Concrete member surface quality detection method based on computer vision
A computer vision and surface quality technology, applied in the field of computer vision, to achieve the effect of improving detection efficiency, improving the level of manufacturing automation production, and overcoming inconsistent detection results
Pending Publication Date: 2019-11-05
TONGJI UNIV
View PDF8 Cites 9 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The main purpose of the present invention is to provide a method for detecting the surface quality of concrete components based on computer vision, to overcome manual detection of defects, and to identify and classify defect types through support vector machines (SVM), so as to improve the factory-manufacturing automation of concrete prefabricated components Level
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
[0060] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0061] see Figure 4 , the inventive method comprises the following steps:
[0062] Image acquisition; image reading; histogram equalization to enhance contrast; image grayscale conversion, binarized image segmentation, image morphology processing, eight-neighborhood area growth, the number of pixels in the connected domain area is less than the set value, surface quality Qualified; otherwise, feature extraction; defect identification and classification; judge whether the surface quality is qualified according to the defect type and defect area.
[0063] Specifically, including:
[0064] (1) if figure 1 As shown, the camera ① is installed on the end effector ③ of the robot, and it moves with the robot ②, and detects while working, which can well meet the requirements of automated production.
[0065] (2) if figure 2 with image 3 As shown, the ma...
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 provides a concrete member surface quality detection method based on computer vision. The method comprises the following steps: (1) arranging a camera to ensure that the camera can capture the surface of a concrete member to be detected; (2) carrying out image preprocessing on the surface of the concrete building prefabricated part; (3) removing the minimum area by adopting a regiongrowing method; (4) carrying out surface defect feature extraction; and (5) judging whether the surface quality of the concrete member is qualified or not based on the concrete member surface defect classification of the support vector machine. The method has the advantages that the problems of non-uniform detection results and high false detection rate caused by traditional human eye detection are solved. The detection time is reduced. The efficiency is improved. Compared with binocular vision detection and multi-vision detection, monocular vision detection adopted by the invention has the characteristics of convenience, high efficiency and low cost. Considering that precast concrete components are produced in batches, an SVM (Support Vector Machine) is adopted to identify and classify defect types. Therefore, the requirement of automatic production can be met.
Description
technical field [0001] The invention belongs to the technical field of computer vision and relates to a method for detecting the surface quality of concrete components based on computer vision. Background technique [0002] During the manufacturing process of precast concrete components, due to the influence of raw materials, processing technology, manual or robot operation, etc., some surface defects, such as holes and protrusions, will inevitably appear on the surface, which will affect the strength of concrete components to a certain extent and appearance. Therefore, it is required that the detection system of precast concrete components on the production line can quickly and accurately detect surface defects, especially the defects of holes. Ultrasonic, infrared and other detection technologies are mainly used in the detection of surface defects of medicine boards, leather, ceramic tiles and other products, but their detection speed is slow and the accuracy is low. [...
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 IPC IPC(8): G06T7/00G06T5/00G06T5/30G06T5/40G06K9/38G06K9/62G01N21/95G01N21/88
CPCG06T7/0004G06T5/30G06T5/40G01N21/95G01N21/8851G06T2207/30132G01N2021/8887G01N2021/8883G01N2021/8854G01N2021/8864G06V10/28G06F18/2411G06T5/70
Inventor 樊留群杨远时朱鸿志王红亚
Owner TONGJI UNIV