A light strip center sub-pixel extraction method based on the uniqueness of the cross-sectional energy distribution of a light strip
A technology of light strip section energy and light strip center, which is applied in image enhancement, image analysis, image data processing, etc., can solve the problem that the extraction accuracy and robustness cannot meet the requirements of forging measurement, and achieve the effect of accurate extraction
Inactive Publication Date: 2018-12-18
DALIAN UNIV OF TECH
View PDF5 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, aiming at the influence of interference factors such as high temperature and strong radiation, random vibration, dust, etc. of the on-site characteristic light strip during the processing of large forgings, resulting in the extraction accuracy of the existing light strip center extraction method and robustness cannot meet the requirements of on-site measurement of forgings
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
specific Embodiment approach
[0026] Usually in actual use, common line lasers generally use low-power LD laser tubes with different levels of power such as 5mW, 10mW, 60mW, 100mW, and 150mW as light sources. The laser power required by the present invention needs to be greater than 1000mw to meet the image acquisition requirements of hot forgings. Therefore, in order to increase the output power of semiconductor lasers, laser line array technology is usually used to group multiple low-power LD laser light sources and modulate them by combining beams. It is a large spot with Gaussian distribution.
[0027] The laser used in this embodiment is composed of two semiconductor light sources that are divided into two groups of unit lights and then composed of two beams to combine light. The Gaussian distribution is formed by the superposition of the two light fields, and then the point light source is scattered in the form of prism scattering. The fan forms a laser line. Due to the different interference states...
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
A light strip center sub-pixel extraction method based on the uniqueness of the cross-sectional energy distribution of a light strip belongs to that field of computer vision detection and image detection, and relate to a method for extracting the center of laser light strip in a binocular vision measurement system under high-temperature thermal radiation environment. The method firstly preprocesses the image containing the characteristic light stripe, Then the multi-order Gaussian model is used to describe the gray-scale distribution of laser beam cross-section, and the k-order Gaussian modelis used to fit the characteristic points of the initial beam cross-section distribution, and the coordinates of the center points of each beam cross-section are extracted by using the invariance of the beam cross-section distribution law. The method takes advantage of the uniqueness of the cross-sectional energy distribution of light strips. The expected value of a multi-order Gaussian function isused as the criterion of stripe center extraction. The precision and robustness of the method are verified by experiments of extracting the feature light strip center of different types of hot forgings. The sub-pixel extraction of the strip cross-section center is realized quickly and precisely.
Description
technical field [0001] The invention belongs to the field of computer vision detection and image detection, and particularly relates to a method for extracting a sub-pixel in the center of a laser light bar in a binocular vision measurement system used in a high-temperature thermal radiation environment. Background technique [0002] As a non-contact measurement method with strong real-time performance and high measurement accuracy, binocular vision measurement is widely used in many fields such as industrial inspection and target recognition, especially in real-time measurement of thermal geometric dimensions in the forging process of large forgings. The advantages. Many scholars have carried out a lot of research on how to obtain high-precision measurement results. However, these research works mainly focus on improving the calibration accuracy of the camera system and the matching accuracy of feature points, and have also done related research work on the extraction accur...
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): G06T7/00G06T5/00G06T5/20G06K9/46
CPCG06T5/20G06T7/0004G06T2207/20032G06T2207/20024G06T2207/30164G06V10/443G06T5/70
Inventor 贾振元刘阳刘巍张仁伟张洋马建伟
Owner DALIAN UNIV OF TECH