A Bird's Nest Recognition Method for Transmission Lines Based on Statistical Features and Machine Learning
A transmission line and statistical feature technology, applied in the field of electric power technology and computer vision, can solve problems such as easy misjudgment or missed judgment, decreased work efficiency, and failure to meet the needs of smart grids, and achieve the effect of reducing grounding or tripping accidents
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0025] In order to make the technical solution of the present invention clearer, the specific implementation of the present invention will be further described below in conjunction with the accompanying drawings. The flow chart of the implementation plan is as follows: figure 1 shown.
[0026] 1. Train the bird's nest image classifier model, the specific steps are as follows:
[0027] 1) Collect the transmission line images obtained after the inspection, classify according to whether there are bird's nests in the transmission lines in the image, and divide them into training set and test set according to a certain number ratio. It is stipulated that the image without bird's nest (that is, the normal image) is a positive sample, and the image with a bird's nest is a negative sample, such as figure 2 shown. All images are preprocessed, and the images are uniformly scaled to 600×400, and the scaling method is bicubic interpolation, which includes 16 nearest neighbor points. ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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