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

Convolutional neural network-based automatic detection method for skyline line in image

A convolutional neural network and automatic detection technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as single usage scenarios, poor anti-interference ability, and inability to accurately detect the skyline

Active Publication Date: 2019-07-26
CENT SOUTH UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a method for automatically detecting the skyline in an image based on a convolutional neural network, which solves the problem that the existing skyline detection method has a single use scene, poor anti-interference ability, and cannot be used in rainy or foggy weather. Accurate detection of skyline problems

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
  • Convolutional neural network-based automatic detection method for skyline line in image
  • Convolutional neural network-based automatic detection method for skyline line in image
  • Convolutional neural network-based automatic detection method for skyline line in image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The present invention will be further described below in conjunction with accompanying drawing and specific embodiment:

[0056] This embodiment is to perform skyline detection on the original field image with rain (fog), and the overall implementation process is as follows figure 1 As shown, the overall network model framework is as follows figure 2 As shown, the automatic detection of the skyline is performed as follows:

[0057] Step A: Extract the dark channel image I of the original image I Dark ;

[0058] Step B: Use the feature extraction network to extract the features F of the original image I R ;

[0059] Step C: The feature F extracted by step B R , using the rain line prediction network to extract the rain line image I Streak ;

[0060] Step D: The rain line image I extracted by step C Streak , use the rain density level classification network to classify the rain density level, and generate the rain density image I according to the rain density lev...

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 convolutional neural network-based automatic detection method for a skyline in an image. The method comprises the following steps of: A, obtaining a dark channel image of anoriginal image I by using an image processing technology; b, fully extracting the feature FR of the original image I by using a Dense network; C, predicting a rain line image by using the convolutional neural network according to the feature FR extracted in the step B; D, classifying the rain density level by using the classification network according to the rain line image extracted in the step C, and carrying out up-sampling to obtain a rain density image; e, splicing the features and images extracted in the steps A-D into a total feature, and then detecting a final skyline by using a convolutional neural network. According to the method, automatic and accurate detection of the skyline under end-to-end and rain (fog) conditions is realized by combining image processing and the deep convolutional neural network.

Description

technical field [0001] The invention belongs to the field of image information processing, in particular to a method for automatic detection of skylines in images based on convolutional neural networks. Background technique [0002] The skyline refers to the dividing line between sky and non-sky areas (such as sky and mountains, sky and ocean, sky and forest) in the image. Skyline detection plays an important role in field positioning, visual navigation, port security, forest fire prevention, desert image marking, and AR (augmented reality), etc. [0003] For example, positioning technology is one of the indispensable technologies for modern national defense and warfare. At present, the positioning methods that people have mastered mainly include satellite positioning, communication base station positioning, WIFI node positioning, and Bluetooth positioning, etc., all of which rely on third-party servers or base stations for auxiliary positioning, instead of only relying on ...

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): G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/44G06N3/045G06F18/214G06F18/2415
Inventor 肖晓明黄余吴志虎郭璠高琰唐琎
Owner CENT SOUTH UNIV
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