Unlock instant, AI-driven research and patent intelligence for your innovation.

Lane line detection method based on image sequence

A technology of lane line detection and image sequence, which is applied in the field of computer vision, can solve the problems that the lane line detection method cannot handle the short-term occlusion of lane lines, the ground light and dark transformation, etc., and achieve the effect of convenient structure optimization

Pending Publication Date: 2021-08-13
ZHEJIANG UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve complex practical application scenarios such as short-term occlusion of lane lines and ground light-dark transformation that cannot be handled well by existing lane line detection methods, the present invention provides a lane line detection method based on image sequences, and the specific steps are as follows:

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Lane line detection method based on image sequence
  • Lane line detection method based on image sequence
  • Lane line detection method based on image sequence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be described in detail below in conjunction with the embodiments and accompanying drawings, but the present invention is not limited thereto.

[0048]The computer hardware configuration that the inventive method selects operation is Intel (R) Xeon (R) E5-2678CPU@2.50GHz, and GPU is GeForce GTX TITAN Xp, and display memory is 12GB, and internal memory is 16GB; Software environment is the Ubuntu 16.04 system of 64, And implemented based on PyTorch0.4.1. The detection indicators of the lane line detection model mainly include: Accuracy, Precision, Recall, F1-Measure and FPS.

[0049] Such as figure 1 As shown, an image-based lane line detection method includes the following four parts:

[0050] (1) Build a lane line parallel detection neural network:

[0051] (2) Training optimization of lane line detection neural network;

[0052] (3) Complete the training of the neural network;

[0053] (4) Use the trained neural network to detect the inpu...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a lane line detection method based on an image sequence. The lane line detection method comprises the following four parts: (1) building a lane line parallel detection network; (2) training and optimizing the lane line parallel detection network; (3) completing the training of the lane line parallel detection network; and (4) detecting an input image by using the trained lane line parallel detection network, and outputting a lane line segmentation image. Compared with the existing semantic segmentation network using the same skeleton network, the parallel network provided by the invention is obviously improved in objective detection precision and subjective detection effect.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a lane line detection method based on image sequences. Background technique [0002] Lane line detection is an important part of the realization of fully automatic driving and advanced assisted driving. It can effectively detect the vehicle's passable area, which is of great significance to the vehicle's environmental perception ability and lane keeping system. Although there are some commercial lane line detection applications, they are still limited by some special scenarios and cannot fully meet the strict requirements of autonomous driving. Big room for improvement. [0003] Early lane line detection methods mainly consider the feature differences of pixels in their domain space by mining different low-level visual features of images, such as color, edge, gradient, etc. Otsuka et al. (see Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rap...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/46G06V20/49G06V20/588G06N3/044G06F18/253Y02T10/40
Inventor 朱威欧全林洪力栋何德峰郑雅羽
Owner ZHEJIANG UNIV OF TECH