Isolating switch icing thickness image identification method based on mathematical morphology

Abstract

The invention discloses a mathematical morphology-based isolation switch icing thickness image identification method, relates to an isolation switch icing thickness image identification method, and solves the problem of poor precision when an existing edge detection method is used for identifying an isolation switch icing thickness image. The method comprises the following steps: acquiring an ice-coated isolation switch image; carrying out image preprocessing on the ice-coated isolating switch image to generate a gray-scale enhanced image; performing edge extraction on the grayscale enhanced image by using mathematical morphology to obtain an edge image; performing edge selection on the edge image to obtain an ice-coated isolation switch extraction image; and comparing and calculating the obtained original edge data of the uniced isolation switch with the extracted image of the iced isolation switch, and calculating the icing thickness of the isolation switch. The beneficial effect is that the icing thickness of the isolation switch can be accurately obtained.

Description

Technical Field

[0001] The invention relates to an image recognition method for ice coating thickness of an isolating switch. Background Art

[0002] In the process of processing and analyzing the ice-covered image of the disconnector, the edge detection method is currently generally used. The edge detection method uses a first-order edge detection operator (Sobel operator or Prewitt operator) and a second-order edge detection operator (Canny operator) for edge detection. The first-order edge detection operator has low sensitivity and can avoid interference from the background environment, but its output edge detection result is intermittent and has serious graininess; the second-order edge detection operator has high sensitivity, but has high requirements on the quality of the original image. If the original image is poor, the output line edge will appear obviously deformed or broken; therefore, the existing edge detection method has poor accuracy when identifying the ice thickness image of the disconnector. Summary of the invention

[0003] The purpose of the present invention is to solve the problem of poor accuracy of the existing edge detection method in identifying the ice thickness image of the disconnector, and proposes a method for identifying the ice thickness image of the disconnector based on mathematical morphology.

[0004] The present invention discloses a method for identifying ice thickness of disconnectors based on mathematical morphology, comprising the following steps:

[0005] The isolating switch ice thickness image recognition method comprises the following steps:

[0006] Step 1: obtaining original edge data of the disconnector switch without ice through the monitoring system; the original edge data includes the diameter d1 of the disconnector switch when it is not covered with ice and the number of pixels x1 of the disconnector switch when it is not covered with ice;

[0007] Step 2: Obtain an image of the ice-covered isolation switch through a monitoring system;

[0008] Step 3: performing image preprocessing on the ice-covered isolation switch image obtained in step 2 to generate a grayscale enhanced image;

[0009] Step 4: Use mathematical morphology to extract the edge of the grayscale enhanced image generated in step 3 to obtain an edge image;

[0010] Step 5: performing edge selection on the edge image obtained in step 4 to obtain an extracted image of the ice-covered isolating switch;

[0011] Step 6: Compare and calculate the ice thickness of the disconnector by using the original edge data of the un-iced disconnector obtained in step 5 and the extracted image of the iced disconnector obtained in step 4;

[0012] The specific formula for the comparison calculation is:

[0013]

[0014] Among them, H is the ice thickness of the disconnector, d1 is the diameter of the disconnector when it is not covered with ice; d2 is the diameter of the disconnector when it is covered with ice; x1 is the number of pixels when the disconnector is not covered with ice; x2 is the number of pixels when the disconnector is covered with ice.

[0015] Preferably, the image preprocessing in step 3 includes image rotation, image grayscale and grayscale image enhancement;

[0016] The image rotation refers to rotating the length direction of the ice-covered isolation switch image to the horizontal direction.

[0017] Preferably, the process of graying the image is: using a floating point algorithm to convert the ice-covered isolation switch image that has undergone image rotation into a grayscale image.

[0018] Preferably, the grayscale image enhancement process is: enhancing the grayscale image using histogram equalization to obtain a grayscale enhanced image.

[0019] Preferably, the specific steps of obtaining the edge image in step 4 are:

[0020] The mathematical morphology method is used to detect the edge of the disconnector. Eight groups of structures are defined. The weights corresponding to each group of structures are calculated and the structures are inserted into the grayscale enhanced image. The grayscale enhanced image is threshold segmented by the iterative optimal threshold segmentation method. The image after threshold segmentation is then inverted. Finally, the edge image is output by the corrosion algorithm.

[0021] Preferably, the specific steps of obtaining the extracted image of the ice-covered isolating switch in step 5 are:

[0022] The position information of the disconnector is extracted by the straight line detection method, and the ice-covered disconnector extraction image is obtained by fitting the angle bisector method.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The present invention proposes an image recognition method for ice thickness of isolating switches based on mathematical morphology. For the target iced isolating switch image taken by the monitoring system, the extracted boundaries are fused using mathematical morphology to obtain the number of pixels when the isolating switch is iced. By importing the diameter of the un-iced isolating switch and the number of pixels of the un-iced isolating switch for comparative calculation, the ice thickness of the isolating switch can be accurately obtained, thereby achieving the purpose of improving the accuracy of ice thickness image detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1This is a flow chart of a method for image recognition of ice thickness of disconnectors based on mathematical morphology as described in the first specific implementation mode;

[0026] Figure 2 This is a grayscale enhanced image effect diagram generated in the fourth specific implementation mode;

[0027] Figure 3 This is the edge image effect diagram obtained in the fifth specific implementation manner. DETAILED DESCRIPTION

[0028] Specific implementation method 1. Combination Figure 1 This embodiment describes a method for image recognition of ice thickness of an isolating switch based on mathematical morphology, and the method for image recognition of ice thickness of an isolating switch comprises the following steps:

[0029] Step 1: obtaining original edge data of the disconnector switch without ice through the monitoring system; the original edge data includes the diameter d1 of the disconnector switch when it is not covered with ice and the number of pixels x1 of the disconnector switch when it is not covered with ice;

[0030] Step 2: Obtain an image of the ice-covered isolation switch through a monitoring system;

[0031] Step 3: performing image preprocessing on the ice-covered isolation switch image obtained in step 2 to generate a grayscale enhanced image;

[0032] Step 4: Use mathematical morphology to extract the edge of the grayscale enhanced image generated in step 3 to obtain an edge image;

[0033] Step 5: performing edge selection on the edge image obtained in step 4 to obtain an extracted image of the ice-covered isolating switch;

[0034] Step 6: Compare and calculate the ice thickness of the disconnector by using the original edge data of the un-iced disconnector obtained in step 5 and the extracted image of the iced disconnector obtained in step 4;

[0035] The specific formula for the comparison calculation is:

[0036]

[0037] Among them, H is the ice thickness of the disconnector, d1 is the diameter of the disconnector when it is not covered with ice; d2 is the diameter of the disconnector when it is covered with ice; x1 is the number of pixels when the disconnector is not covered with ice; x2 is the number of pixels when the disconnector is covered with ice.

[0038] In this embodiment, the image of the ice-covered isolating switch obtained in step one is captured by a monitoring system; the extracted image of the ice-covered isolating switch obtained in step four is the number of pixels when the isolating switch is covered with ice; the original edge data of the un-iced isolating switch in step five includes the diameter of the isolating switch when it is not covered with ice and the number of pixels when the isolating switch is not covered with ice; after obtaining the boundary of the ice-covered isolating switch by pixel-level fusion of the boundary of the isolating switch, and obtaining the coordinates of the pixel points at the edge of the line, the relevant data of the isolating switch when it is not covered with ice is read, and the ice thickness of the isolating switch is calculated according to the proportional relationship of the corresponding pixel points to judge the current status of the ice covering the isolating switch.

[0039] Specific implementation method 2: This implementation method further defines the image recognition method of ice thickness of disconnector based on mathematical morphology described in specific implementation method 1. In this implementation method, the image preprocessing in step 2 includes image rotation, image graying and graying image enhancement;

[0040] The image rotation refers to rotating the length direction of the ice-covered isolation switch image to the horizontal direction.

[0041] In this embodiment, the isolating switch is a cylindrical structure, and the length direction of the ice-covered isolating switch image is the central axis direction of the ice-covered isolating switch; the ice-covered isolating switch image obtained in step three is successively subjected to image rotation, image grayscale and grayscale image enhancement, so that the processed grayscale enhanced image has an overall grayscale distribution more uniform than the original image, thereby achieving the purpose of image enhancement and improving the accuracy of ice thickness image detection.

[0042] Specific implementation method three: This implementation method further limits the image recognition method of ice thickness of isolating switches based on mathematical morphology described in specific implementation method two. In this implementation method, the image grayscale process is: using a floating point algorithm to convert the ice-covered isolating switch image that has undergone image rotation into a grayscale image.

[0043] Specific implementation method 4. Combination Figure 2 To explain this embodiment, this embodiment further limits the image recognition method for ice thickness of isolating switches based on mathematical morphology described in Specific Embodiment 3. In this embodiment, the process of grayscale image enhancement is: enhancing the grayscale image using histogram equalization to obtain a grayscale enhanced image.

[0044] In this embodiment, histogram equalization is used to increase the global contrast of the ice-covered isolation switch image, especially when the contour contrast of the ice-covered isolation switch image is quite close. Through this method, the brightness can be better distributed on the histogram; this can be used to enhance the local contrast without affecting the overall contrast. The histogram equalization realizes the grayscale enhancement function by effectively expanding the commonly used brightness; the image is preprocessed by python programming, and the grayscale enhanced image of the ice-covered isolation switch image is obtained as shown in FIG. Figure 2 Shown

[0045] Specific implementation method V. Combination Figure 3 This embodiment is described. This embodiment further limits the image recognition method for ice thickness of disconnectors based on mathematical morphology described in the first embodiment. In this embodiment, the specific steps of obtaining the edge image in step 4 are as follows:

[0046] The mathematical morphology method is used to detect the edge of the disconnector. Eight groups of structures are defined. The weights corresponding to each group of structures are calculated and the structures are inserted into the grayscale enhanced image. The grayscale enhanced image is threshold segmented by the iterative optimal threshold segmentation method. The image after threshold segmentation is then inverted. Finally, the edge image is output by the corrosion algorithm.

[0047] In this embodiment, the edge of the disconnector is first detected using a mathematical morphology method, and eight groups of structures are defined, wherein the eight groups of structures include two lengths and four phase angles; the two lengths are 3 mm and 5 mm, respectively; the four phase angles are 0°, 45°, 90° and 135°, respectively. Then, the weight corresponding to each group of structures is calculated and the structures are inserted into the grayscale enhanced image. The grayscale enhanced image is threshold segmented by an iterative optimal threshold segmentation method, and then the image after threshold segmentation is inverted. Finally, the edge image is output by a corrosion algorithm; the edge detection is performed on the preprocessed image by a mathematical morphology method, and the output result is as follows: Figure 3 as shown.

[0048] Specific implementation method 6: This implementation method further limits the ice thickness image recognition method of the disconnector based on mathematical morphology described in specific implementation method 1. In this implementation method, the specific steps of obtaining the ice-covered disconnector extraction image in step 5 are:

[0049] The position information of the disconnector is extracted by the straight line detection method, and the ice-covered disconnector extraction image is obtained by fitting the angle bisector method.

[0050] In this embodiment, the method extracts the outline of the isolating switch from its environmental background through edge selection before fusing the images; since the edge detection result of the isolating switch is an edge contour line composed of straight lines, and the edge detection result of the interference background in its environment is usually a curve, the position information of the isolating switch is extracted by the straight line detection method, and the extraction of the ice-covered isolating switch is achieved by fitting the angle bisector method.

[0051] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for identifying ice thickness of disconnector based on mathematical morphology, characterized in that: The isolating switch ice thickness image recognition method comprises the following steps: Step 1: obtaining original edge data of the disconnector switch without ice through the monitoring system; the original edge data includes the diameter d1 of the disconnector switch when it is not covered with ice and the number of pixels x1 of the disconnector switch when it is not covered with ice; Step 2: Obtain an image of the ice-covered isolation switch through a monitoring system; Step 3: performing image preprocessing on the ice-covered isolation switch image obtained in step 2 to generate a grayscale enhanced image; Step 4: Use mathematical morphology to extract the edge of the grayscale enhanced image generated in step 3 to obtain an edge image; Step 5: performing edge selection on the edge image obtained in step 4 to obtain an extracted image of the ice-covered isolating switch; Step 6: Compare and calculate the ice thickness of the disconnector by using the original edge data of the un-iced disconnector obtained in step 5 and the extracted image of the iced disconnector obtained in step 4; The specific formula for the comparison calculation is: Among them, H is the ice thickness of the disconnector, d1 is the diameter of the disconnector when it is not covered with ice; d2 is the diameter of the disconnector when it is covered with ice; x1 is the number of pixels when the disconnector is not covered with ice; x2 is the number of pixels when the disconnector is covered with ice.

2. According to the method for image recognition of ice thickness of disconnector based on mathematical morphology in claim 1, it is characterized in that: The image preprocessing in step 3 includes image rotation, image grayscale and grayscale image enhancement; The image rotation refers to rotating the length direction of the ice-covered isolation switch image to the horizontal direction.

3. The method for image recognition of ice thickness of disconnector based on mathematical morphology according to claim 2 is characterized in that: The process of graying the image is as follows: using a floating point algorithm to convert the ice-covered isolation switch image that has undergone image rotation into a grayscale image.

4. The method for image recognition of ice thickness of disconnector based on mathematical morphology according to claim 3 is characterized in that: The grayscale image enhancement process is: enhancing the grayscale image by using histogram equalization to obtain a grayscale enhanced image.

5. The method for image recognition of ice thickness of disconnector based on mathematical morphology according to claim 1 is characterized in that: The specific steps to obtain the edge image in step 4 are: The mathematical morphology method is used to detect the edge of the disconnector. Eight groups of structures are defined. The weights corresponding to each group of structures are calculated and the structures are inserted into the grayscale enhanced image. The grayscale enhanced image is threshold segmented by the iterative optimal threshold segmentation method. The image after threshold segmentation is then inverted. Finally, the edge image is output by the corrosion algorithm.

6. The method for identifying ice thickness of disconnector based on mathematical morphology according to claim 1 is characterized in that: The specific steps for obtaining the extracted image of the ice-covered isolating switch in step 5 are as follows: The position information of the disconnector is extracted by the straight line detection method, and the ice-covered disconnector extraction image is obtained by fitting the angle bisector method.

Images