Power tower image exposure abnormity correction method based on improved MDIN network
A power tower and correction method technology, applied in the field of deep learning, can solve the problems of large lag time and high efficiency of intelligent inspection, achieve high processing efficiency, convenient calculation, and reduce the effect of operation and maintenance time lag
Pending Publication Date: 2022-07-29
CHINA JILIANG UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] This part aims to summarize the implementation of the present invention to realize the automatic correction method for the abnormal exposure of power tower images. In order to reduce the problems of large lag time caused by the existing low-quality photo processing scheme, the purpose of this application is to provide a method based on the improved MDIN The method for correcting abnormal exposure of images of power poles and towers in the network uses deep learning methods to optimize the MDIN network model and builds an improved MDIN network model for correcting image exposure abnormalities, which realizes real-time correction and output of abnormally exposed images , so that the time lag problem caused by the re-shooting scheme is improved, and the efficiency of intelligent inspection is higher
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] In order to make the objectives, technical solutions and advantages of the present invention clearer, the embodiments of the present invention are further described in detail below.
[0033] The specific embodiment of the present invention and its implementation process are as follows:
[0034] like figure 1 As shown, the method includes the following steps:
[0035] Step 1: Acquire images of power towers and create a power tower image dataset with abnormal exposure;
[0036] Collect several images of power towers with normal lighting in different locations and different weathers, convert the collected images from RGB space to HSV space, and perform Gamma transformation on the V channel in the HSV space to obtain a new V' channel, while maintaining the HSV space. In addition, the two channels of H channel and S channel remain unchanged, and convert back to RGB space to obtain the abnormally exposed power tower image; the abnormally exposed power tower image and its co...
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
Login to View More Abstract
The invention discloses an electric power tower image exposure abnormity correction method based on an improved MDIN network. The method comprises the following steps: creating a power tower image data set with abnormal exposure, preprocessing images, and building an improved MDIN network model; a targeted loss function is established, and training is carried out by taking minimization as a target; and inputting a to-be-processed power tower image with abnormal exposure into the trained improved MDIN network model, and outputting to obtain a corrected power tower image. According to the method, automatic correction of the overexposure or underexposure electric power inspection tower photo is realized, the problem of operation and maintenance time delay of re-shooting can be reduced, the processing efficiency is high, calculation is convenient, and more efficient and intelligent operation of electric power inspection can be realized.
Description
technical field [0001] The invention relates to an image exposure optimization processing method in the technical field of deep learning, in particular to a method for correcting abnormal exposure of power tower images based on an improved MDIN network. Background technique [0002] In order to ensure the normal operation of my country's expanding transmission lines, the current method of intelligent inspection based on drones has accounted for most of the power in the operation and maintenance inspection of transmission lines. Compared with the traditional manual inspection method, UAV intelligent inspection is more efficient and safer, and it can also better meet the current requirements for intelligent inspection and lean management. [0003] During the intelligent inspection process of the UAV, the detailed images and videos of each part of the power tower can be efficiently, safely and comprehensively captured in the harsh environment where the transmission line is loca...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06T7/00G06T7/90G06V20/17G06N3/04G06N3/08
CPCG06T7/0004G06T7/90G06N3/08G06V20/17G06T2207/10024G06T2207/20084G06T2207/20081G06N3/048G06N3/045G06T5/90
Inventor 章苗郑恩辉
Owner CHINA JILIANG UNIV