Target robust detection and defect identification method and device for nuts and pins of power grid
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A defect recognition, nut technology, used in character and pattern recognition, image data processing, instrumentation, etc.
Pending Publication Date: 2019-12-20
NANJING NARI GROUP CORP +3
View PDF5 Cites 15 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] In view of the deficiencies in the above existing technologies, the present invention provides a method and device for robust detection and defect identification of electric grid nuts and pins. Using the method of deep learning target detection, small fittings with complex backgrounds can be quickly identified from pictures (pins and nuts), timely detection and prediction of problematic small fittings
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0042] Such as figure 1 As shown in FIG. 1 , it is a flowchart of a target robust detection and defect identification method for grid nuts and pins proposed by the present invention.
[0043] refer to figure 1 , a target robust detection and defect identification method for grid nuts and pins, comprising the following steps:
[0044] Step 101, collect and filter out the target picture set through the image collection module;
[0045] Step 102, mark and store the target picture set;
[0046] Step 103, constructing a deep learning model to form a training model;
[0047] Step 104, detect and recognize the augmented picture according to the training model.
[0048] In step 101, the collection and screening of the target picture set through the image collection module specifically includes: using a combination of unmanned aerial vehicle and camera device to take pictures of the grid nuts and pins on the transmission line, and collect pictures The images are screened to obtain...
Embodiment 2
[0102] Based on the same inventive concept as the target robust detection and defect identification method for grid nuts and pins in the foregoing embodiments, the present invention also provides a target robust detection and defect identification device for grid nuts and pins.
[0103] see image 3 , a target robust detection and defect identification device for grid nuts and pins, comprising:
[0104] The image collection module 201 collects and screens out the target picture set;
[0105] Annotation storage module 202, annotating and storing the target picture set;
[0106] Training module 203, constructing a deep learning model to form a training model;
[0107] The detection and recognition module 204 detects and recognizes the augmented picture according to the training model.
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 target robust detection and defect identification method for the nuts and pins of a power grid. The method comprises the following steps of acquiring and screening a target picture set through an image acquisition module; labeling and storing the target picture set; constructing a deep learning model to form a training model; and detecting and identifying an augmented picture according to the training model. The invention further provides a target robust detection and defect recognition device for the nuts and pins of the power grid. At the training stage of a detection model, a deep neural network model training technology when the strabismus nut and pin samples are few is studied, and the automatic detection and defect identification of the robust strabismus with insufficient and unbalanced nut and pin samples are realized by utilizing a strabismus training data augmentation method based on perspective transformation.
Description
technical field [0001] The invention relates to the technical field of computer vision recognition, in particular to a method and device for robust detection and defect recognition of grid nuts and pins. Background technique [0002] China's geographical environment is relatively complex and its climate varies greatly. Many transmission lines are installed in harsh environments, such as lakes and forests. Ensuring the safety and stability of transmission lines is a very important content and a prerequisite for the safe and intelligent construction of power grids. Pins and nuts play a non-negligible auxiliary role in the line. In the transmission line, the main function of the pin and nut is to fix large fittings, such as clamps, anti-vibration hammers, pressure equalizing rings, and connecting fittings. Due to the complex environment, the pins and nuts are prone to rust, drop, and damage, which in turn affects the stable operation and work of the above large hardware. Th...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.