Image position calibration method and image displacement sensor

Abstract

The embodiment of the invention provides an image position calibration method and an image displacement sensor. The method comprises the steps of obtaining a target instant image; according to the target instant image and a pre-stored position image library, position information corresponding to the target instant image is determined, the pre-stored position image library at least comprises an instant image and the position information corresponding to the instant image, and the position information corresponding to the instant image is obtained through a scale with a certain length. The method comprises the following steps: acquiring image data at different positions according to required precision, calibrating position information, establishing a field information library, establishing a position image library, acquiring a target instant image, and comparing the target instant image with an image stored in the position image library, so that the target instant image is acquired according to the position information of the image in the position image library. Therefore, the position of the image can be quickly calibrated, errors caused by long-distance testing are avoided, and the accuracy of measurement is improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to an image position calibration method and an image displacement sensor. Background Art

[0002] With the widespread use of CNC machine tools in the processing field, the precision requirements for the products processed by CNC machine tools are constantly increasing. Grating rulers are a product that assists the tool path accuracy of CNC machine tools. They are often used in closed-loop servo systems of CNC machine tools and can be used to detect linear displacement or angular displacement. Grating rulers are currently used to measure the moving distance, but as the measuring distance becomes longer, the error generated will also become larger. How to test long distances with a smaller measurement error is a problem that urgently needs to be solved. Summary of the invention

[0003] Some embodiments of the present application aim to provide an image position calibration method and an image displacement sensor. Through the technical solution of the embodiments of the present application, a target instant image is obtained; according to the target instant image and a pre-stored position image library, the position information corresponding to the target instant image is determined, wherein the pre-stored position image library at least includes an instant image and the position information corresponding to the instant image, and a ruler of a certain length is used to collect image data at different positions according to the required accuracy, and the position information is calibrated to complete the establishment of a field information library, and a position image library is established. After collecting the target instant image, the target instant image is compared with the image stored in the position image library. In this way, the collected target instant image is determined according to the position information of the image in the position image library, so that the image position can be quickly calibrated, the error caused by long-distance testing can be avoided, and the measurement accuracy can be improved.

[0004] In a first aspect, some embodiments of the present application provide a method for calibrating an image position, including:

[0005] Acquire instantaneous image of target;

[0006] The position information corresponding to the target instant image is determined according to the target instant image and a pre-stored position image library, wherein the pre-stored position image library at least includes an instant image and position information corresponding to the instant image.

[0007] Some embodiments of the present application use a ruler of a certain length to collect image data at different positions according to the required accuracy, and calibrate the position information to complete the establishment of a field information library, establish a position image library, and after collecting the target instant image, compare the target instant image with the image stored in the position image library. In this way, the collected target instant image is determined based on the position information of the image in the position image library. In this way, the image position can be calibrated quickly, avoiding errors caused by long-distance testing and improving measurement accuracy.

[0008] Optionally, the pre-stored location image library is obtained in the following manner:

[0009] Acquire instantaneous images;

[0010] Decomposing the instantaneous image to obtain decomposed small images;

[0011] Performing discrete cosine transform processing on the decomposed small images respectively to obtain discrete cosine transform data corresponding to the decomposed small images;

[0012] Determine the average value of discrete cosine coefficients according to the discrete cosine transform data corresponding to the decomposed small image;

[0013] Determining position information of the instantaneous image according to the gray value of each pixel of the instantaneous image and the average value of the discrete cosine coefficients;

[0014] The instantaneous image and the position information corresponding to the instantaneous image are stored in the position image library.

[0015] Some embodiments of the present application calibrate the position of the acquired instantaneous image by using the uniqueness of the microscopic structures of different objects, which have slight differences with each other, and establish a position image library, and save the instantaneous image and the corresponding position information in the position image library, so that the subsequent image positions can be calibrated.

[0016] Optionally, determining the average value of discrete cosine coefficients according to discrete cosine transform data corresponding to the decomposed small image includes:

[0017] Calculate the sum of discrete cosine transform data of each pixel in the decomposed small image;

[0018] The discrete cosine coefficient average value is determined according to the number of pixels in the decomposed small image and the sum value.

[0019] Some embodiments of the present application perform DCT transformation on each image block from left to right and from top to bottom, discard high-frequency components, retain low-frequency components, and calculate the average value of DCT coefficients based on the obtained DCT values.

[0020] Optionally, determining the position information of the instantaneous image according to the gray value of each pixel of the instantaneous image and the average value of the discrete cosine coefficients includes:

[0021] If the grayscale value of the pixel of the instantaneous image is greater than or equal to the discrete cosine coefficient average value, setting the pixel of the instantaneous image as a first flag;

[0022] If the grayscale value of the pixel of the instantaneous image is less than the discrete cosine coefficient average value, setting the pixel of the instantaneous image as a second flag;

[0023] Determining a hash value corresponding to the instantaneous image according to the first identifier and the second identifier;

[0024] According to the hash value corresponding to the instantaneous image, the position information of the instantaneous image is determined.

[0025] Some embodiments of the present application determine whether adjacent images are the same image by calculating the hash value of each instantaneous image, and identify the location information of the instantaneous image.

[0026] Optionally, performing discrete cosine transform processing on the decomposed small images respectively to obtain discrete cosine transform data corresponding to the decomposed small images includes:

[0027] Perform discrete cosine transform processing on the decomposed small images in order from left to right and from top to bottom to obtain low-frequency components corresponding to the small images;

[0028] Performing quantization compression on the decomposed small image to obtain a compressed image;

[0029] The compressed image is subjected to inverse discrete cosine transform processing to obtain the instantaneous image.

[0030] Some embodiments of the present application perform quantization compression on the remaining image blocks, and the image composed of the compressed data greatly reduces the storage space; during decompression, an inverse DCT transform (IDCT) is performed on each image block, and then a complete image is reconstructed, which can reduce the storage space.

[0031] Optionally, the method further comprises:

[0032] When the number of identical values ​​in the hash value of the first instantaneous image and the hash value of the second instantaneous image is greater than or equal to a preset value, it is determined that the first instantaneous image and the second instantaneous image are the same instantaneous image.

[0033] Some embodiments of the present application determine the difference between two adjacent frames, utilize a perceptual hash algorithm, and recheck the initial inspection results to improve the accuracy of image recognition.

[0034] In a second aspect, some embodiments of the present application provide an image displacement sensor, comprising: a measuring unit, a microscopic imaging unit, a transmission unit and a control unit, wherein the measuring unit and the microscopic imaging unit are connected to the control unit via the transmission unit, wherein the control unit is used to execute the image position calibration method described in the first aspect.

[0035] The embodiments of the present application utilize the uniqueness of the microstructures of different objects and the slight differences between them to calibrate the acquired position images and establish a position image library. After capturing the instantaneous captured image, the instantaneous captured image is compared with its image library to determine the position information. The difference between two adjacent frames is judged, the perceptual hash algorithm is used, and the initial inspection results are re-inspected. An image displacement sensor is developed based on the above principles.

[0036] Optionally, the microscopic imaging unit is a camera device, and the microscopic imaging unit is used to take pictures at a shooting position.

[0037] Optionally, the control unit includes at least a control board, and the control board includes at least a single-chip microcomputer and a memory.

[0038] Optionally, the transmission unit includes at least a transmission line, and the transmission unit is used to send the image captured by the microscopic imaging unit to the control unit.

[0039] The embodiments of the present application utilize the uniqueness of the microstructures of different objects and the slight differences between them to calibrate the acquired position images and establish a position image library. After capturing the instantaneous captured image, the instantaneous captured image is compared with its image library to determine the position information. The difference between two adjacent frames is judged, the perceptual hash algorithm is used, and the initial inspection results are re-inspected. An image displacement sensor is developed based on the above principles. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic diagram of a flow chart of a method for calibrating an image position provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of the structure of an image position calibration system provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of another image position calibration system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.

[0045] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0046] With the widespread use of CNC machine tools in the processing field, the precision requirements for products processed by CNC machine tools are constantly increasing. Grating rulers are a product that assists CNC machine tool tooling accuracy. They are often used in closed-loop servo systems of CNC machine tools and can be used to detect linear displacement or angular displacement. Grating rulers are currently used to measure the moving distance, but as the measuring distance becomes longer, the error generated will also become larger. How to test long distances with a smaller measurement error is an issue that urgently needs to be addressed. In view of this, some embodiments of the present application provide a method for calibrating an image position, the method comprising acquiring a target instantaneous image; based on the target instantaneous image and a pre-measured position, a calibration method is provided. The stored position image library determines the position information corresponding to the target instantaneous image, wherein the pre-stored position image library includes at least the instantaneous image and the position information corresponding to the instantaneous image. By using a ruler of a certain length, image data is collected at different positions according to the required accuracy, and the position information is calibrated to complete the establishment of the field information library. After the position image library is established, the target instantaneous image is collected, and the target instantaneous image is compared with the image stored in the position image library. In this way, the collected target instantaneous image is determined according to the position information of the image in the position image library. In this way, the image position can be quickly calibrated to avoid errors caused by long-distance testing and improve the accuracy of measurement.

[0047] like Figure 1 As shown, an embodiment of the present application provides a method for calibrating an image position, the method comprising:

[0048] S101, acquiring a target instant image;

[0049] Specifically, in the embodiments of the present application, Figure 2 The image position calibration system shown in the figure acquires the target instant image through the microscopic imaging unit 2, and sends the acquired target instant image to the control unit 3, and the control unit 3 acquires the target instant image.

[0050] S102: Determine position information corresponding to the target instant image according to the target instant image and a pre-stored position image library, wherein the pre-stored position image library at least includes the instant image and the position information corresponding to the instant image.

[0051] Specifically, a position image library is pre-stored in the control unit. When a target instant image is acquired, the acquired target instant image is compared with the instant image in the position image library, and then the position information of the target instant image is determined based on the position information of the instant image in the position image library.

[0052] Some embodiments of the present application use a ruler of a certain length to collect image data at different positions according to the required accuracy, and calibrate the position information to complete the establishment of a field information library, establish a position image library, and after collecting the target instant image, compare the target instant image with the image stored in the position image library. In this way, the collected target instant image is determined based on the position information of the image in the position image library. In this way, the image position can be calibrated quickly, avoiding errors caused by long-distance testing and improving measurement accuracy.

[0053] Another embodiment of the present application further supplements the image position calibration method provided in the above embodiment.

[0054] Optionally, the pre-stored location image library is obtained by:

[0055] Acquire instantaneous images;

[0056] Decompose the instantaneous image to obtain a decomposed small image;

[0057] Performing discrete cosine transform processing on the decomposed small images respectively to obtain discrete cosine transform data corresponding to the decomposed small images;

[0058] Determine the average value of discrete cosine coefficients according to the discrete cosine transform data corresponding to the decomposed small image;

[0059] Determine the position information of the instantaneous image according to the gray value of each pixel of the instantaneous image and the average value of the discrete cosine coefficient;

[0060] The instantaneous image and the position information corresponding to the instantaneous image are stored in a position image library.

[0061] Some embodiments of the present application calibrate the position of the acquired instantaneous image by using the uniqueness of the microscopic structures of different objects, which have slight differences with each other, and establish a position image library, and save the instantaneous image and the corresponding position information in the position image library, so that the subsequent image positions can be calibrated.

[0062] Optionally, determining the average value of discrete cosine coefficients according to discrete cosine transform data corresponding to the decomposed small image includes:

[0063] Calculate the sum of discrete cosine transform data of each pixel in the decomposed small image;

[0064] The average value of discrete cosine coefficients is determined according to the number and sum of pixels in the decomposed small image.

[0065] Some embodiments of the present application perform DCT transformation on each image block from left to right and from top to bottom, discard high-frequency components, retain low-frequency components, and calculate the average value of DCT coefficients based on the obtained DCT values.

[0066] Optionally, determining the position information of the instantaneous image according to the gray value of each pixel of the instantaneous image and the average value of the discrete cosine coefficient includes:

[0067] If the grayscale value of the pixel of the instantaneous image is greater than or equal to the discrete cosine coefficient average value, the pixel of the instantaneous image is set as the first flag;

[0068] If the grayscale value of the pixel of the instantaneous image is less than the discrete cosine coefficient average value, the pixel of the instantaneous image is set as the second flag;

[0069] Determine a hash value corresponding to the instantaneous image according to the first identifier and the second identifier;

[0070] According to the hash value corresponding to the instantaneous image, the position information of the instantaneous image is determined.

[0071] Some embodiments of the present application determine whether adjacent images are the same image by calculating the hash value of each instantaneous image, and identify the location information of the instantaneous image.

[0072] Optionally, performing discrete cosine transform processing on the decomposed small images respectively to obtain discrete cosine transform data corresponding to the decomposed small images includes:

[0073] The decomposed small images are processed with discrete cosine transform in order from left to right and from top to bottom to obtain low-frequency components corresponding to the small images;

[0074] Perform quantization compression on the decomposed small image to obtain a compressed image;

[0075] The compressed image is processed by inverse discrete cosine transform to obtain an instantaneous image.

[0076] Some embodiments of the present application perform quantization compression on the remaining image blocks, and the image composed of the compressed data greatly reduces the storage space; during decompression, an inverse DCT transform (IDCT) is performed on each image block, and then a complete image is reconstructed, which can reduce the storage space.

[0077] Optionally, the method further comprises:

[0078] When the number of identical values ​​in the hash value of the first instantaneous image and the hash value of the second instantaneous image is greater than or equal to a preset value, it is determined that the first instantaneous image and the second instantaneous image are the same instantaneous image.

[0079] Some embodiments of the present application determine the difference between two adjacent frames, utilize a perceptual hash algorithm, and recheck the initial inspection results to improve the accuracy of image recognition.

[0080] Specifically, in the embodiment of the present application, a location image library is pre-established, specifically including:

[0081] 1. Use microscopic imaging technology to collect instantaneous images and record the location information of the instantaneous images;

[0082] 2. Calibrate the position of its instantaneous image through different position information;

[0083] 3. Establish a position image library based on the instant image and the position information of the instant image;

[0084] The steps to build a location image library are as follows:

[0085] 1) Image acquisition is performed during the movement. If the accuracy is 1um, an image is acquired every 1um, i.e., an instantaneous image;

[0086] 2) Decompose the instantaneous image into 8*8 image blocks;

[0087] 3) Convert the RGB system representing pixels into the YUV system;

[0088] 4) Then, from left to right and from top to bottom, DCT (Discrete Cosine Transform) is performed on each image block, i.e., the decomposed small image, to discard the high-frequency components and retain the low-frequency components;

[0089] 5) The remaining image blocks are quantized and compressed, and the image composed of the compressed data greatly reduces the storage space;

[0090] 6) During decompression, each image block is subjected to an inverse DCT transform (IDCT), and then a complete image is reconstructed;

[0091] 7) Calculate the average value of DCT coefficients,

[0092] 8) Calculate the hash value, that is, compare the grayscale of each pixel with the average value of the DCT coefficient. If it is greater than or equal to the average value, it is recorded as 1, and if it is less than the average value, it is recorded as 0. The results are combined to form a 64-bit binary integer, which is the hash value of the instantaneous image, and the position information is marked according to the hash value;

[0093] 9) Establish a position image library based on the position information and instantaneous images.

[0094] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0095] Another embodiment of the present application provides an image displacement sensor, including: a measuring unit 1, a microscopic imaging unit 2, a transmission unit and a control unit 3, wherein the measuring unit and the microscopic imaging unit are connected to the control unit via the transmission unit, wherein the control unit is used to execute the above-mentioned image position calibration method.

[0096] The embodiments of the present application utilize the uniqueness of the microstructures of different objects and the slight differences between them to calibrate the acquired position images and establish a position image library. After capturing the instantaneous captured image, the instantaneous captured image is compared with its image library to determine the position information. The difference between two adjacent frames is judged, the perceptual hash algorithm is used, and the initial inspection results are re-inspected. An image displacement sensor is developed based on the above principles.

[0097] Optionally, the microscopic imaging unit is a camera device, and the microscopic imaging unit is used to take pictures at a shooting position.

[0098] Optionally, the control unit includes at least a control board, and the control board includes at least a single-chip microcomputer and a memory.

[0099] Optionally, the transmission unit includes at least a transmission line, and the transmission unit is used to send the image captured by the microscopic imaging unit to the control unit.

[0100] like Figure 2 and Figure 3 As shown, the image displacement sensor provided by the embodiment of the present application includes: a ruler 1, a microscopic imaging device 2, a transmission line and a control unit, wherein the ruler 1 is a ruler, which can be an unprocessed grating ruler body. The unprocessed grating ruler body can directly compare the position information to achieve accurate position feedback. The ruler can also be a grating ruler body with processed stripes. Since the grating ruler processing will affect the accuracy of the grating ruler sensor, that is, the accuracy of the grating ruler, the grating ruler with processed stripes can be adjusted for accuracy, thereby improving the positioning accuracy of the grating ruler.

[0101] The microscopic imaging device 2 is a video camera or a still camera, and the control unit is a control board;

[0102] The location information determination method in the embodiment of the present application includes:

[0103] a) Decompose the image into 8×8 image blocks;

[0104] b) Calculate DCT, calculate DCT, but only take the upper left 8×8 matrix, which represents the lowest frequency in the image;

[0105] c) calculating the average value, calculating the average value of the DCT coefficients;

[0106] d) Calculate the hash value and compare the grayscale of each pixel with the average value of the DCT coefficient. If it is greater than or equal to the average value, it is recorded as 1, and if it is less than the average value, it is recorded as 0. The results are combined to form a 64-bit binary integer.

[0107] e) Compare the image hash values. If the number of different data bits does not exceed 5, it means that the two images are very similar. If it is greater than 10, it means that they are two different images.

[0108] Obtain a first hash value of the first instantaneous image, that is, the first binary data, and obtain a second hash value of the second instantaneous image, that is, the second binary data, and compare the first binary data with the second binary data. If the number of identical data is greater than or equal to a preset value, it indicates that the first instantaneous image and the second instantaneous image are the same image, and store a position information. If the number of identical data is less than the preset value, it indicates that the first instantaneous image and the second instantaneous image are different images.

[0109] f) After making a judgment, conduct a second re-inspection, not exceeding 5, to obtain the position information of the mark;

[0110] The embodiments of the present application utilize the uniqueness of the microstructures of different objects and the slight differences between them to calibrate the acquired position images and establish a position image library. After capturing the instantaneous captured image, the instantaneous captured image is compared with its image library to determine the position information. The difference between two adjacent frames is judged, the perceptual hash algorithm is used, and the initial inspection results are re-inspected. An image displacement sensor is developed based on the above principles.

[0111] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0112] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0113] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0114] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0115] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0116] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for calibrating an image position, characterized in that: The method comprises: Acquire instantaneous image of target; The position information corresponding to the target instant image is determined according to the target instant image and a pre-stored position image library, wherein the pre-stored position image library at least includes an instant image and position information corresponding to the instant image.

2. The method for calibrating image position according to claim 1, characterized in that: The pre-stored location image library is obtained in the following manner: Acquire instantaneous images; Decomposing the instantaneous image to obtain decomposed small images; Performing discrete cosine transform processing on the decomposed small images respectively to obtain discrete cosine transform data corresponding to the decomposed small images; Determine the average value of discrete cosine coefficients according to the discrete cosine transform data corresponding to the decomposed small image; Determining position information of the instantaneous image according to the gray value of each pixel of the instantaneous image and the average value of the discrete cosine coefficients; The instantaneous image and the position information corresponding to the instantaneous image are stored in the position image library.

3. The method for calibrating image position according to claim 2, characterized in that: The step of determining the average value of discrete cosine coefficients according to the discrete cosine transform data corresponding to the decomposed small image comprises: Calculate the sum of discrete cosine transform data of each pixel in the decomposed small image; The discrete cosine coefficient average value is determined according to the number of pixels in the decomposed small image and the sum value.

4. The method for calibrating image position according to claim 2, characterized in that: Determining the position information of the instantaneous image according to the gray value of each pixel of the instantaneous image and the average value of the discrete cosine coefficients includes: If the grayscale value of the pixel of the instantaneous image is greater than or equal to the discrete cosine coefficient average value, setting the pixel of the instantaneous image as a first flag; If the grayscale value of the pixel of the instantaneous image is less than the discrete cosine coefficient average value, setting the pixel of the instantaneous image as a second flag; Determining a hash value corresponding to the instantaneous image according to the first identifier and the second identifier; According to the hash value corresponding to the instantaneous image, the position information of the instantaneous image is determined.

5. The method for calibrating image position according to claim 2, characterized in that: The step of performing discrete cosine transform processing on the decomposed small images respectively to obtain discrete cosine transform data corresponding to the decomposed small images includes: Perform discrete cosine transform processing on the decomposed small images in order from left to right and from top to bottom to obtain low-frequency components corresponding to the small images; Performing quantization compression on the decomposed small image to obtain a compressed image; The compressed image is subjected to inverse discrete cosine transform processing to obtain the instantaneous image.

6. The method for calibrating image position according to claim 1, characterized in that: The method further comprises: When the number of identical values ​​in the hash value of the first instantaneous image and the hash value of the second instantaneous image is greater than or equal to a preset value, it is determined that the first instantaneous image and the second instantaneous image are the same instantaneous image.

7. An image displacement sensor, characterized in that: The image displacement sensor comprises at least: a measuring unit, a microscopic imaging unit, a transmission unit and a control unit, wherein the measuring unit and the microscopic imaging unit are connected to the control unit via the transmission unit, wherein the control unit is used for the image position calibration method as described in any one of claims 1-6.

8. The image displacement sensor according to claim 7, characterized in that: The microscopic imaging unit is an imaging device, and the microscopic imaging unit is used to take pictures at a shooting position.

9. The image displacement sensor according to claim 7, characterized in that: The control unit at least includes a control board, and the control board at least includes a single chip microcomputer and a memory.

10. The image displacement sensor according to claim 7, characterized in that: The transmission unit at least includes a transmission line, and the transmission unit is used to send the image collected by the microscopic imaging unit to the control unit.

Images