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

Vehicle lane departure visual detection method based on deep neural network

A deep neural network and lane departure technology, applied in the field of assisted driving, can solve the problems of large network model parameters, inability to apply real scenes, slow detection speed, etc., and achieve strong robustness, low cost, and fast speed Effect

Inactive Publication Date: 2020-10-23
ZHEJIANG UNIV OF TECH
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The network model parameters used by the algorithm are large, the detection speed is slow, and it cannot be applied to real scenarios

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
  • Vehicle lane departure visual detection method based on deep neural network
  • Vehicle lane departure visual detection method based on deep neural network
  • Vehicle lane departure visual detection method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with the accompanying drawings.

[0028] refer to Figure 1 to Figure 10 , a vehicle lane departure visual detection method based on a deep neural network, comprising the following steps:

[0029] (1) The network structure of the lane segmentation network is as follows: figure 1 As shown, it consists of an encoder and a decoder. The encoding part includes 4 Encoders E1, E2, E3, and E4. Each Encoder consists of several convolution, pooling, and BN (BatchNorm) layers. The decoding part includes two branches. The upper right branch consists of two Decoders D1 and D2, which are used to obtain the probability map of the lane line segmentation results, such as figure 2 A lane line shown corresponds to a probability map. The lower right branch P1 is a classification network consisting of several layers of convolution and a fully connected layer, which is used to judge whether there is a lane line in the l...

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 vehicle lane departure visual detection method based on a deep neural network. The vehicle lane departure visual detection method comprises the following steps: (1) positioning and segmenting the position of a lane line by using a lane line segmentation algorithm; (2) cutting out lane lines segmented from the graph, and classifying the lane lines by using a classificationalgorithm; (3) compressing the neural network model; and (4) calibrating a vehicle-mounted instrument camera. According to the vehicle lane departure detection method based on the deep neural network, lane line semantic segmentation recognition and coordinate system view angle conversion algorithms based on the deep neural network are combined, and the vehicle lane departure detection method is deployed on an automobile data recorder and is low in cost and high in robustness. According to the vehicle lane departure visual detection method, the lightweight ERFnet-SAD network is adopted, and corresponding pruning quantitative compression is carried out on the model, and the speed is high while the precision is guaranteed.

Description

technical field [0001] The invention relates to the field of assisted driving of vehicles, in particular to real-time semantic segmentation and recognition of real-time lane lines, and early warning of vehicle departure. Background technique [0002] Vehicle safety assisted driving is an important research direction in the field of intelligent transportation. Many companies and research institutions at home and abroad are doing research on related technologies, including vehicle lane departure warning technology. According to statistics from the traffic department, 50% of traffic accidents are caused by vehicles deviating from normal driving tracks. When the vehicle is running at high speed for a long time, the driver is prone to inattention, which can easily cause the vehicle to deviate from the normal lane, thereby causing traffic accidents. Therefore, developing a vehicle lane departure detection method and actively reminding the driver of safe driving is an effective m...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/08G06T7/80
CPCG06T7/80G06N3/08G06T2207/20081G06T2207/20084G06V20/588G06F18/24
Inventor 郭东岩夏亮明崔滢张梦蝶
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com