Back to results
US 2023/0144209 A1Published application
Lane line detection method and related device
AssigneeHuawei Technologies Co., Ltd.
InventorsXinyue CAI, Hang XU, Wei ZHANG, Zhen YANG, Zhenguo LI
Life of this patent
Estimating the term…
Abstract
This disclosure discloses lane line detection methods and devices. In an implementation, features extracted by different layers of the neural network are fused to obtain a fused second feature map, so that the second feature map obtained through fusion processing has a plurality of layers of features. The fused second feature map has a related feature of a low-layer receptive field and a related feature of a high-layer receptive field. Afterwards, an output predicted lane line set is divided into groups, where each predicted lane line in each group has an optimal prediction interval.
Claims20
A lane line detection method, comprising:
- performing feature fusion on first feature maps that are output by different layers of a trained neural network, to obtain a second feature map, wherein input of the trained neural network is a to-be-detected image;
- dividing the second feature map into a plurality of grids;
- obtaining a first confidence level of each of n first grids in the plurality of grids, wherein the first confidence level indicates a first probability that a real lane line in the second feature map passes through the corresponding first grid, and the first probability exceeds a first preset threshold;
- obtaining, by using a trained prediction head model, a first predicted lane line corresponding to each of the n first grids;
- dividing n first predicted lane lines into m groups, wherein m≤n and n≥2, and wherein a first group in the m groups comprises q first predicted lane lines;
- and
- integrating the q first predicted lane lines based on q first confidence levels corresponding to the q first predicted lane lines and q first grids corresponding to the q first predicted lane lines, to obtain a second predicted lane line, wherein the second predicted lane line is output as a detection result for a real lane line in the second feature map, and q≥2.
4 more elements
A lane line detection framework, comprising a neural network, a feature fusion model, a confidence level adjustment model, a prediction head model, and a predicted lane line integration model;
- the neural network is configured to extract a feature from an input to-be-detected image after being trained;
- the feature fusion model is configured to perform feature fusion on first feature maps that are output by different layers of the trained neural network, to obtain a second feature map;
- the confidence level adjustment model is configured to divide the second feature map into a plurality of grids and obtain a first confidence level of each of n first grids in the plurality of grids, wherein the first confidence level indicates a first probability that a real lane line in the second feature map passes through the corresponding first grid, and the first probability exceeds a first preset threshold;
- the prediction head model is configured to obtain, after being trained, a first predicted lane line corresponding to each of the n first grid;
- the predicted lane line integration model is configured to divide n first predicted lane lines into m groups, wherein m≤n and n≥2, and wherein a first group in the m groups comprises q first predicted lane lines;
- and
- the predicted lane line integration model is configured to integrate the q first predicted lane lines based on q first confidence levels corresponding to the q first predicted lane lines and q first grids corresponding to the q first predicted lane lines, to obtain a second predicted lane line, wherein the second predicted lane line is output as a detection result for a real lane line in the second feature map, and q≥2.
4 more elements
A detection device, comprising:
- at least one processor;
- and
- a memory coupled to the at least one processor and storing programming instructions for execution by the detection device to perform operations comprising:
- performing feature fusion on first feature maps that are output by different layers of a trained neural network, to obtain a second feature map, wherein input of the trained neural network is a to-be-detected image;
- dividing the second feature map into a plurality of grids;
- obtaining a first confidence level of each of n first grids in the plurality of grids, wherein the first confidence level indicates a first probability that a real lane line in the second feature map passes through the corresponding first grid, and the first probability exceeds a first preset threshold;
- obtaining, by using a trained prediction head model, a first predicted lane line corresponding to each of the n first grid;
- dividing n first predicted lane lines into m groups, wherein m≤n and n≥2, and wherein a first group in the m groups comprises q first predicted lane lines;
- and
- integrating the q first predicted lane lines based on q first confidence levels corresponding to the q first predicted lane lines and q first grids corresponding to the q first predicted lane lines, to obtain a second predicted lane line, wherein the second predicted lane line is output as a detection result for a real lane line in the second feature map, and q≥2.
7 more elements
Dependencies are inferred from the claim text.