Supercharge Your Innovation With Domain-Expert AI Agents!

Sun shadow displacement positioning method based on deep learning

A positioning method, deep learning technology, applied in the field of positioning

Inactive Publication Date: 2019-12-20
ZHEJIANG UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem in the prior art of effectively extracting the shooting location of pictures without external hardware such as GPS, and propose a sun shadow displacement positioning method based on deep learning, combined with deep learning technology and computer three-dimensional reconstruction technology , the mathematical modeling method solves the above problems, and completes the work of locating the shooting location in the picture

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
  • Sun shadow displacement positioning method based on deep learning
  • Sun shadow displacement positioning method based on deep learning
  • Sun shadow displacement positioning method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] refer to figure 1 , figure 2 , image 3 , Figure 4 with Figure 5 , the present invention comprises the steps of:

[0045] Step 1: Use the image adaptive grayscale segmentation method to segment the image to be positioned, and segment the image into shadow areas, object areas, and other areas;

[0046] Step 2: Use convolutional neural network image detection technology to detect the specific positions of shadows and objects, and obtain effective pixel end data of shadows;

[0047] Step 3: Establish a mathematical model and use the fish swarm algorithm to solve the entire problem.

[0048] Specifically, the image adaptive grayscale segmentation method in the step 1 includes the following steps:

[0049] Step 11: Set a random segmentation threshold T, and the segmentation results R of the three test points;

[0050] Step 12: Follow the formula The image is segmented to obtain a segmented image G=CUT(P,T), where p(i,j) is the original image, and g(i,j) is the se...

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 sun shadow displacement positioning method based on deep learning, and the method comprises the following steps of 1, segmenting an image to be positioned through employing an image adaptive gray segmentation method, and segmenting the image into a shadow region, an object region and other regions; 2, detecting the specific positions of the shadow and the object by usinga convolutional neural network image detection technology to obtain the effective pixel end data of the shadow; and 3, establishing a mathematical model and solving the whole problem by using a fish swarm algorithm. By combining a deep learning technology, a computer three-dimensional reconstruction technology and a mathematical modeling method, the shooting place of a photo can be effectively extracted by the effective information in the photo on the basis of not using the hardware devices, such as a GPS, etc.

Description

【Technical field】 [0001] The present invention relates to the technical field of positioning methods, in particular to the technical field of a sun shadow displacement positioning method based on deep learning. 【Background technique】 [0002] Since the rise of the Internet, pictures have played an increasingly important role in media and information dissemination. People also increasingly expect to get accurate and effective information from simple pictures. The pictures taken by electronic devices such as mobile phones generally have a GPS field, which means that people can locate the shooting location of the picture according to the GPS field in the picture. The existence of such additional bit fields provides a lot of convenience to human life: for example, when collecting and sorting pictures, pictures can also be classified according to location, and when searching pictures, a large number of candidate pictures can be excluded according to geographical factors, improvi...

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): G06T7/11G06T7/136G06T7/60G06N3/00G06N3/08G01C21/02
CPCG01C21/025G06N3/006G06N3/084G06T7/11G06T7/136G06T7/60G06T2207/20081G06T2207/20084
Inventor 王万良臧泽林童川吴菲
Owner ZHEJIANG UNIV OF TECH
Features
  • R&D
  • 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