CN108344742B - Sapphire inoculation detection device and method based on multi-frame image motion information - Google Patents
Sapphire inoculation detection device and method based on multi-frame image motion information Download PDFInfo
- Publication number
- CN108344742B CN108344742B CN201810333442.6A CN201810333442A CN108344742B CN 108344742 B CN108344742 B CN 108344742B CN 201810333442 A CN201810333442 A CN 201810333442A CN 108344742 B CN108344742 B CN 108344742B
- Authority
- CN
- China
- Prior art keywords
- inoculation
- image
- sapphire
- liquid level
- acquisition module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/87—Investigating jewels
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D3/00—Control of position or direction
- G05D3/12—Control of position or direction using feedback
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8477—Investigating crystals, e.g. liquid crystals
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Crystals, And After-Treatments Of Crystals (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a sapphire inoculation detection device and method based on multi-frame image motion information, which solve the problems that the inoculation critical environment parameters are difficult to measure, the thermal field characteristics of different crystal growth devices are different, and the inoculation critical state environment parameters are different through a multi-frame image feature recognition technology for a sapphire inoculation liquid level. The multi-frame image motion characteristics identified by the invention only appear in the most suitable inoculation environment, the angle and length change characteristics of the key intersection line cluster of the inoculation liquid level can be analyzed, and the method for measuring the most suitable inoculation environment parameters is not used for searching the inoculation point. The invention utilizes the multi-frame image motion information and the image fusion technology to carry out depth analysis on the multi-frame image characteristics of the sapphire inoculation liquid level, predicts the optimal inoculation position of the industrial sapphire, and does not need to detect the related physicochemical characteristics of the optimal inoculation position. The system has good real-time performance and low prediction misjudgment rate.
Description
Technical Field
The invention relates to the field of safety positioning, in particular to a sapphire inoculation detection device and method based on multi-frame image motion information.
Background
Industrial sapphire is mainly colorless sapphire crystals. The sapphire has good physical and chemical properties and is widely applied to scientific and technical research and development. To meet the demand, automatic production has become a development trend of the industrial sapphire industry. The process of preparing sapphire single crystal by using a kyropoulos method, wherein seed crystals contact the liquid level of molten aluminum oxide under the high-temperature condition, and the process of starting the growth of the crystals by slightly pulling and rotating is called inoculation. The cost of raw materials and energy for preparing the industrial sapphire single crystal with large size at one time is about ten-million yuan, and the inoculation level can influence the growth of the crystal and waste all early cost investment, so that the inoculation is a key link in the preparation process of the industrial sapphire and directly influences the production benefit of the sapphire industry.
At present, artificial inoculation is the most common mode, depends on the experience of crystal growers and the attempt of inoculation, has low success rate, and consumes a large amount of manpower and material resources. The yield is improved, the artificial uncontrollable factors are reduced, and the automatic inoculation of important parameter quantification in the inoculation process is realized. However, in the sapphire inoculation process by the kyropoulos method, the temperature in the crucible is over 1800 ℃, the requirement of the inoculation process on the temperature is very strict, and the accurate high-temperature measurement is difficult to realize by the existing temperature control technology, namely the optimum inoculation temperature cannot be quantized. In addition, in the inoculation process of the kyropoulos method, the crucible is externally provided with a symmetrical heating source, the surface of the aluminum oxide in a molten state forms a vortex due to the temperature gradient, and the surface of the liquid level has a slight rolling phenomenon, so that the technical problem is caused for automatic inoculation.
The existing inoculation technology has low automation degree and general inoculation success rate, firstly, the critical environment parameters of inoculation are difficult to measure, and for the sapphire crystal growth furnace adopting the kyropoulos method, the thermal field characteristics of different equipment are different, the zero-boundary state environment parameters for inoculation of different equipment are different, and the unified growth environment parameter standard cannot be established. Secondly, the core idea of the existing sapphire automatic inoculation technology based on machine vision is to only find critical inoculation characteristic points, and not to actively predict the positions of the inoculation points.
Disclosure of Invention
The invention mainly aims to solve the defects of the existing problems and provides a sapphire inoculation detection device and method based on multi-frame image motion information.
The invention adopts the following technical scheme: a sapphire inoculation detection device based on multi-frame image motion information comprises a crucible, a seed rod, a first observation window, a second observation window, a first filtering module, a second filtering module, a first image acquisition module, a second image acquisition module, an image analysis system, a signal transmission system and a control system;
the crucible comprises a crucible body and a crucible cover, wherein the crucible body is used for bearing and heating the sapphire to be inoculated, and the middle part of the crucible cover is provided with a through hole to form a first observation window, a second observation window and a support hole of the seed rod respectively; the first light filtering module and the second light filtering module are respectively arranged in the first observation window and the second observation window, and the first image acquisition module and the second image acquisition module acquire the image characteristics of the sapphire liquid level in the crucible through the first observation window and the second observation window; the image analysis system is connected with the first image acquisition module and the second image acquisition module so as to process images of the first image acquisition module and the second image acquisition module; the control system is connected with the image analysis system and used for controlling the seed rod to move towards the interior of the crucible according to the result of image analysis so as to inoculate the sapphire crystal, and the signal transmission system is respectively connected with the first image acquisition module, the second image acquisition module and the image analysis system so as to control the transmission of signals.
The first observation window, the first filtering module and the first image acquisition module are sequentially connected through matched threaded interfaces.
The first filtering module and the second filtering module are both filters with the wavelength of 0.43-1.6um and are used for providing channels of visible light and partial infrared bands so as to reflect the characteristics of the liquid level of the molten crystal.
The first image acquisition module and the second image acquisition module are formed by sequentially connecting an objective lens, a magnifying lens, an eyepiece and a color industrial CCD.
Wherein the image analysis system comprises:
the receiving unit is connected with the first image acquisition module and the second image acquisition module through a signal transmission system and is used for receiving the sapphire image information in the crucible acquired by the first image acquisition module and the second image acquisition module in real time;
the preprocessing unit is used for carrying out fusion processing on the sapphire images collected by the first image collection module and the second image collection module received by the receiving unit, carrying out noise reduction and enhanced filtering processing on each frame of fused image to obtain a critical inoculation liquid level key intersection line cluster in the fused image, extracting length and included angle fine change characteristics in the image, carrying out Hofman straight line fitting on the liquid level key intersection line cluster, and quantizing length and included angle fine characteristic changes;
and the analysis unit is used for determining the optimal sapphire inoculation position according to the characteristic analysis result of the length and included angle of the fitted straight line cluster in the continuous multi-frame fusion image.
The analysis unit finds that the number of the fitting straight lines of one of the fitting straight lines in the multi-frame fused images tends to be stable, any one fitting straight line does not disappear in less than 3600 frames, at least two adjacent fitting straight lines in the sapphire liquid level key intersection line cluster attract each other, and when the two fitting straight lines are overlapped into one straight line, the best inoculation position is determined to move on an acute angle bisector formed by the two straight lines;
and (3) if the length of the fitting straight line in the key intersection line cluster of the liquid level is not changed, which indicates that the liquid level flows stably, selecting the fitting straight line with the angle relation and the length of the intersection line cluster changing stably, calculating the projection length of each line in the movement direction of the optimal inoculation position through the pythagorean theorem, representing the movement speed of the optimal inoculation position in the direction, calculating the movement direction and the movement speed of the optimal inoculation position by using the change characteristics of angles and lengths of continuous multiframes, and predicting the optimal inoculation position.
After the analysis unit analyzes, calculates and predicts the optimal inoculation position, the seed rod is controlled by a control system to move to the optimal inoculation position, and a buzzer is controlled to give out a sound signal to prompt the start of inoculation.
The control system determines the time taken by the optimal inoculation position to reach the optimal inoculation position according to the optimal inoculation position predicted by the analysis unit and the movement direction and the movement speed of the optimal inoculation position, and controls the seed rod to reach the optimal inoculation position at a specified speed for inoculation by combining the distance between the seed rod and the optimal inoculation position.
The invention adopts the following technical scheme: a sapphire inoculation detection method based on multi-frame image motion information utilizes the sapphire inoculation detection device based on multi-frame image motion information to carry out detection, and comprises the following steps:
the method comprises the steps that images of the sapphire liquid level in a crucible are collected in real time through a first image collection module and a second image collection module, and the images of the sapphire liquid level collected by the two image collection modules are subjected to image fusion;
denoising and enhancing filtering processing are carried out on each frame of fused image to obtain a critical inoculation liquid level key intersection line cluster in the fused image, length and included angle fine change characteristics in the image are extracted, Huffman straight line fitting is carried out on the liquid level key intersection line cluster, and length and included angle fine characteristic changes are quantized;
in a multi-frame fusion image, if the number of the fitting straight lines of one of the fitting straight lines tends to be stable and any one fitting straight line does not disappear in less than 3600 frames, at least two adjacent fitting straight lines in the sapphire liquid level key intersection line cluster attract each other and when the two fitting straight lines are coincided into one straight line, the optimal inoculation position is determined to move on an acute angle bisector formed by the two straight lines;
and (3) if the length of the fitting straight line in the key intersection line cluster of the liquid level is not changed, which indicates that the liquid level flows stably, selecting the fitting straight line with the angle relation and the length of the intersection line cluster changing stably, calculating the projection length of each line in the movement direction of the optimal inoculation position through the pythagorean theorem, representing the movement speed of the optimal inoculation position in the direction, calculating the movement direction and the movement speed of the optimal inoculation position by using the change characteristics of angles and lengths of continuous multiframes, and predicting the optimal inoculation position.
Different from the prior art, the sapphire inoculation detection device and method based on multi-frame image motion information solve the problems that the inoculation critical environment parameters are difficult to measure, the thermal field characteristics of different crystal growth devices are different, and the inoculation critical state environment parameters are different through the multi-frame image feature recognition technology of the sapphire inoculation liquid level. The multi-frame image motion characteristics identified by the invention only appear in the most suitable inoculation environment, the angle and length change characteristics of the key intersection line cluster of the inoculation liquid level can be analyzed, and the method for measuring the most suitable inoculation environment parameters is not used for searching the inoculation point. The invention utilizes the multi-frame image motion information and the image fusion technology to carry out depth analysis on the multi-frame image characteristics of the sapphire inoculation liquid level, predicts the optimal inoculation position of the industrial sapphire, and does not need to detect the related physicochemical characteristics of the optimal inoculation position. The system has good real-time performance and low prediction misjudgment rate.
Drawings
Fig. 1 is a schematic structural diagram of a sapphire inoculation detection device based on multi-frame image motion information provided by the invention.
Fig. 2 is a schematic flow chart of a sapphire inoculation detection method based on multi-frame image motion information provided by the invention.
Detailed Description
The technical solution of the present invention will be further described in more detail with reference to the following embodiments. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a sapphire inoculation detection device based on multi-frame image motion information according to the present invention. The device includes: the device comprises a crucible 1, a seed rod 2, a first observation window 3, a second observation window 4, a first filtering module 5, a second filtering module 6, a first image acquisition module 7, a second image acquisition module 8, an image analysis system 9, a signal transmission system 10 and a control system 11.
Wherein, crucible 1 includes crucible body 101 and crucible cover 102, and crucible body 101 is used for bearing and heats the sapphire of treating the inoculation, and the through-hole is seted up at crucible cover 102 middle part and is formed the supported hole of first observation window 3, second observation window 4 and seed rod 2 respectively. Preferably, the crucible cover 102 is arranged in a circular shape, and the first observation window 3 and the second observation window 4 are arranged on the crucible cover 102 at positions close to the center of the circle and are symmetrically arranged relative to the center of the circle. The supporting hole of the seed rod 2 is arranged at the position of the center of the crucible cover 102 and is directly equal to or slightly larger than the diameter of the seed rod 2. The seed rod 2 is a commonly used seed rod.
The first filtering module 5 and the second filtering module 6 are respectively disposed in the first observation window 3 and the second observation window 4, and specifically cover the first observation window 3 and the second observation window 4. The first filtering module 5 and the second filtering module 6 are both filters with the wavelength of 0.43-1.6um, and are used for providing channels of visible light and partial infrared bands to reflect the characteristics of the liquid level of the molten crystal. The first image acquisition module 7 and the second image acquisition module 8 acquire the image characteristics of the sapphire liquid level in the crucible 1 through the first observation window 3 and the second observation window 4. The first image acquisition module 7 and the second image acquisition module 8 are formed by sequentially connecting an objective lens, a magnifier, an eyepiece and a color industrial CCD. The optimal color industrial CCD is selected by designing a light path to measure and calculate the focal length according to the process of different equipment. The first observation window 3, the first filtering module 5 and the first image acquisition module 7 can be sequentially connected through matched threaded interfaces to form a first light path system. The second observation window 4, the second filtering module 6 and the second image acquisition module 8 can be sequentially connected through matched threaded interfaces to form another light path system. The image analysis system 9 is connected with the first image acquisition module 7 and the second image acquisition module 8 so as to process images of the first image acquisition module 7 and the second image acquisition module 8; the control system 11 is connected with the image analysis system 9 and used for controlling the seed rod 2 to move towards the interior of the crucible 1 according to the result of the image analysis so as to perform the inoculation of the sapphire crystal, and the signal transmission system 10 is respectively connected with the first image acquisition module 7, the second image acquisition module 8, the image analysis system 9 and the control system 11 so as to control the transmission of signals. Specifically, the first image acquisition module 7 and the second image acquisition module 8 acquire image information of the sapphire liquid level in the crucible 1 in real time and send the image information to the signal transmission system 10, the signal transmission system 10 sends the image information to the image analysis system 9, after the analysis is completed, the image analysis system sends the analyzed result information to the control system 11, and the control system 11 controls the movement of the seed rod 2 according to the analyzed result.
Specifically, the image analysis system 9 includes:
the receiving unit 901 is connected with the first image acquisition module 7 and the second image acquisition module 8 through a signal transmission system, and is used for receiving the sapphire image information in the crucible 1 acquired by the first image acquisition module 7 and the second image acquisition module 8 in real time;
the preprocessing unit 902 is configured to perform fusion processing on the sapphire images acquired by the first image acquisition module 7 and the second image acquisition module 8 received by the receiving unit 901, perform noise reduction and enhancement filtering processing on each frame of fused image to obtain a critical inoculation liquid level key intersection line cluster in the fused image, extract length and included angle subtle change features in the image, perform huffman line fitting on the liquid level key intersection line cluster, and quantize length and included angle subtle feature changes;
and the analysis unit 903 is used for determining the optimal sapphire inoculation position according to the length and included angle characteristic analysis result of the fitted straight line cluster in the continuous multi-frame fusion image.
The analysis unit 903 determines that the optimal inoculation position moves on an acute angle bisector formed by two straight lines when the optimal inoculation position is determined to be a straight line according to the fact that the number of the fitting straight lines of one of the multi-frame fused images tends to be stable, any one fitting straight line does not disappear in less than 3600 frames, and at least two adjacent fitting straight lines in the sapphire liquid level key intersection line cluster attract each other;
and (3) if the length of the fitting straight line in the key intersection line cluster of the liquid level is not changed, which indicates that the liquid level flows stably, selecting the fitting straight line with the angle relation and the length of the intersection line cluster changing stably, calculating the projection length of each line in the movement direction of the optimal inoculation position through the pythagorean theorem, representing the movement speed of the optimal inoculation position in the direction, calculating the movement direction and the movement speed of the optimal inoculation position by using the change characteristics of angles and lengths of continuous multiframes, and predicting the optimal inoculation position.
After the analysis unit 903 analyzes and calculates the predicted optimal inoculation position, the control system 11 controls the seed rod 2 to move to the optimal inoculation position, and controls a buzzer 1101 to give out an acoustic signal to prompt the start of inoculation.
The control system 11 determines the time taken for the optimal inoculation position to reach the optimal inoculation position according to the optimal inoculation position predicted by the analysis unit 903 and the movement direction and the movement speed of the optimal inoculation position, and controls the seed rod 2 to reach the optimal inoculation position at a specified speed for inoculation by combining the distance between the seed rod and the optimal inoculation position.
The method mainly utilizes multi-frame image motion information combined with an image fusion technology to analyze the angle and length characteristics of key intersection line clusters of the inoculation liquid level, predicts the optimal inoculation position of the industrial sapphire and realizes automatic inoculation.
Specifically, the working process of the sapphire inoculation detection device provided by the invention is as follows:
1. according to the equipment process for preparing the sapphire by the kyropoulos method, an inoculation light path is designed, the actual object distance (namely the distance between the first observation window 3 and the second observation window 4 and the liquid level of the sapphire) is set to be 44.85cm, the actual visual field diameter of the first observation window 3 and the second observation window 4 is a circle of 5cm, the focal length of a lens is calculated, the focal length of the camera is generally smaller than that of the lens, and a suitable color industrial CCD camera is selected. Two sets of objective lenses, magnifying lenses and eye lenses matched with the CCD camera are selected to serve as a first image acquisition module 7 and a second image acquisition module 8, and a filter with the wavelength range of 0.43-1.6um is selected to serve as a first filtering module 5 and a second filtering module 6 so as to provide visible light and partial infrared band channels, so that the characteristics of the liquid level of the molten crystal are reflected more finely.
2. Calibrating the industrial CCD cameras of the first image acquisition module 7 and the second image acquisition module 8, and enabling each pixel of the obtained re-fused image to correspond to the actual position of the crucible liquid level during critical inoculation through the first image acquisition module 7 and the second image acquisition module 8 by the image analysis system 9.
3. The method comprises the steps that images of a molten crystal liquid level of 75 kilograms of molten aluminum oxide and an image of a seed rod 2 are collected by two image collecting modules at the top of a crucible 1, and the detailed characteristic change of the length and the included angle of a key intersection line cluster of the molten crystal liquid level is collected.
4. The acquired image information is transmitted to the image analysis system 9 via a signal transmission system 10. The image analysis system 9 preprocesses each frame of image under the two image acquisition modules, and then obtains a complete inoculation liquid level image by using a pixel level image fusion technology. And the image analysis system 9 continues to perform noise reduction and enhanced filtering processing on each frame of fused image to obtain a critical inoculation liquid level key intersection line cluster, extracts length and included angle fine change characteristics, performs Huffman line fitting on the liquid level key intersection line cluster, and quantizes length and included angle fine characteristic changes. The method comprises the steps of analyzing the length and included angle characteristics of a fitting straight line cluster in continuous multi-frame fusion images, wherein the multi-frame image motion characteristics only appear in the most suitable inoculation environment, firstly, the number of the fitting straight lines in the continuous multi-frame fusion images is stable, any fitting straight line does not disappear in less than 3600 frames, the angle change relation can provide a basis for seed position prediction, two adjacent fitting straight lines in a liquid level key intersection line cluster are necessarily mutually attracted and coincide into a straight line, and the optimal inoculation position moves on an acute angle bisector formed by the two straight lines. Secondly, the length of a fitting straight line in a key intersection line cluster of the liquid level represents the liquid level flowing speed, the length is unchanged, the liquid level flowing is stable, only the fitting straight line with the angle relation and the length of the intersection line cluster stably changed is selected, the projection length of each line in the movement direction of the optimal inoculation position is calculated through the pythagorean theorem, and the movement speed of the optimal inoculation position in the direction is represented. The optimal inoculation position can be predicted by calculating the movement direction and the movement speed of the optimal inoculation position by utilizing the change characteristics of angles and lengths of continuous multiple frames.
5. The image analysis system 8 informs the prompt and control system 11 to take corresponding actions, the buzzer warns technical workers to start equipment inoculation, time consumed by descending of the seed rod is fully considered, the seed rod accurately reaches a predicted inoculation position, and automatic inoculation is completed.
The invention aims to provide a multi-frame image feature recognition technology for a sapphire inoculation liquid level, and solves the problems that the inoculation critical environment parameters are difficult to measure, the thermal field characteristics of different crystal growth devices are different, and the inoculation critical environment parameters are different. The multi-frame image motion characteristics identified by the invention only appear in the most suitable inoculation environment, the angle and length change characteristics of the key intersection line cluster of the inoculation liquid level can be analyzed, and the method for measuring the most suitable inoculation environment parameters is not used for searching the inoculation point.
The second purpose of the invention is to utilize the multi-frame image motion information and the image fusion technology to carry out depth analysis on the multi-frame image characteristics of the sapphire inoculation liquid level and predict the optimal inoculation position of the industrial sapphire without detecting the related physicochemical characteristics of the optimal inoculation position.
The third purpose of the invention is to provide a sapphire inoculation detection system based on multi-frame image motion information, which has good real-time performance and low prediction error rate.
Referring to fig. 2, fig. 2 is a method for detecting sapphire inoculation based on multi-frame image motion information, the method uses the sapphire inoculation detection device of the technical scheme for detection, and the method specifically comprises the following steps:
the method comprises the steps that images of the sapphire liquid level in a crucible are collected in real time through a first image collection module and a second image collection module, and the images of the sapphire liquid level collected by the two image collection modules are subjected to image fusion;
denoising and enhancing filtering processing are carried out on each frame of fused image to obtain a critical inoculation liquid level key intersection line cluster in the fused image, length and included angle fine change characteristics in the image are extracted, Huffman straight line fitting is carried out on the liquid level key intersection line cluster, and length and included angle fine characteristic changes are quantized;
in a multi-frame fusion image, if the number of the fitting straight lines of one of the fitting straight lines tends to be stable and any one fitting straight line does not disappear in less than 3600 frames, at least two adjacent fitting straight lines in the sapphire liquid level key intersection line cluster attract each other and when the two fitting straight lines are coincided into one straight line, the optimal inoculation position is determined to move on an acute angle bisector formed by the two straight lines;
and (3) if the length of the fitting straight line in the key intersection line cluster of the liquid level is not changed, which indicates that the liquid level flows stably, selecting the fitting straight line with the angle relation and the length of the intersection line cluster changing stably, calculating the projection length of each line in the movement direction of the optimal inoculation position through the pythagorean theorem, representing the movement speed of the optimal inoculation position in the direction, calculating the movement direction and the movement speed of the optimal inoculation position by using the change characteristics of angles and lengths of continuous multiframes, and predicting the optimal inoculation position.
Different from the prior art, the sapphire inoculation detection device and method based on multi-frame image motion information solve the problems that the inoculation critical environment parameters are difficult to measure, the thermal field characteristics of different crystal growth devices are different, and the inoculation critical state environment parameters are different through the multi-frame image feature recognition technology of the sapphire inoculation liquid level. The multi-frame image motion characteristics identified by the invention only appear in the most suitable inoculation environment, the angle and length change characteristics of the key intersection line cluster of the inoculation liquid level can be analyzed, and the method for measuring the most suitable inoculation environment parameters is not used for searching the inoculation point. The invention utilizes the multi-frame image motion information and the image fusion technology to carry out depth analysis on the multi-frame image characteristics of the sapphire inoculation liquid level, predicts the optimal inoculation position of the industrial sapphire, and does not need to detect the related physicochemical characteristics of the optimal inoculation position. The system has good real-time performance and low prediction misjudgment rate.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (7)
1. A sapphire inoculation detection device based on multiframe image motion information is characterized by comprising: the device comprises a crucible, a seed rod, a first observation window, a second observation window, a first light filtering module, a second light filtering module, a first image acquisition module, a second image acquisition module, an image analysis system, a signal transmission system and a control system;
the crucible comprises a crucible body and a crucible cover, wherein the crucible body is used for bearing and heating the sapphire to be inoculated, and the middle part of the crucible cover is provided with a through hole to form a first observation window, a second observation window and a support hole of the seed rod respectively; the first light filtering module and the second light filtering module are respectively arranged in the first observation window and the second observation window, and the first image acquisition module and the second image acquisition module acquire the image characteristics of the sapphire liquid level in the crucible through the first observation window and the second observation window; the image analysis system is connected with the first image acquisition module and the second image acquisition module so as to process images of the first image acquisition module and the second image acquisition module; the control system is connected with the image analysis system and used for controlling the seed rod to move towards the interior of the crucible according to the result of image analysis so as to inoculate the sapphire crystal, and the signal transmission system is respectively connected with the first image acquisition module, the second image acquisition module and the image analysis system so as to control the transmission of signals;
the image analysis system includes:
the receiving unit is connected with the first image acquisition module and the second image acquisition module through a signal transmission system and is used for receiving the sapphire image information in the crucible acquired by the first image acquisition module and the second image acquisition module in real time;
the preprocessing unit is used for carrying out fusion processing on the sapphire images collected by the first image collection module and the second image collection module received by the receiving unit, carrying out noise reduction and enhanced filtering processing on each frame of fused image to obtain a critical inoculation liquid level key intersection line cluster in the fused image, extracting length and included angle fine change characteristics in the image, carrying out Hofman straight line fitting on the liquid level key intersection line cluster, and quantizing length and included angle fine characteristic changes;
the analysis unit is used for determining the optimal sapphire inoculation position according to the characteristic analysis result of the length and included angle of the fitted straight line cluster in the continuous multi-frame fusion image;
the analysis unit finds that the number of the fitting straight lines of one of the fitting straight lines tends to be stable in the multi-frame fusion image, any one fitting straight line does not disappear in less than 3600 frames, at least two adjacent fitting straight lines in the sapphire liquid level key intersection line cluster attract each other, and when the two fitting straight lines are overlapped into one straight line, the best inoculation position is determined to move on an acute angle bisector formed by the two straight lines;
and (3) if the length of the fitting straight line in the key intersection line cluster of the liquid level is not changed, which indicates that the liquid level flows stably, selecting the fitting straight line with the angle relation and the length of the intersection line cluster changing stably, calculating the projection length of each line in the movement direction of the optimal inoculation position through the pythagorean theorem, representing the movement speed of the optimal inoculation position in the direction, calculating the movement direction and the movement speed of the optimal inoculation position by using the change characteristics of angles and lengths of continuous multiframes, and predicting the optimal inoculation position.
2. The sapphire inoculation detection device based on multiframe image motion information of claim 1, wherein the first observation window, the first filtering module, the first image acquisition module, and the second observation window, the second filtering module, and the second image acquisition module are all connected in sequence through matching threaded interfaces.
3. The sapphire inoculation detection device based on multi-frame image motion information, as recited in claim 1, wherein the first filter module and the second filter module are both filters with a wavelength of 0.43-1.6um, and are used for providing visible light and partial infrared band channels to reflect the characteristics of the molten crystal liquid level.
4. The sapphire inoculation detection device based on multiframe image motion information of claim 1, wherein the first image acquisition module and the second image acquisition module are formed by connecting an objective lens, a magnifying lens, an ocular lens and a color industrial CCD in sequence.
5. The sapphire inoculation detection device based on multi-frame image motion information as claimed in claim 1, wherein after the analysis unit analyzes and calculates the predicted optimal inoculation position, the control system controls the seed rod to move to the optimal inoculation position and controls a buzzer to give out an acoustic signal to prompt the start of inoculation.
6. The sapphire inoculation detection device based on multi-frame image motion information as claimed in claim 5, wherein the control system determines the time taken for the optimal inoculation position to reach the optimal inoculation position according to the optimal inoculation position predicted by the analysis unit and the motion direction and the motion speed of the optimal inoculation position, and controls the seed rod to reach the optimal inoculation position at a specified speed for inoculation by combining the distance between the seed rod and the optimal inoculation position.
7. A sapphire inoculation detection method based on multi-frame image motion information, which is used for detection by the sapphire inoculation detection device based on multi-frame image motion information as claimed in claims 1-6, and is characterized by comprising the following steps:
the method comprises the steps that images of the sapphire liquid level in a crucible are collected in real time through a first image collection module and a second image collection module, and the images of the sapphire liquid level collected by the two image collection modules are subjected to image fusion;
denoising and enhancing filtering processing are carried out on each frame of fused image to obtain a critical inoculation liquid level key intersection line cluster in the fused image, length and included angle fine change characteristics in the image are extracted, Huffman straight line fitting is carried out on the liquid level key intersection line cluster, and length and included angle fine characteristic changes are quantized;
in a multi-frame fusion image, if the number of the fitting straight lines of one of the fitting straight lines tends to be stable and any one fitting straight line does not disappear in less than 3600 frames, at least two adjacent fitting straight lines in the sapphire liquid level key intersection line cluster attract each other and when the two fitting straight lines are coincided into one straight line, the optimal inoculation position is determined to move on an acute angle bisector formed by the two straight lines;
and (3) if the length of the fitting straight line in the key intersection line cluster of the liquid level is not changed, which indicates that the liquid level flows stably, selecting the fitting straight line with the angle relation and the length of the intersection line cluster changing stably, calculating the projection length of each line in the movement direction of the optimal inoculation position through the pythagorean theorem, representing the movement speed of the optimal inoculation position in the direction, calculating the movement direction and the movement speed of the optimal inoculation position by using the change characteristics of angles and lengths of continuous multiframes, and predicting the optimal inoculation position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810333442.6A CN108344742B (en) | 2018-04-13 | 2018-04-13 | Sapphire inoculation detection device and method based on multi-frame image motion information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810333442.6A CN108344742B (en) | 2018-04-13 | 2018-04-13 | Sapphire inoculation detection device and method based on multi-frame image motion information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108344742A CN108344742A (en) | 2018-07-31 |
| CN108344742B true CN108344742B (en) | 2020-06-05 |
Family
ID=62954970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810333442.6A Active CN108344742B (en) | 2018-04-13 | 2018-04-13 | Sapphire inoculation detection device and method based on multi-frame image motion information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108344742B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109487334A (en) * | 2018-11-22 | 2019-03-19 | 太原理工大学 | A kind of kyropoulos sapphire based on random distribution melts brilliant inoculation state control method |
| CN112642022B (en) * | 2020-12-31 | 2022-07-05 | 遵义师范学院 | Infusion monitoring system and monitoring method |
| CN113252176B (en) * | 2021-04-30 | 2022-04-12 | 太原理工大学 | Sapphire inoculation point high-precision sensing device and method based on radiation spectrum |
| CN113280906B (en) * | 2021-06-18 | 2022-05-10 | 太原理工大学 | Computer vision-based best seed crystal inoculation timing vibration sensing method for kyropoulos method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1307654A (en) * | 1998-06-26 | 2001-08-08 | Memc电子材料有限公司 | Crystal puller for growing low defect density, self-interstitial dominated silicon |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5882402A (en) * | 1997-09-30 | 1999-03-16 | Memc Electronic Materials, Inc. | Method for controlling growth of a silicon crystal |
| JP3592909B2 (en) * | 1997-10-29 | 2004-11-24 | 東芝セラミックス株式会社 | Single crystal pulling device |
| CN1396965A (en) * | 2000-02-01 | 2003-02-12 | Memc电子材料有限公司 | Method for controlling growth of silicon crystal to minimize growth rate and diameter deviations |
| JP4056206B2 (en) * | 2000-09-11 | 2008-03-05 | 株式会社荏原製作所 | Ribbon crystal growth method and apparatus |
| JP2004035352A (en) * | 2002-07-05 | 2004-02-05 | Sumitomo Mitsubishi Silicon Corp | Pull-up device for silicon single crystal |
| JP4930488B2 (en) * | 2008-10-21 | 2012-05-16 | 信越半導体株式会社 | Single crystal diameter detection method, single crystal manufacturing method using the same, and single crystal manufacturing apparatus |
| JP5109928B2 (en) * | 2008-10-21 | 2012-12-26 | 信越半導体株式会社 | Single crystal diameter detection method, single crystal manufacturing method using the same, and single crystal manufacturing apparatus |
| US8545623B2 (en) * | 2009-06-18 | 2013-10-01 | Sumco Phoenix Corporation | Method and apparatus for controlling the growth process of a monocrystalline silicon ingot |
| DE102012003114B4 (en) * | 2012-02-16 | 2014-02-13 | Audiodev Gmbh | METHOD OF MEASURING THE DISTANCE BETWEEN TWO OBJECTS |
| JP2016121023A (en) * | 2014-12-24 | 2016-07-07 | 株式会社Sumco | Production method of single crystal |
| JP6477356B2 (en) * | 2015-08-21 | 2019-03-06 | 株式会社Sumco | Single crystal manufacturing method and manufacturing apparatus |
| KR101775057B1 (en) * | 2015-09-07 | 2017-09-05 | 한국생산기술연구원 | Apparatus and method for island position detecting of furnace |
| CN107818559B (en) * | 2017-09-22 | 2021-08-20 | 太原理工大学 | Crystal inoculation state detection method and crystal inoculation state image acquisition device |
-
2018
- 2018-04-13 CN CN201810333442.6A patent/CN108344742B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1307654A (en) * | 1998-06-26 | 2001-08-08 | Memc电子材料有限公司 | Crystal puller for growing low defect density, self-interstitial dominated silicon |
Non-Patent Citations (2)
| Title |
|---|
| "In-situ monitoring system of the position andtemperature at the crystal–solution interface";Gen Sazaki 等;《Journal of Crystal Growth》;20021231;第236卷;第125–131页 * |
| "大直径蓝宝石生长工艺及性能研究";王铎;《中国优秀硕士学位论文全文数据库 工程科技I辑》;20100215(第2期);第B014-96页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108344742A (en) | 2018-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108344742B (en) | Sapphire inoculation detection device and method based on multi-frame image motion information | |
| CN108918539B (en) | Apparent disease detection device and method for tunnel structure | |
| CN110614638B (en) | Transformer substation inspection robot autonomous acquisition method and system | |
| CN108152869B (en) | Small step focusing method suitable for bionic vision rapid focusing | |
| CN110472698B (en) | Metal additive forming penetration real-time prediction method based on depth and transfer learning | |
| CN105675266A (en) | Device and method for measuring modulation transfer function of optical lens based on infinite conjugate optical path | |
| EP3158284B1 (en) | Apparatus and method for heating and measuring of transparent cylindrical articles | |
| CN111126206B (en) | Smelting state detection system and method based on deep learning | |
| CN106210520A (en) | A kind of automatic focusing electronic eyepiece and system | |
| SE518836C2 (en) | Device and method for an infrared image analyzing autofocus | |
| CN106979952A (en) | A kind of algae detection and Statistics of Density devices and methods therefor based on machine vision technique | |
| CN104596638B (en) | High-resolution multi-wavelength laser intensity distribution detector and measurement method implemented by same | |
| CN204984698U (en) | Spark plug measuring device based on machine vision technique | |
| CN111504885A (en) | Full-automatic blood smear morphological analysis device based on machine vision | |
| CN106755683A (en) | A kind of blast-furnace roasting band temperature field detection device based on colorimetric method | |
| CN107818559B (en) | Crystal inoculation state detection method and crystal inoculation state image acquisition device | |
| CN114034383B (en) | Real-time tunnel-outside brightness measuring device and method thereof | |
| CN110514302B (en) | Marine optical fiber spectrometer detection method based on small underwater machine equipment | |
| CN208568616U (en) | Glass tin defects vision identification system | |
| CN114324080B (en) | Device for online detection of morphology and particle size distribution of energetic material particles | |
| CN103983649B (en) | A kind of foreign matter detecting method based on light spectrum image-forming | |
| Gao et al. | A vision-based instrument for measuring milk somatic cell count | |
| CN202145259U (en) | Binocular stereoscopic vision imaging device of two-lens single-image sensor | |
| CN113029014B (en) | Method and device for detecting diameter of single crystal silicon rod | |
| CN114910478A (en) | Visual interface instrument for chemical interface detection and detection method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |