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

Rare earth mining high-resolution image recognition and positioning method

A technology of image recognition and positioning method, applied in scene recognition, neural learning method, character and pattern recognition, etc., can solve the problem of low positioning accuracy

Inactive Publication Date: 2021-06-25
JIANGXI UNIV OF SCI & TECH
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The one-stage detection algorithm is superior to the two-stage detection algorithm in detection speed, but the positioning accuracy is lower than the two-stage detection algorithm

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
  • Rare earth mining high-resolution image recognition and positioning method
  • Rare earth mining high-resolution image recognition and positioning method
  • Rare earth mining high-resolution image recognition and positioning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Such as figure 1 As shown, a rare earth mining high-resolution image recognition and positioning method of the present invention includes the following steps,

[0040] Step S1: Acquisition and preprocessing of remote sensing image data. After obtaining the remote sensing image data, perform radiation correction, geometric correction and image fusion preprocessing, and then export it as an RGB three-channel image. Finally, crop the image and eliminate the image that does not contain the detection target. part;

[0041] Step S2: Establish the YOLOv3 model, first determine the network structure of the YOLOv3 algorithm, and then determine the loss function in the YOLOv3 algorithm. The loss function includes the first part of target positioning loss, the second part of target confidence loss, and the last part of target classification loss ;

[0042] Step S3: YOLOv3 algorithm adjustment, when the prediction box and the real box do not intersect, use CIOU Loss to replace th...

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 relates to the technical field of rare earth mining, in particular to a rare earth mining high-resolution image recognition and positioning method, which comprises the following steps of S1, collecting and preprocessing remote sensing image data; S2, establishing a YOLOv3 model; S3, performing YOLOv3 algorithm adjustment; and S4, outputting a result by the model, and marking pixel position information including the prediction bounding box, namely pixel coordinate information relative to the left upper corner of the image, on the remote sensing image in a point form. After the method is adopted, a YOLOv3 target detection algorithm is improved, and an attention mechanism is embedded into a feature extraction network, so that a gradient with an attention effect can flow into a deeper network, and the key feature extraction capability is improved on the premise of not influencing the detection speed; Meanwhile, faster and more stable convergence of the model is realized by improving a loss function.

Description

technical field [0001] The invention relates to the technical field of rare earth mining, in particular to a high-resolution image recognition and positioning method for rare earth mining. Background technique [0002] The southern ion-adsorption rare earth mining area is one of the most important mining areas for rare earth resource mining in my country. Rare earth mining areas involve a wide range and are mostly located in remote mountainous areas. Common monitoring methods are inefficient and time-sensitive. [0003] Field survey is the basis of rare earth mining monitoring. The existing monitoring methods for rare earth mining mainly include ground survey, satellite remote sensing monitoring and UAV remote sensing monitoring. High-spatial-resolution images can more clearly express the spatial structure and surface texture characteristics of ground objects, and can distinguish the finer components inside the ground objects. And satellite remote sensing monitoring has li...

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): G06K9/00G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08G06T7/73G06T5/00G06T5/50
CPCG06T5/50G06T7/73G06N3/08G06T2207/10032G06T2207/20132G06T2207/30181G06T2207/20221G06V20/176G06V20/13G06V10/267G06V10/56G06V2201/07G06N3/045G06F18/23213G06F18/24323G06T5/80
Inventor 李恒凯肖松松王利娟武镇邦
Owner JIANGXI UNIV OF SCI & 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