Unmanned aerial vehicle aerial image target detection method and system based on deep learning

A target detection and deep learning technology, applied in the fields of computer vision and image processing, can solve problems such as low efficiency and achieve the effect of improving detection accuracy

Pending Publication Date: 2021-01-29
山东捷讯通信技术有限公司
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the detection methods used at this stage are manual interpretation, that is, artificially query aerial images
Although manual detection can reduce the workload of on-site inspections, it is still inefficient to completely use manual interpretation for a large number of aerial pictures or videos taken by drones

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
  • Unmanned aerial vehicle aerial image target detection method and system based on deep learning
  • Unmanned aerial vehicle aerial image target detection method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040]Such asfigure 1 As shown, the present disclosure provides a method for detecting drone aerial image targets based on deep learning, including: acquiring multiple types of target images and drone images;

[0041]Preprocess the target image, and divide the preprocessed target image into a training set and a verification set;

[0042]Establishing a target detection network, the target detection network is used to extract feature maps of the target image, fuse the feature maps to obtain a fusion feature map, and perform model training according to the fusion feature map;

[0043]Input the target image of the training set into the target detection network for training to obtain a trained target detection model;

[0044]Input the target image of the verification set into the trained target detection model for verification, and obtain multiple classification detection target recognition models;

[0045]Input the images taken by the drone into multiple types of detection target recognition models to...

Embodiment 2

[0080]A UAV aerial image target detection system based on deep learning, including:

[0081]The data acquisition module is configured to: acquire various types of target images and images taken by drones;

[0082]The preprocessing module is configured to: preprocess the target image, and divide the preprocessed target image into a training set and a verification set;

[0083]The target detection network establishment module is configured to: establish a target detection network, the target detection network is used to extract a feature map of the target image, fuse the feature maps to obtain a fused feature map, and perform model training according to the fused feature map;

[0084]The training module is configured to: input the target image of the training set into the target detection network for training to obtain a trained target detection model; input the target image of the validation set into the trained target detection model for verification, and obtain more Recognition model for each ...

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 unmanned aerial vehicle aerial image target detection method and system based on deep learning. The method comprises the steps of obtaining multiple types of target images and shot images of an unmanned aerial vehicle; preprocessing the target image, and dividing the preprocessed target image into a training set and a verification set; inputting the target image of the training set into a target detection network for training to obtain a trained target detection model; inputting the target image of the verification set into a trained target detection model for verification, and obtaining a plurality of types of detection target recognition models; inputting the shot image of the unmanned aerial vehicle into a plurality of category detection target recognition models to obtain a detection result; through feature recognition of multiple target types, realizing recognition and troubleshooting of multiple types of detection targets; the problem of insufficient data volume of part of types of detection targets is solved.

Description

Technical field[0001]The present disclosure relates to the field of computer vision and image processing, and mainly relates to a method for detecting drone aerial image targets based on deep learning.Background technique[0002]The statements in this section merely mention background technologies related to the present disclosure, and do not necessarily constitute prior art.[0003]The use of drone aerial photography provides a more convenient and effective management method for many application fields. Among them, target detection, that is, detecting image targets with certain characteristics from drone aerial pictures is the most widely used application. However, most of the detection methods adopted at this stage are manual interpretation, that is, to query aerial images manually. Although manual detection can reduce the workload of on-site inspections, it is still inefficient to use manual interpretation for massive amounts of UAV aerial photos or videos.[0004]With the continuous 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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V20/13G06N3/047G06N3/045G06F18/23G06F18/2415G06F18/241
Inventor 谷永辉刘昌军
Owner 山东捷讯通信技术有限公司
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