Image detection method, device and system for unmanned aerial vehicle image

An image detection and UAV technology, applied in the field of UAV images, can solve the problems of high cost of satellite remote sensing, long image processing time, and great influence of weather, etc., and achieve fast mapping speed, strong flexibility and reality, Applicable effects

Active Publication Date: 2020-02-28
HEFEI SIWILL INTELLIGENT +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Conventional satellite remote sensing for urban planning and natural resource management is costly, has poor real-time performance, is greatly affected by weather, and takes a long time to process images

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
  • Image detection method, device and system for unmanned aerial vehicle image
  • Image detection method, device and system for unmanned aerial vehicle image
  • Image detection method, device and system for unmanned aerial vehicle image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] refer to figure 1 , a kind of image detection method for drone image that the present invention proposes, comprises the following steps:

[0034] S1. An image detection model is set. The input of the image detection model is an image, and the output is an initial detection frame detection result of the image.

[0035] Specifically, in this embodiment, an image detection model is trained based on images manually marked with detection frames. In this embodiment, during manual labeling, an attribute is marked corresponding to each detection frame, and the attribute is specifically the category or name of the transaction in the detection frame in the image.

[0036] In a specific embodiment, it is assumed that the sample images are manually marked, and there are stones, trees, etc. in multiple sample images; the image detection model obtained by training according to the sample images can detect other images in the form of frames Automatically mark stones and trees in 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 provides an image detection method for an unmanned aerial vehicle image, and the method comprises the steps: obtaining a current to-be-detected image in the unmanned aerial vehicle image, and obtaining an initial detection frame detection result of the current to-be-detected image through an image detection model; obtaining a reference image of the current detection image from pre-stored manual detection images, and obtaining a detection frame detection result of the reference image; obtaining a missing detection frame according to the detection frame detection result and the initial detection frame detection result, and obtaining a missing detection frame detection result; obtaining a final detection result of the current to-be-detected image according to the initial detection box detection result and the missing detection box detection result; and performing comparative analysis on the final detection result of the current to-be-detected image and the detection result of the initial detection frame, and correcting the image detection model according to the analysis result. The unmanned aerial vehicle image is utilized, the image recognition and processing technologyis combined, high-precision detection for the image is achieved, and the accuracy of image recognition can be further improved.

Description

technical field [0001] The present invention relates to the technical field of drone images, in particular to an image detection method, device and system for drone images. Background technique [0002] With the rapid development of the economy and the expansion of the scope of human activities, land use and fine management are facing problems such as scattered construction layout, extensive land occupation, inconsistency between planning and construction, and degradation of cultural features. For the construction of new countryside, etc., there is an urgent need to formulate refined spatial planning and implement real-time and precise control of the construction process. [0003] Conventional satellite remote sensing for urban planning and natural resource management is costly, poor in real-time performance, greatly affected by weather, and takes a long time to process images. Utilizing UAV remote sensing technology, it has the advantages of low cost, simple and convenient...

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): G06K9/00G06K9/46
CPCG06V20/10G06V20/13G06V10/462Y02T10/40
Inventor 王秋阳周勇赵瑜盛恩菊杜强史淑芬
Owner HEFEI SIWILL INTELLIGENT
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap