CN110827224A - High-resolution high-temperature forging shape detection method - Google Patents
High-resolution high-temperature forging shape detection method Download PDFInfo
- Publication number
- CN110827224A CN110827224A CN201911097885.0A CN201911097885A CN110827224A CN 110827224 A CN110827224 A CN 110827224A CN 201911097885 A CN201911097885 A CN 201911097885A CN 110827224 A CN110827224 A CN 110827224A
- Authority
- CN
- China
- Prior art keywords
- resolution
- image
- low
- temperature forging
- resolution image
- 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.)
- Pending
Links
- 238000005242 forging Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 title abstract description 6
- 238000005070 sampling Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000006073 displacement reaction Methods 0.000 claims abstract description 11
- 239000002131 composite material Substances 0.000 claims abstract description 6
- 238000013507 mapping Methods 0.000 claims abstract description 4
- 239000010425 asbestos Substances 0.000 claims description 7
- 229910052895 riebeckite Inorganic materials 0.000 claims description 7
- 238000012952 Resampling Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 238000003754 machining Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G06T5/73—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Abstract
The invention discloses a high-resolution high-temperature forging shape detection method, which comprises the following steps of: collecting a low-resolution image of a high-temperature forging to be detected; estimating the relative displacement between the low-resolution images according to the requirement; mapping a plurality of images obtained after displacement to a high-resolution grid so as to form a composite image consisting of sampling sample values in the grid; filling low-resolution image sampling information into a high-resolution image grid to obtain a reconstructed image; and removing the blur and noise in the reconstructed image to obtain a high-resolution image. The invention adopts a non-uniform interpolation method for obtaining the ultrahigh-resolution image to acquire the information of one pixel point for multiple times, and the information acquired for multiple times is superposed to obtain the pixel point with high resolution although the resolution of the image acquired for each time is lower.
Description
Technical Field
The invention belongs to the technical field of shape detection of high-temperature forgings, and particularly relates to a high-resolution shape detection method of a high-temperature forging.
Background
The national economic development strategy depends on some major large-scale equipment, wherein the forged piece is a key and core component of the key equipment, the quality of the forged piece is measured by the national industrial manufacturing level, and the improvement of the manufacturing level of the forged piece is particularly important.
The size and shape of the forging piece are important indexes which need to be detected in time in the production of the forging piece. The shape measurement is carried out in the machining process, the forging and pressing equipment and the machining process can be adjusted in time, and the machining precision and the machining efficiency are improved. However, the temperature of the forged piece is usually as high as 800-1000 ℃, and the measurement of the forged piece in such an environment has great difficulty.
The method is limited by the use environment and cost, and often only a few low-pixel forged piece images can be obtained, which has certain influence on the judgment of the size and shape of the forged piece. If a high pixel image can be generated from a low pixel image, the cost and efficiency problems can be better solved.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a method for detecting the shape of a high-resolution high-temperature forging aiming at the defects of the prior art, wherein a pixel point is subjected to multiple times of low-resolution image acquisition, and a plurality of acquired information of the same point are synthesized and superposed to generate a high-resolution image.
In order to achieve the technical purpose, the technical scheme adopted by the invention is as follows:
a high-resolution high-temperature forging shape detection method comprises the following steps:
step 1: collecting a low-resolution image of a high-temperature forging to be detected;
step 2: estimating the relative displacement between the low-resolution images according to the requirement;
and step 3: mapping a plurality of images obtained after displacement to a high-resolution grid so as to form a composite image consisting of sampling sample values in the grid;
and 4, step 4: filling low-resolution image sampling information into a high-resolution image grid to obtain a reconstructed image;
and 5: and removing the blur and noise in the reconstructed image to obtain a high-resolution image.
In order to optimize the technical scheme, the specific measures adopted further comprise:
the step 1 of acquiring the low-resolution image of the high-temperature forging to be measured specifically comprises the following steps: the high temperature forgings move on a conveyor belt, and a low resolution forgings image composed of a plurality of image points is formed through a perforated asbestos shield.
In step 2, motion estimation is performed on the low-resolution image to obtain registration parameters, which specifically include:
and (4) carrying out low pixel sampling points at the scale of the sub-pixels to obtain the sub-pixel displacement between the low pixel images.
In the step 3, a high pixel point in the composite image is a weighted sum of the low pixel sampling values.
And step 4, filling the low-resolution image sampling information into the high-resolution image grid through interpolation and resampling to obtain a reconstructed image.
In the step 5, the blur and noise in the reconstructed image are removed by wiener filtering, and a high-resolution image is obtained.
The invention has the following beneficial effects:
the invention adopts a non-uniform interpolation method for obtaining the ultrahigh-resolution image to acquire the information of one pixel point for multiple times, and the information acquired for multiple times is superposed to obtain the pixel point with high resolution although the resolution of the image acquired for each time is lower.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic diagram of a multiple acquisition synthesis in an embodiment of the present invention;
FIG. 3 is a transpose diagram of a high-temperature forging measured in the embodiment of the invention.
Detailed Description
Embodiments of the present invention are described in further detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for detecting the shape of the high-resolution high-temperature forging according to the present invention employs a non-uniform interpolation method to acquire information of a pixel point for multiple times, and superimposes the acquired information for multiple times to obtain a high-resolution pixel point although the resolution of an image acquired for each time is low, and specifically includes the following steps:
step 1: the method comprises the following steps of collecting a low-resolution image of a high-temperature forging to be detected, specifically: the high temperature forgings move on a conveyor belt, and a low resolution forgings image composed of a plurality of image points is formed through a perforated asbestos shield.
Step 2: estimating the relative displacement between the low-resolution images according to the requirement;
and step 3: mapping a plurality of images obtained after displacement to a high-resolution grid so as to form a composite image consisting of sampling sample values in the grid;
and 4, step 4: filling low-resolution image sampling information into a high-resolution image grid to obtain a reconstructed image;
and 5: and removing the blur and noise in the reconstructed image to obtain a high-resolution image.
The non-uniform interpolation method has the basic idea that an original high-resolution image is regarded as a continuous function, and a low-resolution observation image is formed by sampling at non-uniform positions on the continuous function of the high-resolution image, so that the reconstruction process of the high-resolution image can be regarded as inserting sampling points of the low-resolution observation image back to the original function.
In an embodiment, the three basic steps of non-uniform interpolation include:
1. performing motion estimation on the low-resolution image to obtain registration parameters;
2. interpolating the low-resolution image by using a non-uniform interpolation algorithm to obtain a high-resolution image;
3. deblurring and denoising treatment is carried out on high-resolution image
The motion estimation is performed by making low-pixel sampling points at a sub-pixel scale, and assuming that two low-resolution images f and g have a vertical translation a, a horizontal translation b and a rotation angle theta, the two low-resolution images can be expressed as g (x, y) ═ f (x · cos theta-y · sin theta + a, y · cos theta-x · sin theta + b)
The above formula is expanded by Taylor series, high-order terms are omitted, partial derivatives of a, b and theta are calculated, an equation set can be obtained, values of a, b and theta are calculated, and the size of sub-pixel displacement among low-pixel images can be obtained.
The obtained information of a series of low pixel images is complementary to the high pixel images, so that one high pixel point can be regarded as the weighted sum of low pixel sampling values, namely if the high pixel images are M, the weights are respectively L1And L2The solution of the weight can be obtained by nearest neighbor interpolation, then
M=L1·g+L2·f。
And the generated high-resolution image is subjected to deblurring and denoising treatment. The noise is mainly sensor blurring caused by the integration of the photosensitive sensor, additive noise introduced in the process of focusing and sampling of optical components, and the like, and the noise and blurring can be generally expressed by an idealized approximate model, so that the effect of removing the above influence can be realized by a classical wiener filter, and the effect of the noise is widely recognized.
As shown in fig. 2, the embodiment of the present invention is:
the high-temperature forge piece moves on the conveyor belt, a forge piece image consisting of a plurality of image points can be formed through the asbestos shield plate with the holes, if the image resolution is low, a new forge piece image can be obtained by changing the speed of the asbestos shield plate, and the first image and the second image information can be synthesized into a high-resolution image through the above formula.
Let the asbestos shield plate velocity be v1The obtained image information is Σ f1Changing the speed of the asbestos shield to v1+ Δ v, the obtained image information is Σ f2If the velocity becomes v1+2 Δ v, may yield Σ f3And the images can be clearer by increasing the acquisition times.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may be made by those skilled in the art without departing from the principle of the invention.
Claims (6)
1. The method for detecting the shape of the high-resolution high-temperature forging is characterized by comprising the following steps of:
step 1: collecting a low-resolution image of a high-temperature forging to be detected;
step 2: estimating the relative displacement between the low-resolution images according to the requirement;
and step 3: mapping a plurality of images obtained after displacement to a high-resolution grid so as to form a composite image consisting of sampling sample values in the grid;
and 4, step 4: filling low-resolution image sampling information into a high-resolution image grid to obtain a reconstructed image;
and 5: and removing the blur and noise in the reconstructed image to obtain a high-resolution image.
2. The method for detecting the shape of the high-resolution high-temperature forging piece according to claim 1, wherein the step 1 of acquiring the low-resolution image of the high-temperature forging piece to be detected specifically comprises the following steps: the high temperature forgings move on a conveyor belt, and a low resolution forgings image composed of a plurality of image points is formed through a perforated asbestos shield.
3. The method for detecting the shape of the high-resolution high-temperature forging piece according to claim 1, wherein in the step 2, motion estimation is performed on the low-resolution image to obtain registration parameters, and specifically:
and (4) carrying out low pixel sampling points at the scale of the sub-pixels to obtain the sub-pixel displacement between the low pixel images.
4. The method for detecting the shape of the high-resolution high-temperature forging piece according to claim 1, wherein in the step 3, a high pixel point in the composite image is a weighted sum of low pixel sampling values.
5. The method for detecting the shape of the high-resolution high-temperature forging according to claim 1, wherein in the step 4, a reconstructed image is obtained by filling low-resolution image sampling information into a high-resolution image grid through interpolation and resampling.
6. The method for detecting the shape of the high-resolution high-temperature forging piece according to claim 1, wherein in the step 5, the blurs and the noises in the reconstructed image are removed by adopting wiener filtering, so that the high-resolution image is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911097885.0A CN110827224A (en) | 2019-11-12 | 2019-11-12 | High-resolution high-temperature forging shape detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911097885.0A CN110827224A (en) | 2019-11-12 | 2019-11-12 | High-resolution high-temperature forging shape detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110827224A true CN110827224A (en) | 2020-02-21 |
Family
ID=69554136
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911097885.0A Pending CN110827224A (en) | 2019-11-12 | 2019-11-12 | High-resolution high-temperature forging shape detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110827224A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102651127A (en) * | 2012-04-01 | 2012-08-29 | 深圳市万兴软件有限公司 | Image processing method and image processing system for super-resolution reconstruction |
CN104034263A (en) * | 2014-07-02 | 2014-09-10 | 北京理工大学 | Non-contact measurement method for sizes of forged pieces |
CN105931210A (en) * | 2016-04-15 | 2016-09-07 | 中国航空工业集团公司洛阳电光设备研究所 | High-resolution image reconstruction method |
CN106920213A (en) * | 2017-01-19 | 2017-07-04 | 首都师范大学 | The acquisition methods and system of a kind of high-definition picture |
CN110211091A (en) * | 2019-04-25 | 2019-09-06 | 合刃科技(深圳)有限公司 | A kind of full resolution pricture reconstructing method, device and crack nondestructive detection system |
-
2019
- 2019-11-12 CN CN201911097885.0A patent/CN110827224A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102651127A (en) * | 2012-04-01 | 2012-08-29 | 深圳市万兴软件有限公司 | Image processing method and image processing system for super-resolution reconstruction |
CN104034263A (en) * | 2014-07-02 | 2014-09-10 | 北京理工大学 | Non-contact measurement method for sizes of forged pieces |
CN105931210A (en) * | 2016-04-15 | 2016-09-07 | 中国航空工业集团公司洛阳电光设备研究所 | High-resolution image reconstruction method |
CN106920213A (en) * | 2017-01-19 | 2017-07-04 | 首都师范大学 | The acquisition methods and system of a kind of high-definition picture |
CN110211091A (en) * | 2019-04-25 | 2019-09-06 | 合刃科技(深圳)有限公司 | A kind of full resolution pricture reconstructing method, device and crack nondestructive detection system |
Non-Patent Citations (1)
Title |
---|
张喜英: "高温锻件红外图像增强的算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110310227B (en) | Image super-resolution reconstruction method based on high-low frequency information decomposition | |
CN112254801B (en) | Micro-vibration vision measurement method and system | |
CN107478657A (en) | Stainless steel surfaces defect inspection method based on machine vision | |
CN102494675B (en) | High-speed visual capturing method of moving target features | |
CN110084127B (en) | Vision-based magnetic suspension rotor vibration measurement method | |
CN104458766B (en) | A kind of cloth surface flaw detection method based on structural texture method | |
CN104933678B (en) | A kind of image super-resolution rebuilding method based on image pixel intensities | |
CN107564091A (en) | A kind of three-dimensional rebuilding method and device based on quick corresponding point search | |
CN112347992B (en) | Remote sensing estimation method for time sequence AGB in desert area | |
CN102155933B (en) | Method for measuring galloping of transmission conductor on the basis of video difference analysis | |
CN112927135A (en) | Edge perception-based polarized image interpolation method | |
CN111353400A (en) | Whole scene vibration intensity atlas analysis method based on visual vibration measurement | |
CN110827224A (en) | High-resolution high-temperature forging shape detection method | |
CN103914807B (en) | Non-locality image super-resolution method and system for zoom scale compensation | |
CN101917624B (en) | Method for reconstructing high resolution video image | |
CN108918654A (en) | A kind of processing of wirerope radial direction magnetic leakage signal and imaging method | |
Zhu et al. | A visual measurement method of structural body vibration displacement combined with image deblurring | |
CN111369483B (en) | Method for generating high-spatial-temporal-resolution remote sensing data by fusing multi-source remote sensing data | |
CN116734980A (en) | Non-contact type mechanical vibration monitoring and fault diagnosis method based on event camera | |
CN103903235A (en) | Cell image super-resolution reconstruction method | |
CN110033469A (en) | A kind of sub-pixel edge detection method and system | |
CN109785268A (en) | A kind of underwater image restoration method based on double-spectrum analysis optimization algorithm | |
Zou et al. | Iterative Denoiser and Noise Estimator for Self-Supervised Image Denoising | |
CN107292839B (en) | TDI flutter image restoration method based on image block self-adaptive adjustment | |
CN112884750B (en) | GPU-based plain color fabric crease extraction method |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200221 |
|
RJ01 | Rejection of invention patent application after publication |