A Corrosion Defect Segmentation Method for Tower Cranes
A tower crane and defect technology, applied in the directions of image analysis, image enhancement, instruments, etc., can solve the problems of a lot of manpower, financial resources, and difficulty in ensuring the comprehensiveness and accuracy of detection, so as to avoid false detection and remove interference factors. , the effect of improving the detection accuracy
Active Publication Date: 2022-05-24
FUZHOU UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The existing regular maintenance methods of tower cranes mainly rely on manual inspection, which not only has subjective influence, but also consumes a lot of manpower and financial resources, and it is difficult to guarantee the comprehensiveness and accuracy of inspection
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
[0038] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0039] Please refer to figure 1 , the present invention provides a kind of rust defect segmentation method of tower crane, comprises the following steps:
[0040] Step S1: collecting a tower crane rust defect image, and expanding through data enhancement to obtain an image data set;
[0041] In this embodiment, a total of 1484 images are obtained through drone inspection, photographing, and online collection, including images of different illumination, brightness, and angles, which are universal. Then, the data set is expanded through data enhancement, such as increasing brightness, reducing brightness, mirror flipping, random translation, etc. In the end, a total of 7420 data sets are obtained, and LabelMe is used to mark the rusted target, and then the training and testing are divided in the ratio of 8:2. data set. The data augmentation results are a...
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 present invention relates to a method for segmenting corrosion defects of tower cranes, comprising the following steps: step S1: collecting images of corrosion defects of tower cranes, and obtaining image data sets through data enhancement and expansion; step S2: preprocessing the image data sets , obtain the preprocessed image data set; step S3: based on YOLO V3, introduce the channel attention mechanism SENet, improve the residual module, and build an improved YOLO V3 model; step S4: train and improve YOLO V3 according to the preprocessed image data set Model; step S5: input the image to be tested into the improved YOLO V3 model after training for detection, and judge whether there is a corrosion defect in the tower crane; step S6: when judging that there is a corrosion defect in the tower crane, use the threshold segmentation method to Rust areas are segmented from other areas in the image. The invention can effectively detect and segment the corrosion area of the tower crane, is feasible, and is convenient for checking out the hidden danger of corrosion defects of the tower crane.
Description
technical field [0001] The invention relates to the field of image segmentation, in particular to a method for segmenting corrosion defects of tower cranes. Background technique [0002] Tower cranes are large-scale equipment frequently used in construction sites. They are exposed to the natural environment for a long time and are affected by harsh environments such as wind and sun. The steel structure of tower cranes is prone to oxidation corrosion, that is, rust, which will affect Its strength and stiffness, when the corrosion is too serious, will reduce the working performance of the tower crane, resulting in collapse accidents, resulting in serious casualties. According to statistics, between 2012 and 2014, there were 162 tower crane accidents, of which collapse and fracture accidents accounted for 123, accounting for about 75.93% of the total accidents. The degree of corrosion of tower cranes, such as corrosion area, corrosion rate, etc., is an important indicator 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 Patents(China)
IPC IPC(8): G06T7/00G06T5/00G06T5/40G06T7/136
CPCG06T7/0004G06T7/136G06T5/40G06T2207/10004G06T5/70
Inventor 陈国栋王翠瑜
Owner FUZHOU UNIV