Low-altitude aerial image power line foreign object detection method based on light convolutional neural network

A convolutional neural network and foreign object detection technology, applied in the field of deep learning, can solve problems such as the limited effect of target recognition methods, achieve the effect of ensuring real-time performance and improving detection efficiency

Active Publication Date: 2022-07-12
BEIJING UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Considering the increasing number of power line inspection images and the limited effect of traditional target recognition methods, this invention proposes a method for detecting foreign objects on power lines in aerial images based on multi-scale convolutional neural networks.

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
  • Low-altitude aerial image power line foreign object detection method based on light convolutional neural network
  • Low-altitude aerial image power line foreign object detection method based on light convolutional neural network
  • Low-altitude aerial image power line foreign object detection method based on light convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] According to the above description, the following is a specific implementation process, but the scope of protection of this patent is not limited to this implementation process.

[0022] Step 1: Construction of a power line foreign object detection model based on convolutional neural network

[0023] Step 1.1: Construction of Powerline Detection Model Based on Lightweight Convolutional Neural Network

[0024] The existing deep learning target detection models have a wide range of application scenarios and can often detect thousands of objects, such as YOLO9000, which can detect 9418 categories. In the power line inspection scenario, the types of targets are extremely limited, mainly power lines, balloons and kites. In this model, only power lines need to be identified, and their features are very limited. The existing deep learning target detection models are too specific for power line scenarios. Over-redundancy, while the lightweight model is effective in this case, ...

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 detection method of power line foreign objects in low-altitude aerial imagery based on light convolutional neural network belongs to the field of computer vision. A real-time detection method for power line foreign objects in UAV aerial imagery is studied. First, a light-weight power line detection model is constructed by using convolutional neural network, and the depth features of power lines in aerial images are calculated. Then, a multi-target power line foreign body detection model is constructed by using convolutional neural network. Finally, the video frames without power lines are filtered by the power line detection model, and the multi-target power line foreign object detection model is used to realize real-time power line foreign object detection in low-altitude aerial images on the video with detected power lines.

Description

technical field [0001] Based on the deep learning technology, the present invention studies a real-time detection method for foreign objects in power lines in aerial photography images of unmanned aerial vehicles. First, a light-weight power line detection model is constructed by using convolutional neural network, and the depth features of power lines in aerial images are calculated. Then, a multi-target power line foreign body detection model is constructed by using convolutional neural network. Finally, the power line detection model is used to filter the video frames without power lines, and the multi-target power line foreign object detection model is used to realize real-time power line foreign object detection in low-altitude aerial images on the video with power lines detected. The invention belongs to the field of computer vision, and specifically relates to technologies such as deep learning and target detection. Background technique [0002] With the development ...

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 Patents(China)
IPC IPC(8): G06V20/17G06N3/04G06N3/08
CPCG06N3/08G06V20/13G06N3/045Y04S10/50
Inventor 张菁王立元卓力梁西李昱钊
Owner BEIJING UNIV OF TECH
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