CN115908201B - Method and device for quickly correcting hot zone of image distortion - Google Patents
Method and device for quickly correcting hot zone of image distortion Download PDFInfo
- Publication number
- CN115908201B CN115908201B CN202310024490.8A CN202310024490A CN115908201B CN 115908201 B CN115908201 B CN 115908201B CN 202310024490 A CN202310024490 A CN 202310024490A CN 115908201 B CN115908201 B CN 115908201B
- Authority
- CN
- China
- Prior art keywords
- curve
- image
- hot zone
- broken line
- area
- 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 31
- 230000009466 transformation Effects 0.000 claims abstract description 40
- 238000003708 edge detection Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000226585 Antennaria plantaginifolia Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention is applicable to the technical field of image processing, and provides a method and a device for quickly correcting a hot zone of image distortion, wherein the method comprises the following steps: s1, searching an edge at an expected position of an image through edge detection, and forming a fitting curve according to the edge; s2, obtaining a target hot zone according to the fitting curve; s3, dividing the target hot zone into a plurality of areas; and S4, performing perspective transformation on each area to obtain a distortion correction image of the hot zone. The invention divides the heat area into a plurality of areas, uses a plurality of continuous polygons to carry out continuous perspective transformation to achieve the effect of correcting the image distortion, and has the advantages of higher speed and good real-time performance of the distortion correction as no relatively complex operation such as calibration is needed.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a method and a device for quickly correcting a hot zone of image distortion.
Background
The optical system of the shooting terminal such as a camera does not work precisely according to the principle of idealized pinhole imaging, perspective distortion exists, and an optical distortion error exists between actual imaging and ideal imaging of an object on an imaging surface of the shooting terminal, so that the situations of image distortion, including pincushion distortion, barrel distortion and the like, exist in an actually output video and image.
The root cause of image distortion is that the magnification of the central region of the lens is inconsistent with that of the peripheral region, and the magnification of the central region of the lens is larger than that of the peripheral region. In the prior art, there is a technology for performing perspective distortion correction of a lens based on a physical distance and a physical direction, wherein a plurality of images are shot through focusing of the lens, then the images are analyzed to judge a focus calculation distance, and then perspective distortion correction is performed on the images by utilizing a distance parameter.
Therefore, the essence of the current general processing method for image distortion is to perform a series of coordinate transformations, and relatively complex operations such as image calibration and the like are required, including the use of a calibration plate and the like. Especially for the occasion that the user is required to calibrate the image in the use of the product, the professional requirement on the user is higher, the complexity of the use of the product is increased, and the use is not friendly; in different application occasions, calibration is needed, and a larger threshold is formed on the aspects of product usability and market popularization.
In practical applications, the purpose of correcting the distortion of the image is often to identify or further process the image of the interested hot zone (ROI, region of interest), for example, in places such as a high-speed toll station, a logistics toll post, etc., the vehicle type identification only needs to identify the target vehicle therein, the hot zone is the area where the target vehicle is located, and the normally displayed target vehicle can be obtained by correcting the distortion of the hot zone, so that the subsequent further image identification or processing is facilitated. Therefore, in some occasions, only the hot area in the image needs to be subjected to quick distortion correction, and the purpose of image distortion correction can be achieved.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a method and a device for quickly correcting a hot zone of an image distortion, which aims to solve the technical problems of high operation complexity and difficult use of the existing image distortion correction scheme.
The invention adopts the following technical scheme:
in one aspect, the method for quickly correcting the hot zone of the image distortion comprises the following steps:
s1, searching an edge at an expected position of an image through edge detection, and forming a fitting curve according to the edge;
s2, obtaining a target hot zone according to the fitting curve;
s3, dividing the target hot zone into a plurality of areas;
and S4, performing perspective transformation on each area to obtain a distortion correction image of the hot zone.
In another aspect, the apparatus for rapidly correcting a hot zone of an image distortion includes:
the edge detection unit is used for searching an edge through edge detection at an expected position of the image and forming a fitting curve according to the edge;
the hot zone generating unit is used for obtaining a target hot zone according to the fitting curve;
the area dividing unit is used for dividing the target hot area into a plurality of areas;
and the perspective transformation unit is used for carrying out perspective transformation on each area to obtain a distortion correction image of the hot zone.
The beneficial effects of the invention are as follows: the invention finds the edge deformation of straight line, quadrangle or polygon caused by distortion in the camera view, then divides the hot zone, and realizes the correction of image distortion from the practical effect through the continuous perspective transformation of polygon; the method of the invention does not need to carry out the relative complex operations such as camera calibration, etc., has high image distortion correction processing speed and low requirement on hardware, and the related products of the scheme used by users have the characteristics of simple use and strong functions, and the distortion correction speed is faster, the real-time performance is good, the cost of camera hardware can be reduced, and the method is suitable for wide popularization and use.
Drawings
FIG. 1 is a flow chart of a method for hot zone rapid correction of image distortion provided by an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating selection of polyline points according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a division of the target hot zone;
FIG. 4 is a schematic diagram of a two-division of the target hot zone;
FIG. 5 is a schematic view of a target rectangle obtained by perspective transformation of each region under a division;
fig. 6 is a block diagram of a device for quickly correcting image distortion in a hot zone according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The camera is fixed, so that the correction of image distortion is to realize a better visual effect or to be beneficial to more accurately identifying an image target;
in order to illustrate the technical scheme of the invention, the following description is made by specific examples.
Embodiment one:
as shown in fig. 1 and 2, the method for quickly correcting the image distortion in the hot zone according to the present embodiment includes the following steps:
and S1, searching an edge at an expected part of the image through edge detection, and forming a fitting curve according to the edge.
The invention is applied to image distortion correction of local areas in the occasion of camera fixation. Because of the fixed scene, distortion of straight lines, quadrilaterals or polygons due to distortion causes is easily found in the camera field of view. For example, in an actual application scene, the expected part can be the upper part, the lower part, the left part and the right part of the original image, and the deformation of the periphery part of the image distortion, whether pillow-shaped or barrel-shaped, is larger. Therefore, the step needs to search the edge through edge detection in a preset area, select a plurality of points on the edge, and perform curve fitting by adopting a least square method to obtain a fitting curve.
In a practical scenario, the optional edges include road edges, building edges, target edges, and the like. For example, in the vehicle entrance management, the safety island edge detection or the road shoulder edge detection is a feasible scheme, and even for a van, the carriage edge can be used as a detection object. The specific edge detection algorithm is not described herein, and is within the protection scope of this embodiment, for example, a Sobel or Canny operator may be used to detect edges.
Then selecting N points on the edge to perform curve fitting. In this embodiment, a least square method is used, and the least square method is a common method for solving the problem of curve fitting. Data point P selected for a given edge i (x i ,y i ) The i maximum value is selected to be N, so thatThe deviation of the approximation curve y=phi (x) from the actual edge y=f (x) is minimal. The approximate curve is at point P i (x i ,y i ) Deviation delta at i =φ(x i )- f(x i ) Delta, i.e i =φ(x i )- y i I=1, 2,..n, fitting according to the method where the sum of absolute values is minimum, the specific procedure is not repeated.
For example, in fig. 2, 9 points are selected, namely hollow dots in the figure, and a graph fitting curve is obtained after fitting. The curve selected and generated at the upper part of the original image is an upper fitting curve, and the curve is a lower fitting curve at the lower part.
And S2, obtaining a target hot zone according to the fitting curve.
Firstly, selecting a plurality of broken line points on a fitting curve, wherein the number of the broken line points is between 1 and N, as shown in fig. 2, and assuming that 5 edge points are selected, namely P1-P5. In this embodiment, the selection requirement of the polyline point is that, for the current polyline point, the angle formed between the line connecting the polyline point and the next polyline point and the circumscribed line of the current polyline point is within the angle threshold. For example, the tangent line of the line segment P1P2 and the point P1 in the illustration forms +.α1, the tangent line of the line segment P2P3 and the point P2 forms +.α2, the tangent line of the line segment P3P4 and the point P3 forms +.α3, the tangent line of the line segment P4P5 and the point P4 forms +.α4, and the four angles are all within the angle threshold range, for example, can be set to be between 5 ° and 15 °. The angular threshold range may also be set to a specific angular value, such as β=10°.
As an implementation manner, during specific operation, a first broken line point P1 of a fitting curve is selected, an external tangent line of the curve is generated starting from the point P1, sliding forwards along the point P1 on the fitting curve, searching for a point P2 on the fitting curve, and if the angle +.α1 between the line P1P2 and the external tangent line of the point P1 is equal to β, the current P2 position is fixed, i.e. the point P1 and the point P2 are the two broken line points on the selected fitting curve.
Continuing to operate, generating the circumscribed line from the point P2, sliding the point P3 forwards from the point P2, enabling the angle alpha 2 between the line P2P3 and the circumscribed line of the point P1 to be equal to beta, searching for a third broken line point P3 at the moment, positioning the point P3 after the angle is met, and then continuing to search for P4 and P5 until the tail of the fitted curve is finished. The end point of the tail end of the fitting curve can be directly used as the broken line point of the tail end.
The above manner is just a selection manner of the broken line points, and other manners may be adopted, for example: the angle formed between the circumscribed lines of the adjacent broken line points is in the angle threshold range, namely the angles of the outer tangent line of P1 and the outer tangent line of P2 meet the angle threshold range requirement.
The target hot zone is in the area where distortion correction is needed, and the target to be processed is in the target hot zone. In this embodiment, the target thermal zone is generated by fitting a curve. As one mode, a symmetrical curve of the fitting curve is generated in the image by taking the central axis of the image as an axis, and the area between the fitting curve and the symmetrical curve is a target hot area. For example, the upper fitted curve currently fitted generates a symmetric curve with the lateral center axis of the image. If the current fitting is a left fitting curve, a symmetrical curve is generated with the vertical center axis of the image.
Of course, the upper and lower edges can be obtained by edge detection directly at the upper and lower parts, and the upper and lower edges are used as fitting treatment to obtain two fitting curves.
And S3, dividing the target hot zone into a plurality of areas.
Dividing the target hot zone into a plurality of areas by the broken line point location boundary in the step S2.
Dividing mode one:
as shown in fig. 3, the target hot zone is divided into a plurality of zones according to the fitted curve, the symmetrical curve, the central axis of the image (i.e., the transverse dotted line in the drawing) and the broken line point connecting line. In the illustration, the upper fitting curve is selected, and the symmetry automatically generates the lower symmetry curve.
P1-P5 are 5 broken line points of the fitting curve, projection points P1', P2', … and P5 'on the symmetrical curve are found according to P1, P2 and … P5, and the intersection points of the connecting lines of the broken line points and the projection points and the central axis are P1', P2', … and P5'.
The target hot zone thus divides into eight polygonal areas R1-R8, as follows:
quadrilateral R1: p1→p2→p2'→p1';
quadrilateral R2: p2→p3→p3'→p2';
quadrilateral R3: p3→p4→p4'→p3';
quadrilateral R4: p4→p5→p5'→p4';
quadrilateral R5: p1' →p2"→p1";
quadrilateral R6: p2' →p3"→p2";
quadrilateral R7: p3' →p4"→p3";
quadrilateral R8: p4' →p5"→p4".
The second division mode is as follows:
as shown in fig. 4, the target hot zone is divided into a plurality of zones according to the fitted curve, the symmetrical curve, the central axis of the image (i.e., the transverse dotted line in the drawing) and the broken line point connecting line. P1-P5 are 5 polyline points of the fitted curve, and projection points P1', P2', … and P5' on the symmetrical curve are found according to P1, P2 … P5.
The target hot zone thus divides into eight polygonal areas R1-R8, as follows:
quadrilateral R1: p1→p2→p2"→p1";
quadrilateral R2: P2→P3→P3"→P2";
quadrilateral R3: p3→p4→p4"→p3";
quadrilateral R4: p4→p5→p5"→p4".
And S4, performing perspective transformation on each area to obtain a distortion correction image of the hot zone.
And setting a target rectangle width according to the width of the original quadrilateral region aiming at the correction of each region, namely keeping the width of the region unchanged, performing perspective transformation in the height direction of the broken line point connecting line to obtain corresponding target rectangles, setting the whole target rectangles to be equal in height during perspective transformation, and finally obtaining a distortion correction image of the hot region. Therefore, after perspective transformation is performed on the 8 polygonal areas R1-R8 in the first division manner, a hot zone image after distortion correction as shown in fig. 5 is obtained, and in the figure, the target rectangles R1'-R8' are respectively obtained by perspective transformation of the polygonal areas R1-R8.
The perspective transformation adopts a three-dimensional coordinate system, and the transformation matrix is calculated, and the coordinates of 4 corresponding points are selected for transformation. Perspective transformation is a well-known technique and will not be described in detail here. Whereas affine transformation is a special perspective transformation, it is also possible to transform polygonal areas into target rectangles with affine transformation in some cases of actual image distortion. The perspective transformation in this embodiment includes affine transformation.
Therefore, the method finds out the deformation areas, realizes the correction of image distortion in actual effect through continuous polygon perspective transformation, realizes better visual effect, and is beneficial to the follow-up more accurate image target recognition and the like.
Embodiment two:
as shown in fig. 6, this embodiment further provides a device for quickly correcting a hot zone of image distortion, including:
an edge detection unit 101 for searching for an edge by edge detection at an expected portion of the image and forming a fitting curve according to the edge;
the hot zone generating unit 102 is used for obtaining a target hot zone according to the fitting curve;
a region dividing unit 103 for dividing the target hot zone into a plurality of regions;
a perspective transformation unit 104 for performing perspective transformation on each block region to obtain a distortion corrected image of the hot zone.
The four functional units correspondingly realize steps S1-S4 in the first embodiment, specifically, during implementation, the edge detection unit detects the edge and fits a fitting curve, then the hot zone generating unit generates a target hot zone, the zone dividing unit divides the target hot zone into zones, finally, the perspective transformation unit performs perspective transformation on each zone to obtain a target rectangle, and all targets are specifically combined into a distortion correction image.
As a specific structure, the edge detection unit includes:
the edge detection module is used for searching edges at the expected positions of the images through edge detection;
and the curve fitting module is used for selecting a plurality of points on the edge, and performing curve fitting by adopting a least square method to obtain a fitting curve.
The hot zone generating unit includes:
the broken line point selecting module is used for selecting a plurality of broken line points from the fitting curve, and for the current broken line point, the angle formed between the connecting line of the current broken line point and the next broken line point and the circumscribed line of the current broken line point is within the angle threshold range;
and the curve symmetry module is used for generating a symmetry curve of the fitting curve in the image by taking the central axis of the image as an axis, and the region between the fitting curve and the symmetry curve is a target hot zone.
The area dividing unit is specifically configured to: and dividing the target hot zone into a plurality of areas according to the fitting curve, the symmetrical curve and the corresponding broken line point connecting line on the symmetrical curve, or dividing the target hot zone into a plurality of areas according to the fitting curve, the symmetrical curve, the central axis of the image and the broken line point connecting line.
The perspective transformation unit is specifically configured to: and performing perspective transformation on each area in the height direction of the lines of the fold line points, wherein the width of each area is unchanged, so as to obtain target rectangles, setting the whole target rectangles at the same height during perspective transformation, and finally obtaining the distortion correction image of the hot area.
The specific structure of each functional unit realizes the specific implementation process of each step in the first embodiment. And will not be described in detail here.
In summary, the present invention achieves the effect of image distortion correction by dividing the heat region into a plurality of regions and performing continuous perspective transformation (including affine transformation) using a plurality of continuous polygons (such as trilateral or quadrilateral) for the actual distortion of the ROI region. Because no relatively complex operation such as calibration is needed, the related product adopting the method has the characteristics of simple use and strong functions, and the distortion correction speed is faster and the instantaneity is good.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (4)
1. A method for rapidly correcting a hot zone of an image distortion, the method comprising the steps of:
s1, searching an edge at an expected position of an image through edge detection, and forming a fitting curve according to the edge;
s2, obtaining a target hot zone according to the fitting curve;
s3, dividing the target hot zone into a plurality of areas;
s4, performing perspective transformation on each area to obtain a distortion correction image of the hot area;
the specific process of the step S1 is as follows:
searching an edge at an expected position of the image through edge detection;
selecting a plurality of points on the edge, and performing curve fitting by adopting a least square method to obtain a fitted curve;
the specific process of the step S2 is as follows:
selecting a plurality of broken line points from the fitting curve, wherein for the current broken line point, the angle formed between the connecting line of the current broken line point and the next broken line point and the circumscribed line of the current broken line point is within an angle threshold range;
generating a symmetrical curve of the fitting curve in the image by taking the central axis of the image as an axis, wherein the area between the fitting curve and the symmetrical curve is a target hot area;
the specific process of the step S3 is as follows:
and dividing the target hot zone into a plurality of areas according to the fitting curve, the symmetrical curve and the corresponding broken line point connecting line on the symmetrical curve, or dividing the target hot zone into a plurality of areas according to the fitting curve, the symmetrical curve, the central axis of the image and the broken line point connecting line.
2. The method for quickly correcting the image distortion according to claim 1, wherein the step S4 is as follows:
and performing perspective transformation on each area in the height direction of the lines of the fold line points, wherein the width of each area is unchanged, so as to obtain target rectangles, setting the whole target rectangles at the same height during perspective transformation, and finally obtaining the distortion correction image of the hot area.
3. A hot zone rapid correction device for image distortion, the correction device comprising:
the edge detection unit is used for searching an edge through edge detection at an expected position of the image and forming a fitting curve according to the edge;
the hot zone generating unit is used for obtaining a target hot zone according to the fitting curve;
the area dividing unit is used for dividing the target hot area into a plurality of areas;
the perspective transformation unit is used for carrying out perspective transformation on each area to obtain a distortion correction image of the hot area;
the edge detection unit includes:
the edge detection module is used for searching edges at the expected positions of the images through edge detection;
the curve fitting module is used for selecting a plurality of points on the edge, and performing curve fitting by adopting a least square method to obtain a fitting curve;
the hot zone generating unit includes:
the broken line point selecting module is used for selecting a plurality of broken line points from the fitting curve, and for the current broken line point, the angle formed between the connecting line of the current broken line point and the next broken line point and the circumscribed line of the current broken line point is within the angle threshold range;
the curve symmetry module is used for generating a symmetry curve of the fitting curve in the image by taking the central axis of the image as an axis, and a region between the fitting curve and the symmetry curve is a target hot zone;
the area dividing unit is specifically configured to: and dividing the target hot zone into a plurality of areas according to the fitting curve, the symmetrical curve and the corresponding broken line point connecting line on the symmetrical curve, or dividing the target hot zone into a plurality of areas according to the fitting curve, the symmetrical curve, the central axis of the image and the broken line point connecting line.
4. A hot zone rapid correction apparatus for image distortion as set forth in claim 3, wherein said perspective transformation unit is specifically configured to: and performing perspective transformation on each area in the height direction of the lines of the fold line points, wherein the width of each area is unchanged, so as to obtain target rectangles, setting the whole target rectangles at the same height during perspective transformation, and finally obtaining the distortion correction image of the hot area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310024490.8A CN115908201B (en) | 2023-01-09 | 2023-01-09 | Method and device for quickly correcting hot zone of image distortion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310024490.8A CN115908201B (en) | 2023-01-09 | 2023-01-09 | Method and device for quickly correcting hot zone of image distortion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115908201A CN115908201A (en) | 2023-04-04 |
| CN115908201B true CN115908201B (en) | 2023-11-28 |
Family
ID=86486033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310024490.8A Active CN115908201B (en) | 2023-01-09 | 2023-01-09 | Method and device for quickly correcting hot zone of image distortion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115908201B (en) |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1804861A (en) * | 2005-12-29 | 2006-07-19 | 北大方正集团有限公司 | Document image geometry fault correction method |
| CN101783011A (en) * | 2010-01-08 | 2010-07-21 | 宁波大学 | Distortion correction method of fish eye lens |
| KR20100091383A (en) * | 2009-02-10 | 2010-08-19 | 전남대학교산학협력단 | Correction method of radial distortion based on a line-fitting |
| CN102208025A (en) * | 2011-05-27 | 2011-10-05 | 中国科学院自动化研究所 | Method for correcting geometric distortion of text image |
| CN104820973A (en) * | 2015-05-07 | 2015-08-05 | 河海大学 | Image correction method for distortion curve radian detection template |
| CN107169494A (en) * | 2017-06-01 | 2017-09-15 | 中国人民解放军国防科学技术大学 | License plate image segmentation bearing calibration based on handheld terminal |
| CN108629221A (en) * | 2018-05-11 | 2018-10-09 | 南京邮电大学 | A kind of bearing calibration of fold distortion QR Quick Response Codes |
| CN108830810A (en) * | 2018-06-07 | 2018-11-16 | 辽宁工业大学 | A kind of fisheye image distortion correction method based on rectangular projection |
| CN109544484A (en) * | 2019-02-20 | 2019-03-29 | 上海赫千电子科技有限公司 | A kind of method for correcting image and device |
| CN111126306A (en) * | 2019-12-26 | 2020-05-08 | 江苏罗思韦尔电气有限公司 | Lane line detection method based on edge features and sliding window |
| CN111127339A (en) * | 2019-12-04 | 2020-05-08 | 北京华宇信息技术有限公司 | Method and device for correcting trapezoidal distortion of document image |
| CN112258583A (en) * | 2020-10-16 | 2021-01-22 | 中国石油大学(华东) | Distortion calibration method for close-range image based on equal distortion partition |
| KR102279259B1 (en) * | 2020-01-17 | 2021-07-20 | 네이버 주식회사 | Method for compensating image distortion and, method for collecting objects from the image by using the same |
| CN114078165A (en) * | 2020-08-13 | 2022-02-22 | 华为技术有限公司 | Calibration method of optical imaging module, distortion correction method and related equipment |
| JP2022069967A (en) * | 2020-10-26 | 2022-05-12 | 住友重機械工業株式会社 | Distortion aberration correction processing device, distortion aberration correction method, and program |
| CN114792104A (en) * | 2021-01-26 | 2022-07-26 | 中国科学院沈阳自动化研究所 | Method for identifying and decoding ring-shaped coding points |
| CN115049535A (en) * | 2022-05-24 | 2022-09-13 | 张全胜 | Method for obtaining effective area of fisheye lens and finely correcting image |
| CN115082355A (en) * | 2022-07-20 | 2022-09-20 | 北京智汇云舟科技有限公司 | Fisheye camera full-pixel image correction method and device, fisheye camera and medium |
| CN115187473A (en) * | 2022-06-23 | 2022-10-14 | 珠海博明视觉科技有限公司 | Image distortion calibration and correction algorithm based on region transformation |
| CN115239596A (en) * | 2022-08-10 | 2022-10-25 | 深圳开阳电子股份有限公司 | HUD distortion correction method and device and computer storage medium |
-
2023
- 2023-01-09 CN CN202310024490.8A patent/CN115908201B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1804861A (en) * | 2005-12-29 | 2006-07-19 | 北大方正集团有限公司 | Document image geometry fault correction method |
| KR20100091383A (en) * | 2009-02-10 | 2010-08-19 | 전남대학교산학협력단 | Correction method of radial distortion based on a line-fitting |
| CN101783011A (en) * | 2010-01-08 | 2010-07-21 | 宁波大学 | Distortion correction method of fish eye lens |
| CN102208025A (en) * | 2011-05-27 | 2011-10-05 | 中国科学院自动化研究所 | Method for correcting geometric distortion of text image |
| CN104820973A (en) * | 2015-05-07 | 2015-08-05 | 河海大学 | Image correction method for distortion curve radian detection template |
| CN107169494A (en) * | 2017-06-01 | 2017-09-15 | 中国人民解放军国防科学技术大学 | License plate image segmentation bearing calibration based on handheld terminal |
| CN108629221A (en) * | 2018-05-11 | 2018-10-09 | 南京邮电大学 | A kind of bearing calibration of fold distortion QR Quick Response Codes |
| CN108830810A (en) * | 2018-06-07 | 2018-11-16 | 辽宁工业大学 | A kind of fisheye image distortion correction method based on rectangular projection |
| CN109544484A (en) * | 2019-02-20 | 2019-03-29 | 上海赫千电子科技有限公司 | A kind of method for correcting image and device |
| CN111127339A (en) * | 2019-12-04 | 2020-05-08 | 北京华宇信息技术有限公司 | Method and device for correcting trapezoidal distortion of document image |
| CN111126306A (en) * | 2019-12-26 | 2020-05-08 | 江苏罗思韦尔电气有限公司 | Lane line detection method based on edge features and sliding window |
| KR102279259B1 (en) * | 2020-01-17 | 2021-07-20 | 네이버 주식회사 | Method for compensating image distortion and, method for collecting objects from the image by using the same |
| CN114078165A (en) * | 2020-08-13 | 2022-02-22 | 华为技术有限公司 | Calibration method of optical imaging module, distortion correction method and related equipment |
| CN112258583A (en) * | 2020-10-16 | 2021-01-22 | 中国石油大学(华东) | Distortion calibration method for close-range image based on equal distortion partition |
| JP2022069967A (en) * | 2020-10-26 | 2022-05-12 | 住友重機械工業株式会社 | Distortion aberration correction processing device, distortion aberration correction method, and program |
| CN114792104A (en) * | 2021-01-26 | 2022-07-26 | 中国科学院沈阳自动化研究所 | Method for identifying and decoding ring-shaped coding points |
| CN115049535A (en) * | 2022-05-24 | 2022-09-13 | 张全胜 | Method for obtaining effective area of fisheye lens and finely correcting image |
| CN115187473A (en) * | 2022-06-23 | 2022-10-14 | 珠海博明视觉科技有限公司 | Image distortion calibration and correction algorithm based on region transformation |
| CN115082355A (en) * | 2022-07-20 | 2022-09-20 | 北京智汇云舟科技有限公司 | Fisheye camera full-pixel image correction method and device, fisheye camera and medium |
| CN115239596A (en) * | 2022-08-10 | 2022-10-25 | 深圳开阳电子股份有限公司 | HUD distortion correction method and device and computer storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于光学系统畸变设计曲线的畸变校正方法;张涛;;智能计算机与应用(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115908201A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111145238B (en) | Three-dimensional reconstruction method and device for monocular endoscopic image and terminal equipment | |
| US20030169918A1 (en) | Stereoscopic image characteristics examination system | |
| US8787671B2 (en) | Character recognition preprocessing method and apparatus | |
| CN111899164B (en) | Image splicing method for multi-focal-segment scene | |
| CN110060259A (en) | A kind of fish eye lens effective coverage extracting method based on Hough transformation | |
| CN111652937B (en) | Vehicle-mounted camera calibration method and device | |
| US20240231485A1 (en) | Eyeball tracking method and virtual reality device | |
| CN110443245A (en) | Localization method, device and the equipment of a kind of license plate area under unrestricted scene | |
| CN107689033A (en) | A kind of fish eye images distortion correction method based on ellipse segmentation | |
| CN107492080A (en) | Exempt from calibration easily monocular lens image radial distortion antidote | |
| CN114565612A (en) | PCB U-shaped groove processing abnormity detection method based on image contrast | |
| CN111311658B (en) | Image registration method and related device for dual-light imaging system | |
| KR20220049864A (en) | Method of recognizing license number of vehicle based on angle of recognized license plate | |
| CN111767752A (en) | Two-dimensional code identification method and device | |
| CN115908201B (en) | Method and device for quickly correcting hot zone of image distortion | |
| US7561306B2 (en) | One-dimensional lens shading correction | |
| CN111860270B (en) | Obstacle detection method and device based on fisheye camera | |
| CN112052859B (en) | License plate accurate positioning method and device in free scene | |
| CN113313968A (en) | Parking space detection method and storage medium | |
| CN111630569B (en) | Binocular matching method, visual imaging device and device with storage function | |
| CN112634377B (en) | Camera calibration method, terminal and computer readable storage medium of sweeping robot | |
| Zhang et al. | Fisheye image correction based on straight-line detection and preservation | |
| CN111210384B (en) | Image splicing method suitable for airport runway scene | |
| CN114724111A (en) | Intelligent forklift identification obstacle avoidance method based on deepstream | |
| CN111899189A (en) | Fisheye image correction method based on adaptive classification fitting |
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 |