-eye view will cause robustness problems in the next step of lane line fitting

Images