A method for calculating the threshold value of transmission line mountain fire monitoring based on cloud transformation
A transmission line and cloud transformation technology, applied in computing, image data processing, instruments, etc., can solve problems such as large amount of calculation, formation of multiple valleys, roughness, etc., achieve good segmentation effect, improve accuracy, and clear thinking
Active Publication Date: 2018-07-17
STATE GRID HUNAN ELECTRIC POWER +2
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Among them, the bimodal method requires the gray level histogram of the image to show an obvious bimodal shape, but the actual histogram is discrete, often very rough and uneven, and may form multiple valleys; gray threshold segmentation The selection of the threshold is mostly based on experience, and it is difficult to determine the complex wildfire environment; the maximum between-class variance method is suitable for dealing with situations where the contrast between the target and the background is large and the background is not very complicated; the maximum entropy threshold method can be used for non-ideal bimodal histograms. Image segmentation is a widely used image segmentation method at present.
However, this method has a lot of calculations when determining the threshold, and it is difficult to meet the requirements of wildfire monitoring in terms of real-time performance, and the efficiency is relatively low
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
[0020] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0021] A method for calculating the threshold value of mountain fire monitoring on transmission lines based on cloud transformation, such as figure 1 As shown, the specific implementation steps are:
[0022] Step 1: Acquire the thermal infrared image of the transmission line mountain fire video surveillance, obtain the transmission line mountain fire video surveillance thermal infrared image by sampling, and use the median filter method for distortion correction and noise suppression. The calculation formula of median filter is:
[0023] f(x,y)=med{g(x-i,y-j),(i,j∈W)}
[0024] In the formula, g(x, y) and f(x, y) are the gray value of the pixel at position (x, y) of the original image and the processed image respectively, and W is a two-dimensional area module, which is taken in this embodiment 3*3 area.
[0025] Step 2: Normalize the gray level of t...
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 a cloud transformation based power transmission line forest fire monitoring threshold calculation method, which is characterized in that qualitative features of grayscale probability distribution of an infrared image are extracted by using a peak value method based cloud transformation method on the basis of an image grayscale histogram, and a potential optimal threshold of thermal infrared image segmentation is acquired; and an optimal threshold is acquired through calculating an entropy function value of the image under the potential threshold so as to recognize a forest fire region in the image, and the accuracy of power transmission line forest fire monitoring is effectively improved. The method disclosed by the invention takes a cloud model as a theoretical basis, can automatically generate a series of basic concepts represented by the cloud model according to actual conditions of grayscale distribution of the thermal infrared image, acquires the optimal threshold for forest fire region recognition through calculating the entropy function value, and realizes effective search for the infrared image grayscale histogram. The method disclosed by the invention is clear in thinking, convenient to operate and high in practicability, can effectively recognize a forest fire region in the image, and has good segmentation effects for a multi-peak histogram.
Description
technical field [0001] The invention belongs to the technical field of electric power engineering, and in particular relates to a method for calculating a mountain fire monitoring threshold of a power transmission line based on cloud transformation. Background technique [0002] Most of the overhead transmission lines in my country are located in the mountains and mountains. Especially in recent years, with the continuous expansion of the grid scale, the towers of ±800kV and above cross-regional UHV lines are mostly located in remote mountainous areas. Due to the topography and climatic conditions, it is very easy to cause wildfires and cause tripping accidents of transmission lines. In order to realize the effective monitoring of mountain fires on transmission lines, the State Grid Corporation has adopted a variety of methods, including meteorological satellite remote sensing, installing smoke and fire detection devices at fixed locations, and sending forest rangers to cond...
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 Patents(China)
IPC IPC(8): G06T7/00
CPCG06T7/0002G06T2207/10048G06T2207/30232
Inventor 陆佳政章国勇李波谭艳军方针熊蔚立刘毓
Owner STATE GRID HUNAN ELECTRIC POWER