Sample set construction method applied to training line foreign matter target detection model
A technology for target detection and construction methods, applied in character and pattern recognition, instrument, scene recognition, etc., can solve the problem of low accuracy of target detection models, and achieve the effect of improving the level of intelligence and accuracy.
Pending Publication Date: 2021-04-13
STATE GRID HEILONGJIANG ELECTRIC POWER CO LTD ELECTRIC POWER RES INST +1
View PDF9 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to solve the problem of low accuracy of the target detection model used in the existing automatic inspection mode for power grid lines. The present invention provides a sample set construction method applied to the training line foreign object target detection model
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
[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0031] It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.
[0032] For details, see figure 1 To illustrate this embodiment, the method for constructing a sample set for training a line foreign object target detection model described in this embodiment includes the following steps:
[0033] Step 1. UAV line inspection operation, inspection according to th...
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 sample set construction method applied to training a line foreign matter target detection model, and belongs to the field of image data enhancement. According to the invention, the problem of low accuracy of the target detection model used in the existing automatic inspection mode of the power grid line is solved. The method comprises the following steps: step 1, carrying out line patrol operation by an unmanned aerial vehicle, carrying out patrol inspection according to a preset route, automatically shooting an image in real time, and uploading the image to a remote terminal; step 2, enabling the remote terminal to preprocess the images transmitted by the unmanned aerial vehicle in real time to obtain N preprocessed images, wherein the preprocessed images serve as a sample set; and step 3, carrying out data expansion on the N preprocessed images by using an image enhancement method, so that the number of sample sets is expanded to 7N, and the expanded sample sets are used for training the line foreign matter target detection model, thereby realizing the construction of the sample set of the line foreign matter target detection model. The method is mainly used for training the line foreign matter target detection model by using the constructed sample set.
Description
technical field [0001] The invention relates to the field of detection of foreign objects on power grid lines, and specifically belongs to the field of image data enhancement. Background technique [0002] Bird nests often appear on electrical equipment such as lines, poles and towers. Bird nests are a hidden danger to the safe operation of the power grid. Birds moving on lines and equipment are likely to cause damage to transmission lines. Branches and dry grass in bird nests fall on live parts of lines or insulators It is easy to cause line faults and cause power outages, especially in severe weather such as wind, rain, and lightning. The risk of short-circuit faults is high. The bird's nest on the line equipment poses a threat to the insulation of the power grid. The interruption of power supply caused by short-circuit faults brings inconvenience to people's production and life and even causes major economic losses. The power outage in commercial blocks and industrial par...
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): G06K9/00G06K9/62G06K9/54
CPCG06V20/13G06V10/20G06V2201/07G06F18/214
Inventor 祖光鑫武国良王东梅贺兴于洋李维建
Owner STATE GRID HEILONGJIANG ELECTRIC POWER CO LTD ELECTRIC POWER RES INST