CN115063311B - Star map tailing straight line rapid removal method - Google Patents
Star map tailing straight line rapid removal method Download PDFInfo
- Publication number
- CN115063311B CN115063311B CN202210661236.4A CN202210661236A CN115063311B CN 115063311 B CN115063311 B CN 115063311B CN 202210661236 A CN202210661236 A CN 202210661236A CN 115063311 B CN115063311 B CN 115063311B
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- straight line
- tailing
- neighborhood
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 abstract description 5
- 230000010365 information processing Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000007796 conventional method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method for quickly removing a star map trailing straight line. Firstly, calculating the gray mean value, variance and the maximum value of the pixels of an image; then constructing a three-band characteristic image; calculating trailing straight line pixel candidate points for the three-band characteristic image to form a trailing candidate binary image; removing isolated points from the tail candidate binary image; carrying out trailing straight line statistics on the binary images of the continuous areas; and finally, removing the trailing straight line by using a neighborhood interpolation method. According to the invention, statistics is carried out through the target distribution rule, the tailing linear targets are screened, the inclined tailing and the vertical tailing can be detected simultaneously, meanwhile, the tailing targets of batch data can be detected in batches, and the calculated amount is greatly reduced. In addition, the invention adopts column pixel statistical information to remove the tailing target, can adapt to the characteristic of nonuniform tailing, and is simple and effective. The method only comprises addition, subtraction and shift operation, so that the time cost of a real-time information processing system can be reduced, and the real-time requirement of a preprocessing stage can be met.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a star map tailing straight line rapid removal method.
Background
The technology of modern photoelectric telescope is developed rapidly, and the detection capability of the equipment is improved continuously. The trailing phenomenon in the star map brings great pressure to the precision and timeliness of astronomical positioning processing. The star map has low contrast and uneven background intensity distribution, and the problem of how to remove trailing straight-line noise and keep the target information and the target positioning accuracy of the star map is challenging.
When the star image tailing is that the full frame CCD transfers signal charge, the light leakage charge generated by the high brightness shooting object at the CCD integration time is mixed with the signal charge transmitted by the CCD. In the astronomical photoelectric observation system for a long time, the mechanical shutter of the CCD camera is easy to damage under the condition of high-strength frequent opening and closing, and the service life of the mechanical shutter is limited, so that the maintenance cost of the astronomical photoelectric observation system is increased, the mechanical shutter is in a normally open state or is directly dismantled, when the mechanical shutter is not used, the photosensitive element is still in a photosensitive state in the process of exposing charge transfer and erasure, and then the photosensitive element can influence the signal charge transferred to the photosensitive element at the back, so that the tailing phenomenon in a CCD image is quite serious.
The occurrence of tailing phenomenon can reduce image quality, increase image processing difficulty, influence detection and positioning of targets, and further influence continuous tracking and information extraction of follow-up moving targets. According to the characteristics of the star map, the star tailing phenomenon needs to be processed in the preprocessing stage. However, since the star map data size in the preprocessing stage is large, the computing overhead of the real-time information processing system is obviously reduced while the star map image quality is improved, and therefore, the most important requirement of the smear removal algorithm is that the algorithm is relatively simple and effective. In general, the conventional smear removal method needs to detect and remove vertical smear and inclined smear respectively, has no uniform removal method, and needs exposure information of a known CCD camera, so that the algorithm is time-consuming.
Disclosure of Invention
In view of the above, the invention provides a method for quickly removing the trailing straight line of a star map, which has good effect, is easy to realize, has lower calculation complexity, can effectively remove the trailing straight line, can reduce the false alarm probability of space target detection, and improves the astronomical positioning precision of the space target.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a star map tailing straight line rapid removal method comprises the following steps:
step 1, reading the gray value u of each pixel point of the image with the image size m×n (x,y) X=1, 2, m, y=1, 2, n, the mean u, variance σ, maximum p, minimum q of the pixel gray values are counted;
step 2, traversing each pixel point of the image, respectively calculating 8 neighborhood pixel sums and 8 neighborhood pixel differences of each pixel point to obtain 8 neighborhood pixel sum images and 8 neighborhood pixel difference images, and forming three-band characteristic images by the original image, the 8 neighborhood pixel sum images and the 8 neighborhood pixel difference images;
step 3, calculating trailing straight line pixel candidate points for the three-band characteristic image in the step 2 according to the mean value u, the variance sigma, the maximum value p and the minimum value q obtained in the step 1, and forming a trailing candidate binary image;
step 4, removing isolated points from the tailing candidate binary image in the step 3; traversing each pixel point of the image, setting the pixel value of the pixel with the brightness of 1 as 0 if all 8 neighborhood pixels of the pixel are zero, and forming a continuous area binary image; at this time, all pixels with the brightness of 1 in the image have at least one neighborhood pixel with the brightness of 1;
step 5, carrying out trailing straight line statistics on the continuous area binary image; the method comprises the following steps: the pixel point with 1 pixel in the image is marked as (x 0, y 0), the pixel point with 1 pixel in the neighborhood pixel is marked as (x 1, y 1), the neighborhood pixel with (x 1, y 1) is searched, marking the pixel with the gray value of 1 as (x 2, y 2), searching the pixel with the pixel of 1 in the neighborhood pixels of (x 2, y 2), and the like until all the connected pixel points are marked; for the searched connected pixel points, if the number of the pixel points is not less than a threshold value, determining the connected pixel points as trailing straight line pixel points, wherein the connected pixel points in the original image corresponding to the trailing straight line pixel points are trailing straight lines in the original image;
and 6, processing the tailing straight line in the original image by using a neighborhood interpolation method, so as to remove the tailing straight line in the original image.
Further, the threshold value in step 5 is 8 to 12.
Further, the specific mode of the step 3 is as follows:
(3.1) comparing the pixel value of the original image of the three-band characteristic image with lambda 1 Is assigned 1 and the remaining pixels are assigned 0, where lambda 1 ＝u+σ；
(3.2) setting the pixel value of the original image processed in the step (3.1) to be 1, and setting the pixel value of the corresponding pixel point in the 8 neighborhood pixel and the pixel value in the image to be [ lambda ] 2 ,λ 3 ]The pixel points in the range are assigned 1, and the rest pixel points are assigned 0, wherein lambda 2 ＝8u+2σ，λ 3 ＝2p+6σ；
(3.3) setting the pixel value of the original image processed in the step (3.2) to be 1, and setting the pixel value of the corresponding pixel point in the 8-neighborhood pixel difference image to be [ lambda ] 4 ,λ 5 ]The pixel points in the range are assigned 1, and the rest pixel points are assigned 0, wherein lambda 4 ＝6σ，λ 5 ＝2p-2u+6σ。
The invention has the following advantages:
1. the invention provides a star map tailing straight line rapid removal method, which is used for counting through a pixel gray level distribution rule, screening tailing straight line targets, simultaneously detecting inclined tailing and vertical tailing, simultaneously detecting tailing targets of batch data in batches and greatly reducing the calculated amount.
2. The method only carries out addition, subtraction and shift (average value calculation) operation, can reduce the time cost of a real-time information processing system and meets the real-time requirement of a preprocessing stage.
In a word, the invention realizes the rapid detection of the trailing target straight line of the single frame image through the star map target information statistics rule, and the removal of the star map trailing straight line is rapidly completed by utilizing the interpolation technology, thereby eliminating the interference of the trailing on the detection of the space target, reducing the false alarm probability generated by the trailing and improving the astronomical positioning precision of the space target.
Drawings
Fig. 1 is a diagram of typical elements of a star chart.
Fig. 2 is a schematic view of vertical tailing.
Fig. 3 is a schematic view of a sloped tailing.
FIG. 4 is a schematic diagram of a trailing straight line and a spatial target neighborhood distribution.
Fig. 5 is an overall flow chart of a method according to an embodiment of the invention.
FIG. 6 is a graph showing the result of removing the tailing straight line in the method of the embodiment of the present invention.
Detailed Description
The invention will be described in further detail with reference to the accompanying drawings and examples of implementation.
In the sidereal tracking shooting mode, for a relatively stationary sidereal object, a complete tail is formed in the upper and lower sides of the sidereal object, which is called as vertical tail or sidereal tail, as shown in fig. 2 and 3; for a relatively moving spatial target, an oblique tail, referred to as "oblique tail" or "target tail", is formed due to the high angular velocity of the target movement. As shown in fig. 1 and 2. The detection and removal of vertical tailing are relatively simple, but the removal of inclined tailing is complex because of the relative motion, certain displacement and inclination exist. In general, the conventional method for removing the smear needs to detect and remove the vertical smear and the inclined smear respectively, and has no unified removal method, and the inclined smear is mostly detected by a conventional method of Canny operator+Hough transformation, by detecting all the edges of the smear straight line, reducing the detection range, and then performing Hough straight line detection in the edge detection range. The Hough algorithm is a common method for straight line detection in the field of image processing, is suitable for natural images with richer features, and has lower processing precision and time consumption for star images with single features, and requires exposure information of known CCD cameras, so that the calculation is complex.
The star map tailing straight line rapid removal method is adopted in the embodiment, the image tailing target rapid detection is achieved through statistics of the image target distribution rule, meanwhile, vertical tailing and inclined tailing can be detected and removed, the calculation complexity is reduced, and the star map tailing straight line rapid removal method has important engineering application value.
The star map image of the present embodiment is a sequence image taking deep space as background and captured by a large-field-of-view base optical telescope, and its image elements mainly include a spatial target, a star target, a tailing target, a deep space background and noise, and the tailing linear target is different from the star and the spatial target, as shown in fig. 1. The distribution of trailing straight lines and spatial target neighborhoods is shown in fig. 4, and the distribution rule can be summarized as follows:
(1) The space target and the star represent brighter spots, the pixel number is 5-8, the pixel value of each point is larger than a certain gray threshold;
(2) The background is a dark deep space background, and the pixel value is generally lower than a certain gray threshold;
(3) The projection length of the trailing target straight line in the horizontal direction is 1-2 pixels, and the length of the trailing target straight line in the inclined direction of the pixel number is at least 10 pixels.
Referring to fig. 5, the specific implementation steps of this embodiment are as follows:
step 1, obtaining image parameters: the total line number m=1024 and the line width n=1024 of the image, in order to facilitate the image display, the original 16bit image is converted into 8bit image gray value range (0, 255), and the image average value is calculated
Variance->
Maximum p, minimum q;
step 2, traversing the image, and respectively calculating 8 neighborhood pixels and:
8 neighborhood pixel difference:
combining an original image, an image formed by 8 neighborhood pixels and 8 neighborhood pixel differences as three wave bands of the image to form a three-wave band characteristic image, wherein the three wave bands are respectively marked as a, b and c;
step 3, calculating trailing straight line pixel candidate points for the three-band characteristic image in the step 2 in the following manner to form a trailing candidate binary image;
(3.1) comparing the value of the a-band pixel in the characteristic image with lambda 1 Is marked 1 and the remaining pixels are marked 0, where lambda 1 ＝u+σ；
(3.2) the pixel value in the a-band processed in the step (3.1) is 1, and the pixel value of the corresponding point in the b-band is [ lambda ] 2 ,λ 3 ]The pixel values within the range are marked 1 and the remaining pixels are marked 0, where lambda 2 ＝8u+2σ，λ 3 ＝2p+6σ；
(3.3) the pixel value in the a-band processed in the step (3.2) is 1, and the pixel value of the corresponding point in the c-band is [ lambda ] 4 ,λ 5 ]The pixel values within the range are marked 1 and the remaining pixels are marked 0, where lambda 4 ＝6σ，λ 5 ＝2p-2u+6σ。
Step 4, removing isolated points from the tailing candidate binary image in the step 3, traversing the image, setting the pixel value to 0 if the neighborhood pixels of the pixel with the brightness of 1 are zero, and forming a continuous area binary image, wherein at least one neighborhood pixel with the brightness of 1 exists in all the pixels with the brightness of 1 in the image;
and 5, carrying out trailing straight line statistics on the continuous area binary image. For the pixel with 1 in the image, the pixel is marked as (x 0, y 0), the pixel with 1 in the neighborhood pixel is marked as (x 1, y 1), the neighborhood pixel is searched for (x 1, y 1), the pixel with 1 gray scale value is marked as (x 2, y 2), the pixel with 1 in the neighborhood pixel is searched for (x 2, y 2), and the like until all the connected pixels are marked; the pixel points adjacent to each other with 10 or more consecutive pixels are determined as a tailing straight line.
And 6, removing the trailing straight line by using methods such as neighborhood interpolation and the like.
The effect of this embodiment can be further illustrated by the following test:
1. test conditions.
The computer is configured as Intel Core i7-3770 CPU 3.4Ghz,4GB memory, and the software environment is Matlab R2013.
2. Test methods.
The experiment adopts Hough transformation and the method of the embodiment to carry out trailing linear targets and respectively carry out star map trailing linear target extraction, and the calculation time of the two methods is statistically compared aiming at 8 frames 1024 x 1024 size images; then, a uniform tailing removal method is adopted, and the removal result is shown in fig. 6.
3. Test results.
Under single thread, the time for single-frame tailing target removal by using the method of the embodiment is 0.71s, and the time for single-frame tailing target removal by Hough transformation is 4.83s. It can be seen that, on the premise of not increasing computing resources, the method of the embodiment can greatly reduce computing complexity and improve computing efficiency.
As can be seen from the tailing processing result in fig. 6, most of tailing straight lines in the star map can be removed by the method in the embodiment, meanwhile, target information can be reserved, the image quality is obviously improved, and the method has obvious advantages compared with a Hough transformation method.
In a word, the invention uses the gray statistical information of the star map to quickly remove the trailing straight line according to the characteristics of the star map. According to the method, statistics is carried out through a target distribution rule, tailing linear targets are screened, inclined tailing and vertical tailing can be detected simultaneously, meanwhile, batch detection of tailing targets of batch data can be carried out, and the calculated amount is greatly reduced. In addition, the invention adopts column pixel statistical information to remove the tailing target, can adapt to the characteristic of nonuniform tailing, and is simple and effective. The method only comprises addition, subtraction and shift operation, so that the time cost of a real-time information processing system can be reduced, and the real-time requirement of a preprocessing stage can be met.
Claims (3)
1. A star map tailing straight line rapid removal method is characterized by comprising the following steps:
step 1, reading an imageSize m×n and gray value u of each pixel point of image (x,y) X=1, 2, m, y=1, 2, n, the mean u, variance σ, maximum p, minimum q of the pixel gray values are counted;
step 2, traversing each pixel point of the image, respectively calculating 8 neighborhood pixel sums and 8 neighborhood pixel differences of each pixel point to obtain 8 neighborhood pixel sum images and 8 neighborhood pixel difference images, and forming three-band characteristic images by the original image, the 8 neighborhood pixel sum images and the 8 neighborhood pixel difference images;
step 3, calculating trailing straight line pixel candidate points for the three-band characteristic image in the step 2 according to the mean value u, the variance sigma, the maximum value p and the minimum value q obtained in the step 1, and forming a trailing candidate binary image;
step 4, removing isolated points from the tailing candidate binary image in the step 3; traversing each pixel point of the image, setting the pixel value of the pixel with the brightness of 1 as 0 if all 8 neighborhood pixels of the pixel are zero, and forming a continuous area binary image; at this time, all pixels with the brightness of 1 in the image have at least one neighborhood pixel with the brightness of 1;
step 5, carrying out trailing straight line statistics on the continuous area binary image; the method comprises the following steps: the pixel point with 1 pixel in the image is marked as (x 0, y 0), the pixel point with 1 pixel in the neighborhood pixel is marked as (x 1, y 1), the neighborhood pixel with (x 1, y 1) is searched, marking the pixel with the gray value of 1 as (x 2, y 2), searching the pixel with the pixel of 1 in the neighborhood pixels of (x 2, y 2), and the like until all the connected pixel points are marked; for the searched connected pixel points, if the number of the pixel points is not less than a threshold value, determining the connected pixel points as trailing straight line pixel points, wherein the connected pixel points in the original image corresponding to the trailing straight line pixel points are trailing straight lines in the original image;
and 6, processing the tailing straight line in the original image by using a neighborhood interpolation method, so as to remove the tailing straight line in the original image.
2. The method for quickly removing the trailing straight line of the star map according to claim 1, wherein the threshold value in the step 5 is 8-12.
3. The method for quickly removing the trailing straight line of the star map according to claim 1, wherein the specific mode of the step 3 is as follows:
(3.1) comparing the pixel value of the original image of the three-band characteristic image with lambda 1 Is assigned 1 and the remaining pixels are assigned 0, where lambda 1 ＝u+σ；
(3.2) setting the pixel value of the original image processed in the step (3.1) to be 1, and setting the pixel value of the corresponding pixel point in the 8 neighborhood pixel and the pixel value in the image to be [ lambda ] 2 ,λ 3 ]The pixel points in the range are assigned 1, and the rest pixel points are assigned 0, wherein lambda 2 ＝8u+2σ，λ 3 ＝2p+6σ；
(3.3) setting the pixel value of the original image processed in the step (3.2) to be 1, and setting the pixel value of the corresponding pixel point in the 8-neighborhood pixel difference image to be [ lambda ] 4 ,λ 5 ]The pixel points in the range are assigned 1, and the rest pixel points are assigned 0, wherein lambda 4 ＝6σ，λ 5 ＝2p-2u+6σ。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210661236.4A CN115063311B (en) | 2022-06-13 | 2022-06-13 | Star map tailing straight line rapid removal method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210661236.4A CN115063311B (en) | 2022-06-13 | 2022-06-13 | Star map tailing straight line rapid removal method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115063311A CN115063311A (en) | 2022-09-16 |
| CN115063311B true CN115063311B (en) | 2023-05-05 |
Family
ID=83200904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210661236.4A Active CN115063311B (en) | 2022-06-13 | 2022-06-13 | Star map tailing straight line rapid removal method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115063311B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115661122B (en) * | 2022-11-14 | 2024-01-12 | 南京图格医疗科技有限公司 | Image grid pattern removing method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957058A (en) * | 2016-04-21 | 2016-09-21 | 华中科技大学 | Preprocessing method of star map |
| CN107449416A (en) * | 2017-06-20 | 2017-12-08 | 中国人民解放军国防科学技术大学 | Fixed star hangover asterism extracting method based on vector accumulation |
| CN112465712A (en) * | 2020-11-09 | 2021-03-09 | 华中光电技术研究所（中国船舶重工集团公司第七一七研究所） | Motion blur star map restoration method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11830246B2 (en) * | 2020-05-01 | 2023-11-28 | CACI, Inc.—Federal | Systems and methods for extracting and vectorizing features of satellite imagery |
-
2022
- 2022-06-13 CN CN202210661236.4A patent/CN115063311B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957058A (en) * | 2016-04-21 | 2016-09-21 | 华中科技大学 | Preprocessing method of star map |
| CN107449416A (en) * | 2017-06-20 | 2017-12-08 | 中国人民解放军国防科学技术大学 | Fixed star hangover asterism extracting method based on vector accumulation |
| CN112465712A (en) * | 2020-11-09 | 2021-03-09 | 华中光电技术研究所（中国船舶重工集团公司第七一七研究所） | Motion blur star map restoration method and system |
Non-Patent Citations (5)
| Title |
|---|
| Denoising star map data via sparse representation and dictionary learning;Zhou Mingyuan;《Optik》;第126卷(第11-12期);1133-1137 * |
| 基于CCD拖尾特性的空间目标单帧检测方法;董文娟;王宏义;黄宗福;陈曾平;;信号处理(第05期);807-810 * |
| 基于卷积曲面的动态实时星图模拟;闫劲云;刘慧;赵伟强;江洁;;北京航空航天大学学报(第04期);681-686 * |
| 基于能量函数的极值中值滤波星图去噪算法;王敏;赵金宇;陈涛;崔博川;高扬;;电子与信息学报(第06期);1387-1393 * |
| 星空观测图像目标拖尾的自动消除;张健;任建存;张春华;;应用光学(第01期);62-67 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115063311A (en) | 2022-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112884064B (en) | Target detection and identification method based on neural network | |
| CN103543394A (en) | Discharge ultraviolet imaging quantization parameter extraction method of high-voltage electric equipment | |
| CN111967498A (en) | Night target detection and tracking method based on millimeter wave radar and vision fusion | |
| US20060067569A1 (en) | Image inspection device, image inspection method, and image inspection program | |
| CN103810722A (en) | Moving target detection method combining improved LBP (Local Binary Pattern) texture and chrominance information | |
| CN111965636A (en) | Night target detection method based on millimeter wave radar and vision fusion | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN115063311B (en) | Star map tailing straight line rapid removal method | |
| AU2020272936B2 (en) | Methods and systems for crack detection using a fully convolutional network | |
| CN111008632A (en) | License plate character segmentation method based on deep learning | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN115131354A (en) | Laboratory plastic film defect detection method based on optical means | |
| CN115131346B (en) | Fermentation tank processing procedure detection method and system based on artificial intelligence | |
| TWI729587B (en) | Object localization system and method thereof | |
| CN109872315B (en) | Method for detecting stray light uniformity of optical astronomical telescope in real time | |
| CN113286142B (en) | Artificial intelligence-based image imaging sensitivity prediction method and system | |
| CN113971681A (en) | Edge detection method for belt conveyor in complex environment | |
| JP2006309650A (en) | Number recognition device and method | |
| CN112330618B (en) | Image offset detection method, device and storage medium | |
| CN108830834B (en) | Automatic extraction method for video defect information of cable climbing robot | |
| CN111626104A (en) | Cable hidden danger point detection method and device based on unmanned aerial vehicle infrared thermal imagery | |
| CN115082504B (en) | Light spot identification method for solar photovoltaic panel | |
| CN113284066B (en) | Automatic cloud detection method and device for remote sensing image | |
| Kang et al. | Specular highlight region restoration using image clustering and inpainting | |
| CN111583341B (en) | Cloud deck camera shift detection 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |