A Crack Detection Method for Underwater Dam Based on Local and Global Clustering
A detection method and clustering technology, applied in the field of visual inspection, can solve the problems of high cost, time-consuming and labor-intensive, etc., and achieve the effect of improving accuracy and meeting the requirements of non-destructive testing and real-time performance
Active Publication Date: 2022-04-26
HOHAI UNIV CHANGZHOU
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the deficiencies in the prior art, the purpose of the present invention is to provide a method for detecting cracks in underwater dams based on local and global clustering, which is used to realize the automatic detection of cracks on the surface of dams below the water level, which can overcome the traditional artificial visual The shortcomings of time-consuming, labor-intensive and high cost of detection technology can realize non-destructive testing and meet the requirements of accuracy and real-time
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
[0028] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.
[0029] The invention has the characteristics of low cost, quickness and convenience, and meets the non-destructive, accuracy and real-time requirements of dam detection. Local clustering is combined with global clustering; gray-scale intensity features are combined with geometric features, gray-scale intensity features use mean and standard deviation, and geometric features use circularity, area, and slenderness ratio; second-level threshold segmentation is automatically realized.
[0030] Firstly, the image blocks without crack features are removed through local feature analysis; then the gray intensity of the image is equalized to realize adaptive secondary threshold segmentation; finally, the interference with the same features as cracks is furt...
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 crack detection method of an underwater dam based on local and global clustering, which comprises the following steps: collecting surface images of underwater dams and transmitting them to an image database; preprocessing the images, and preliminarily balancing the background light of the images , to enhance the target area; after processing the image and equalizing the gray intensity of the image, the binary threshold segmentation method is used to realize image binarization; the feature of the image block is extracted, and the two-dimensional feature space is calculated by the cluster analysis method to obtain the image block containing cracks ; Extract all connected domains, take each connected domain as a sample, extract its features respectively, form a three-dimensional feature space, and detect cracks through cluster analysis method again; locate the image containing cracks to the dam, so that Identify areas of the image that contain cracks. The invention realizes the automatic detection of cracks on the surface of the dam below the water level, saves time and labor, has low cost, can realize non-destructive detection, and meets the requirements of accuracy and real-time performance.
Description
technical field [0001] The invention relates to an underwater dam crack detection method based on local and global clustering, and belongs to the technical field of visual detection. Background technique [0002] The research method of underwater dam crack detection technology based on computer vision has become a research hotspot and one of the future development directions because of its intuition, safety, efficiency and universality. The traditional identification of dam cracks is underwater visual inspection. This method has two main defects: first, the detection results are subjective; second, the efficiency is low, the time required is long, and the cost is high. Moreover, this method requires underwater work, which will cause injury to the operator's body, and there is a great risk. [0003] The automatic detection system for underwater dam cracks based on computer vision mainly includes two parts, hardware system and software system. The hardware system part is the...
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): G06V10/762G06V10/44G06V10/50G06V20/10
CPCG06V20/176G06V10/50G06V10/44G06F18/23213
Inventor 范新南吴晶晶史朋飞张学武倪建军罗成名
Owner HOHAI UNIV CHANGZHOU