Transformer substation picture bird nest detection method combining ResNet50 + FPN + DCN

A detection method and substation technology, applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve problems such as hidden safety hazards, time-consuming and labor-consuming, and achieve high accuracy, improve detection results, and good robustness Effect

Pending Publication Date: 2020-08-25
ZHEJIANG UNIV +1
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] A large number of equipment in the substation are deployed outdoors, which are easily affected by foreign bird nests and cause safety hazards
The tradi

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
  • Transformer substation picture bird nest detection method combining ResNet50 + FPN + DCN
  • Transformer substation picture bird nest detection method combining ResNet50 + FPN + DCN
  • Transformer substation picture bird nest detection method combining ResNet50 + FPN + DCN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0040] The embodiment and implementation process thereof implemented according to the complete method of the content of the present invention are as follows:

[0041] First of all, build the substation bird's nest image library, the typical picture of the picture is as follows figure 1 shown. Second, establish labels corresponding to the image dataset. The label file meets the xml label file standard in Pascal VOC format, and the content includes the image name, image path, image height and width, and the coordinate values ​​of the upper left vertex and lower right vertex of the real target frame.

[0042] Establish a deep learning network model, and build a deep learning target detection network based on the ResNet50 framework + FPN + DCN and Faster RCNN target detection algorithm.

[0043] The network structure of the Faster R-CN...

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 transformer substation picture bird nest detection method in combination with ResNet50 + FPN + DCN. The method comprises: collecting a transformer substation bird nest samplepicture and adding a label; establishing a deep learning network model by combining the ResNet50 network framework model and the Faster R-CNN detection network model with the FPN feature pyramid network model and the DCN deformable convolution kernel; randomly dividing into a training set and a test set; after data of the training set is enhanced, training a deep learning network model of a Faster RCNN + ResNet50 + FPN + DCN network structure, then using test set test adjustment, inputting a solidified bird nest detection model for an image to be detected, and outputting and obtaining a detection result. The method can achieve the automatic detection of the bird nest of the transformer substation, is higher in accuracy, is good in stability, is high in anti-interference capability, is high in universality, is good in robustness, and can be used for an intelligent robot inspection system of the transformer substation.

Description

technical field [0001] The invention relates to a method for detecting a bird's nest in a substation, in particular to a method for detecting a bird's nest in a substation picture combined with ResNet50+FPN+DCN. Background technique [0002] A large number of equipment in substations are deployed outdoors, which are easily affected by foreign bird nests and cause potential safety hazards. The traditional manual inspection method is time-consuming and labor-intensive on the one hand, and has high requirements on the inspection personnel on the other hand. Therefore, if the inspection robot can be used to automatically detect the bird's nest in the substation environment, it is of great significance for the realization of intelligent inspection. Using deep learning methods to automatically detect inspection images captured by inspection robots is also one of the problems that needs to be solved urgently. Contents of the invention [0003] In order to solve the problems in ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/176G06N3/045G06F18/214
Inventor 齐冬莲王逸舟闫云凤季瑞松张建良郑伊
Owner ZHEJIANG UNIV
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