Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Road line detection method based on concatenated convolutional neural network

A technology of convolutional neural network and detection method, which is applied to biological neural network models, neural architectures, instruments, etc., can solve problems affecting the accuracy and reliability of line detection, increase the calculation cost of ADAS system, etc., and reduce the calculation cost Effect

Active Publication Date: 2018-11-16
ZHEJIANG GONGSHANG UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing road line detection methods are based on edge point detection. Usually, the edge points of vehicles and roadside plants and the edge points of real road lines are input into the voting module of Hough transform without distinction, and non-road line objects are introduced False information not only affects the accuracy and reliability of line detection, but also increases the calculation cost of the ADAS system in line 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
  • Road line detection method based on concatenated convolutional neural network
  • Road line detection method based on concatenated convolutional neural network
  • Road line detection method based on concatenated convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The invention provides a method for detecting traces based on a cascaded convolutional neural network. The provided technology takes the image sequence collected by a vehicle-mounted camera as input, and uses a cascaded convolutional neural network to detect trace marker blocks, and uses Hough transform Determine the position of the trace in the image. The cascaded convolutional neural network in the present invention includes a first-level convolutional neural network and a second-level convolutional neural network.

[0033] figure 1 It shows a schematic diagram of line area labeling and training sample extraction, refer to figure 1 , the embodiment of the present invention divides the trace line into image blocks along its extending direction, that is, the trace mark blocks. In the embodiment of the present invention, it is assumed that the road line has a similar width in a local area of ​​the image, and the marking part of the road line approximately occupies the ...

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 road line detection method based on a concatenated convolutional neural network, and relates to the field of image processing. According to the method, road line mark blocksare detected by the concatenated convolutional neural network, and then road lines are determined through a Hough transform algorithm by center position coordinates of all the road line mark blocks detected and obtained by the concatenated convolutional neural network and category label numbers to which the same belong. Compared with road line detection, which takes edge point detection as an algorithm basis, in the prior art, the method can better distinguish edge points of interference objects and the real road lines, prevents false information, which is introduced by non-road-line objects,from impacting accuracy and reliability of road line detection, and reduces calculation costs of an ADAS system in road line detection.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for detecting traces based on a cascaded convolutional neural network. Background technique [0002] With the development of sensor technology and electronic technology, Advanced Driver Assistance System (ADAS) has become an important direction for the development of the automobile industry. In the ADAS system, lane detection is an important basis for applications such as lane departure warning, intelligent cruise control, and front vehicle collision avoidance warning. [0003] In addition to lane markings, various vehicles, shadows cast by vehicles, lane separation guardrails, roadside greening and other objects often appear in the field of view observed by the camera of the ADAS system. The existing road line detection methods are based on edge point detection. Usually, the edge points of vehicles and roadside plants and the edge points of real road lines are input int...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/588G06N3/045G06F18/241G06F18/214
Inventor 陈卫刚
Owner ZHEJIANG GONGSHANG UNIVERSITY
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com