Visual metal rust spot detecting device and method adopting optimal spectral band selecting
A visual detection device and optimal spectrum technology, applied in the field of visual detection, can solve the problems of limited detection accuracy of metal rust spots and limited number of channels, and achieve the goal of improving the accuracy and precision of visual detection, strong versatility, and rich visual feature information Effect
Inactive Publication Date: 2015-12-02
HARBIN UNIV OF SCI & TECH
View PDF3 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the number of channels of ordinary visual imaging devices is limited, which limits the detection accuracy of metal rust spots, and in the complex environment of industrial sites, the gray-scale mutation characteristics are seriously affected by factors such as ambient light, the shape and posture of metal workpieces, and it is difficult to detect metal corrosion. Make an accurate assessment
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
[0055] Below in conjunction with accompanying drawing, and take the steel workpiece with rust attached to the surface as an example to further describe the present invention in detail:
[0056] Three semiconductor lasers with dominant wavelengths of 405nm, 510nm and 650nm are selected for spectral calibration; the conductor laser is placed at the imaging entrance of the optical and sensing system 10; the relative positions of the semiconductor laser and the semiconductor laser with the optical and sensing system 10 are adjusted to achieve collimation;
[0057] The laser beam with a known wavelength is deflected and reaches the LCOS surface to form a spectral line; adjust the position of the CCD to make the CCD image the LCOS, thereby obtaining the corresponding relationship between the spectral line and the image coordinates;
[0058] Sequentially complete the LCOS coordinate sampling corresponding to three fixed wavelengths of 405nm, 510nm and 650nm; use the known wavelength ...
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 relates to a visual metal rust spot detecting device and method adopting optimal spectral band selecting and belongs to the technical field of visual detection. The detecting device comprises an optics and sensor system, a measurement control system, a computer information processing system and a record display system. The optics and sensor system is composed of a first lens assembly, a transmittance type diffraction grating, a second lens assembly, a silicon-based liquid crystal, a CCD camera and an external shell and used for measuring one-dimensional spectral data and two-dimensional space data information. The detecting method comprises the steps of calibrating spectral lines, searching for the optimal spectral band and dividing an image. By collecting rich three-dimensional data array information and selecting the optimal spectral band, influence on the detecting result from factors such as ambient light, and the shape and the posture of a metal work-piece is reduced, and the visual metal rust spot detecting accuracy and precision are effectively improved.
Description
technical field [0001] The invention relates to a visual detection device and method for selecting the optimal spectral band of metal rust spots, and belongs to the technical field of visual detection. Background technique [0002] The visual detection technology of metal rust spots is widely used in the screening of metal raw materials and product classification in the equipment manufacturing process, and is an important link in the complete process of equipment manufacturing. At present, the visual detection of metal rust spots generally adopts the method of direct post-image processing, and the detection is completed according to the step change of the channel data of the rust spots and the background on the photoelectric sensor, that is, the gray level mutation. However, the number of channels of ordinary visual imaging devices is limited, which limits the detection accuracy of metal rust spots, and in the complex environment of industrial sites, the gray-scale mutation ...
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): G01N21/25
Inventor 赵首博范剑英王洋
Owner HARBIN UNIV OF SCI & TECH