Heterogeneous image fusion detection method for power inspection of unmanned aerial vehicle
A technology of power inspection and image fusion, applied in the field of visual inspection, to improve reliability and real-time performance, avoid the influence of subjective factors and condition restrictions of manual inspection, and overcome unreliable diagnosis results
Active Publication Date: 2019-08-06
HOHAI UNIV CHANGZHOU
View PDF3 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
It can get a good detection effect on the internal heating abnormality of the high-voltage line, but it is not sensitive to fault types such as cable damage, and cannot detect external defects and abnormalities of the cable.
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
specific Embodiment approach
[0048] Around the content of the invention, the specific embodiments of the present invention are as follows:
[0049] Such as figure 1 As shown, a heterogeneous image fusion detection method for unmanned aerial vehicle power inspection, including the following steps
[0050] (1) Install an optical imaging camera for collecting visible light images and a thermal infrared imaging camera for collecting thermal infrared images on the UAV for power inspection, and collect visible light images and images from different angles during the flight of the UAV. thermal infrared image;
[0051] (2) Extract the abnormal features of power inspection from visible light images and thermal infrared images and build a feature knowledge base of various fault types;
[0052]Constructing the feature knowledge base of various fault types refers to: for visible light images, select the Hu invariant moment feature of the fault target segmented in the image; for thermal infrared images, select the 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 heterogeneous image fusion detection method for power inspection of an unmanned aerial vehicle, and the method comprises the following steps: firstly, installing an optical imaging camera and a thermal infrared imaging camera on the unmanned aerial vehicle for power inspection, and collecting visible light images and thermal infrared images at different angles; (2) extracting power inspection abnormal characteristics from the visible light image and the thermal infrared image, and constructing a characteristic knowledge base of various fault types; (3) extracting a fault target from the visible light imageS and the thermal infrared imageS collected in the flight process of the unmanned aerial vehicle, and constructing basic credibility distribution functions by combining a characteristic knowledge base; and (4) fusing the obtained heterogeneous image evidences for the same fault target, fusing the heterogeneous image evidences at different angles, and settinga fusion weight by using comprehensive credibility. The defect that the diagnosis result is not reliable due to the fact that a single visible light image and a single thermal infrared image are usedis overcome.
Description
technical field [0001] The invention belongs to the field of visual detection, and is an application of image processing and recognition technology, in particular a heterogeneous image fusion detection method for unmanned aerial vehicle power patrol inspection. Background technique [0002] In the power supply operation of the power system, the most common faults are high-voltage transmission line faults, including cable damage, insulator faults, casing rupture, tower collapse, suspended foreign matter faults, and bird damage faults. Timely and effective detection of faults and abnormalities of high-voltage transmission lines is crucial to the safe operation of power systems. Manual inspection is the most extensive line inspection method for electric power inspection at this stage, but this method is not only time-consuming and labor-intensive, but also has low efficiency. The environment of transmission lines is complex, and there are many places that are not suitable for ...
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): G06T5/50
CPCG06T5/50G06T2207/10004G06T2207/10048G06T2207/20221
Inventor 史朋飞辛元雪范新南倪建军张学武田斌汪杰钱靖瑜张君怡
Owner HOHAI UNIV CHANGZHOU