Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Abrasion lane line detection method based on phase consistency Hough transform

A technology of lane line detection and Hough transform, applied in image analysis, instrument, scene recognition, etc., can solve the problems of discontinuous lane markings, uneven color of lane markings, and missed detection.

Pending Publication Date: 2022-04-29
山西省交通科技研发有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, considering that there are problems such as low contrast between the background image and the lane markings, uneven color of the lane markings, and discontinuous lane markings in the worn lane markings, the linear lane markings in the image space are not obvious. Generate missed detection

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
  • Abrasion lane line detection method based on phase consistency Hough transform
  • Abrasion lane line detection method based on phase consistency Hough transform
  • Abrasion lane line detection method based on phase consistency Hough transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] figure 1 It shows a schematic flow chart of a phase-consistent Hough transform wear lane line detection system and its implementation method in the preferred embodiment of the present invention. The example of the present invention develops an edge detection platform, and performs normalized stretching transformation and image grayscale transformation on the image , two-dimensional Fourier transform and phase consistency measurement technology; re-develop the signal enhancement platform, select the filter module through the frequency range of the image content, input the filtered image into the developed lane line extraction platform, and perform Hough transform and Set the local maximum value, and finally output the lane line detection.

[0040] The example of the present invention takes images of long-worn lane lines on the road. In the obtained image, due to the shooting angle, the parallel lane lines in the actual road appear to cross in the image. figure 2 A sche...

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 discloses a worn lane line detection method based on phase consistency Hough transform. According to the method, an edge detection platform, a signal enhancement platform, a lane line extraction platform and the like are built. The edge detection platform forms an edge detection image by processing a shot original image of a lane line through each module; the signal enhancement platform selects a filtering module according to the target distribution of the to-be-detected signal to form a local texture target signal enhancement image; and the lane line extraction platform maps the enhanced image signal to a Hough space by using a Hough transformation method, adjusts and sets a local threshold value, detects straight line information of the lane line, and an output platform displays a detection and identification interface of the worn lane line. According to the method, the insensitivity of a phase consistency method to light brightness and the robustness of Hough transformation to straight line detection are adopted, automatic identification of the worn lane line under low contrast is realized in combination with a filtering enhancement method, and the technical problems that in an existing lane line detection technology, contour extraction is incomplete, and the identification accuracy is greatly influenced by light are solved.

Description

technical field [0001] The invention belongs to the technical field of image recognition, in particular to a method for detecting worn lane markings based on phase-consistent Hough transform, which utilizes phase features of worn lane marking images to extract line element information of weak lane marking signals under low contrast, In the case of obtaining as much edge information as possible of the lane markings, the lane markings are detected using the robustness of the Hough transform to straight line detection. Background technique [0002] The detection and recognition of lane markings is one of the key technologies in automatic driving and vehicle-road coordination technology. Accurate recognition of lane markings can ensure more accurate and safer warnings such as lane assistance, lane departure, and lane change. However, the lane markings will be worn after years of vehicle rolling and rain and snow erosion, and the wear of the road near the lane markings will cause...

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): G06V20/58G06V10/75G06K9/62G06T7/13
CPCG06T7/13
Inventor 周丽军孙贝周晓旭吴宏涛刘博孟颖薛春明段英杰岳鹏程牛秉青谢昊良
Owner 山西省交通科技研发有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products