CN102075785A - Method for correcting wide-angle camera lens distortion of automatic teller machine (ATM) - Google Patents

Method for correcting wide-angle camera lens distortion of automatic teller machine (ATM) Download PDF

Info

Publication number
CN102075785A
CN102075785A CN 201010608963 CN201010608963A CN102075785A CN 102075785 A CN102075785 A CN 102075785A CN 201010608963 CN201010608963 CN 201010608963 CN 201010608963 A CN201010608963 A CN 201010608963A CN 102075785 A CN102075785 A CN 102075785A
Authority
CN
China
Prior art keywords
msubsup
msub
mrow
msup
mtr
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.)
Granted
Application number
CN 201010608963
Other languages
Chinese (zh)
Other versions
CN102075785B (en
Inventor
胡瑞敏
江俊君
韩镇
卢涛
兰诚栋
黄克斌
张春景
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan University WHU
Original Assignee
Wuhan University WHU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan University WHU filed Critical Wuhan University WHU
Priority to CN2010106089631A priority Critical patent/CN102075785B/en
Publication of CN102075785A publication Critical patent/CN102075785A/en
Application granted granted Critical
Publication of CN102075785B publication Critical patent/CN102075785B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Image Processing (AREA)
  • Studio Devices (AREA)

Abstract

The invention relates to the technical field of image processing, in particular relating to a method for correcting wide-angle camera lens distortion of an automatic teller machine (ATM). The method comprises the following steps: establishing a database in accordance with correction parameters for the wide-angle camera lens distortions of ATMs of different types from different manufacturers; shooting a wide-angle image in a scene containing a plurality of straight lines; manually extracting curves in the image; determining a group of optimal correction parameters for the wide-angle camera lens of the ATM; and correcting the wide-angle image in accordance with the optimal parameters. By utilizing the method provided by the invention, the optimal correction parameters can be acquired fast and accurately, and the wide-angle lens images can be accurately corrected based on the optimal parameters.

Description

Method for correcting wide-angle camera lens distortion of ATM (automatic Teller machine)
Technical Field
The invention relates to the technical field of image processing, in particular to a method for correcting the distortion of a wide-angle camera lens of an ATM (automatic Teller machine).
Background
The image correction technology can establish a corresponding mathematical model according to the image distortion reason, extract required information from the distorted image signal, and recover the original undistorted image by solving the inverse process of image distortion. The wide-angle lens distortion image correction technology can effectively recover distortion information of distortion images in the monitoring video, improves accuracy of key clue identification of the monitoring images such as human faces and the like, and has important significance for improving depth application capability of criminal investigation images, further improving case solving rate of public security departments and maintaining social public safety.
In the existing method, the method based on the calibration plate solves the internal and external parameters of the camera by establishing the relationship between the three-dimensional coordinates and the feature point set of the image plane coordinates, thereby correcting the distorted image. This type of method has a high correction accuracy, but it requires a high accuracy calibration block or plate, which is difficult to implement in many practical applications. The other method is based on the existing geometric characteristics in the scene, and the original geometric characteristic information of the distorted image scenery is used for correction. As suggested in document 1 by Moumen Ahmed et al in 2005, a set of parameters is obtained to correct a curve in an image into a straight line by minimizing a distortion measure objective function according to the characteristic that a straight line in a scene corresponds to a curve in a perspective image, and this method may fall into local optimality due to the need of multiple iterations. In 2010, JunFujiki et al, the japan industrial complex technology institute, proposed a model selection-based radial symmetric distortion correction method in document 2. The method comprises the steps of linearly representing a distortion model through a group of model basis functions, taking correction precision of straight characteristic points in an image as coefficients of linear combination of basis functions of a target solving model, and finally correcting the image according to the linearly combined distortion model. However, the algorithm does not constrain the search space of the parameters in the optimization process, the optimal parameters are difficult to converge to the global optimal solution due to the overlarge search space, and the image correction precision is difficult to improve.
Document 1: moumen Ahmed, Aly Farag. nometric Calibration of Camera Lens departure: IEEE Transactions on Image Processing, Vol.14, No.8, Aug 2005
Document 2: jun Fujiki, Hideitsuhino, YumiUsami, ShotaroAkahol, Nobouu Murata.Self-simulation of radial symmetry diagnosis by model selection.20 th International Conference on Pattern recognition.2010, pp.1812-1815
Document 3: ZHengyou Zhang. A Flexible New Technique for Camera calibration. IEEE Transactions on Pattern analysis and Machine analysis, Vol.22, No.11, pages 1330-
Disclosure of Invention
In view of the above technical problems, an object of the present invention is to provide a wide-angle camera lens distortion correction method for an ATM machine, so as to achieve fast and efficient wide-angle lens distortion correction for the ATM machine.
In order to achieve the purpose, the invention adopts the following technical scheme:
according to a camera calibration method based on a moving plane template, the wide-angle camera lens correction parameters of ATM machines of different manufacturers and different models are solved, wherein the parameters comprise a transverse distortion parameter k1Longitudinal distortion parameter k2Center of transverse distortion u0And a center of longitudinal distortion v0Establishing a library according to the distortion correction parameters of the wide-angle camera lens of the ATM of different manufacturers and different models:
shooting a wide-angle image in a scene containing a plurality of straight lines, and taking M curves L on the image1，L2，...，Lj，...，LMJ is more than or equal to 1 and less than or equal to M, manual marking is carried out, LjFrom NjDot
Figure BDA0000041151670000021
I is not less than 1 and not more than NjLet a straight line
Figure BDA0000041151670000022
And a straight line
Figure BDA0000041151670000023
At a point of intersection of
Figure BDA0000041151670000024
Coordinates of (2)Is the center of distortion of the wide-angle image;
determining a set of optimal parameters for the wide-angle camera lens calibration of the ATM
Figure BDA0000041151670000026
According to the correction parameterAnd assigning a pixel value of the distorted image coordinate (u, v) to a corresponding point of the corrected image coordinate (u ', v') by the following formula:
<math><mfenced open='{' close=''><mtable><mtr><mtd><msup><mi>u</mi><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mo>*</mo></msubsup><mo>=</mo><mrow><mo>(</mo><mi>u</mi><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mo>*</mo></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>1</mn><mo>*</mo></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr><mtr><mtd><msup><mi>v</mi><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mo>*</mo></msubsup><mo>=</mo><mrow><mo>(</mo><mi>v</mi><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mo>*</mo></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>2</mn><mo>*</mo></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr></mtable></mfenced></math>
wherein,
Figure BDA0000041151670000029
a corrected image is obtained.
Determining a group of optimal parameters for correcting the wide-angle camera lens of the ATM
Figure BDA00000411516700000210
Comprises the following substeps:
to a certain set of parameters in the distortion correction parameter library
Figure BDA00000411516700000211
All the feature occupancies on each curve were calculated using the following formula
Figure BDA00000411516700000212
Corrected image coordinates
Figure BDA00000411516700000213
<math><mfenced open='{' close=''><mtable><mtr><mtd><msup><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mi>s</mi></msubsup><mo>=</mo><mrow><mo>(</mo><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mi>s</mi></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>1</mn><mi>j</mi></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr><mtr><mtd><msup><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mi>s</mi></msubsup><mo>=</mo><mrow><mo>(</mo><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mi>s</mi></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>2</mn><mi>j</mi></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr></mtable></mfenced></math>
Wherein,
Figure BDA00000411516700000215
the distortion measure of the image after the image is corrected by the set of coefficients is:
<math><mrow><mi>DE</mi><mo>_</mo><mi>k</mi><mo>=</mo><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>j</mi><mo>&le;</mo><mi>M</mi></mrow></munder><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>i</mi><mo>&le;</mo><msub><mi>N</mi><mi>j</mi></msub></mrow></munder><mfrac><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mrow><mo>&prime;</mo><mo>&prime;</mo></mrow></msup><mo>|</mo><mo>|</mo></mrow><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>q</mi><mn>0</mn><mi>s</mi></msubsup><mo>|</mo><mo>|</mo></mrow></mfrac></mrow></math>
the smallest of these s distortion measures is denoted DE _ k*The set of parameters to which it corresponds is noted
Figure BDA0000041151670000031
If DE _ k*Less than a predetermined threshold value epsilon, the group
Figure BDA0000041151670000032
The optimal correction parameters of the wide-angle camera lens of the ATM are obtained; otherwise, the parameters are set
Figure BDA0000041151670000033
Is set to an initial value, i.e.
Figure BDA0000041151670000034
Figure BDA0000041151670000035
Figure BDA0000041151670000036
Figure BDA0000041151670000037
At this time, the distortion center q0Has the coordinates of
Figure BDA0000041151670000038
Make a straight line
Figure BDA0000041151670000039
And a straight line
Figure BDA00000411516700000310
At a point of intersection of
Figure BDA00000411516700000311
Secondly, the correction parameter k obtained in the previous step is adjusted by the following two formulas1，k2，u0，v0Value of }:
<math><mfenced open='{' close=''><mtable><mtr><mtd><msub><mi>k</mi><mn>1</mn></msub><mo>=</mo><msub><mi>k</mi><mn>1</mn></msub><mo>+</mo><msub><mi>&alpha;</mi><mn>1</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>cos</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr><mtr><mtd><msub><mi>k</mi><mn>2</mn></msub><mo>=</mo><msub><mi>k</mi><mn>2</mn></msub><mo>+</mo><msub><mi>&alpha;</mi><mn>2</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>sin</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr></mtable></mfenced></math>
<math><mfenced open='{' close=''><mtable><mtr><mtd><msub><mi>u</mi><mn>0</mn></msub><mo>=</mo><msub><mi>u</mi><mn>0</mn></msub><mo>+</mo><msub><mi>&beta;</mi><mn>1</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>cos</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr><mtr><mtd><msub><mi>v</mi><mn>0</mn></msub><mo>=</mo><msub><mi>v</mi><mn>0</mn></msub><mo>+</mo><msub><mi>&beta;</mi><mn>2</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>sin</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr></mtable></mfenced></math>
wherein alpha is1And alpha2Are each k1And k2Iteration step size of, beta1And beta2Are each u0And v0The iteration step size of (2);
thirdly, calculating characteristic points on each straight line according to the new correction parameter values obtained in the step (2)
Figure BDA00000411516700000314
Corrected image coordinates
Figure BDA00000411516700000315
<math><mfenced open='{' close=''><mtable><mtr><mtd><msup><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msub><mi>u</mi><mn>0</mn></msub><mo>=</mo><mrow><mo>(</mo><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msub><mi>u</mi><mn>0</mn></msub><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msub><mi>k</mi><mn>1</mn></msub><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr><mtr><mtd><msup><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msub><mi>v</mi><mn>0</mn></msub><mo>=</mo><mrow><mo>(</mo><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msub><mi>v</mi><mn>0</mn></msub><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msub><mi>k</mi><mn>2</mn></msub><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr></mtable></mfenced></math>
Wherein,
Figure BDA00000411516700000317
and then calculating the distortion measure of the corrected image:
<math><mrow><mi>DE</mi><mo>_</mo><mi>k</mi><mo>=</mo><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>j</mi><mo>&le;</mo><mi>M</mi></mrow></munder><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>i</mi><mo>&le;</mo><msub><mi>N</mi><mi>j</mi></msub></mrow></munder><mfrac><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mrow><mo>&prime;</mo><mo>&prime;</mo></mrow></msup><mo>|</mo><mo>|</mo></mrow><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msub><mi>q</mi><mn>0</mn></msub><mo>|</mo><mo>|</mo></mrow></mfrac></mrow></math>
if DE _ k is less than the predetermined threshold ε
Figure BDA00000411516700000319
Figure BDA00000411516700000320
Figure BDA00000411516700000321
Then this group isThe optimal correction parameters of the wide-angle camera lens of the ATM are obtained; otherwise, the process turns to step two.
The preset threshold epsilon is as follows: 10 ∈ ═ 10-2。
Establishing a library according to the distortion correction parameters of the wide-angle camera lens of the ATM of different manufacturers and different models:
Figure BDA00000411516700000324
s is more than or equal to 1 and less than or equal to S, and S groups of parameters are provided in total, wherein each group of parameters comprises the transverse distortion degree
Figure BDA00000411516700000325
Degree of longitudinal distortion
Figure BDA00000411516700000326
Center of distortion
Figure BDA00000411516700000327
The number of the four parameters is four,
Figure BDA00000411516700000328
and
Figure BDA00000411516700000329
respectively, a transverse distortion center and a longitudinal distortion center.
When there is no pixel value at (u ', v'), the pixel value at (u ', v') is found by an interpolation algorithm.
The invention has the following advantages and positive effects:
1) the invention can effectively correct various ATM wide-angle lenses by establishing different types of ATM wide-angle lens correction parameter libraries of different manufacturers;
2) the invention can quickly and accurately obtain the optimal correction parameters, and based on the optimal parameters, the wide-angle lens image can be accurately corrected.
Drawings
FIG. 1 is a flow chart of the method for correcting the lens distortion of the wide-angle camera of the ATM.
Detailed Description
The method for correcting the lens distortion of the wide-angle camera of the ATM, as shown in figure 1, comprises the following steps:
1. establishing a wide-angle camera lens correction parameter library of ATM machines of different manufacturers and different models:
in this step, the calibration parameters of the wide-angle camera lens of the ATM machine of different manufacturers and models can be obtained according to the camera calibration method based on the moving plane template proposed by zhangying friend of microsoft research institute in document 3, and these parameters include the transverse distortion parameter k1Longitudinal distortion parameter k2Center of transverse distortion u0And a center of longitudinal distortion v0Establishing a library according to the distortion correction parameters of the wide-angle camera lens of the ATM of different manufacturers and different models:
Figure BDA0000041151670000041
s is more than or equal to 1 and less than or equal to S, and S groups of parameters are provided in total, wherein each group of parameters comprises the transverse distortion degree
Figure BDA0000041151670000042
Degree of longitudinal distortion
Figure BDA0000041151670000043
Center of distortionThe number of the four parameters is four,
Figure BDA0000041151670000045
and
Figure BDA0000041151670000046
a transverse distortion center and a longitudinal distortion center, respectively;
2. taking a wide-angle image in a scene containing a plurality of straight lines:
in a scene containing a plurality of straight lines, shooting a wide-angle image by using a wide-angle camera of an ATM (automatic Teller machine) of a certain model;
3. manually extracting the image of the scene straight line in the image:
for M curves L on the image shot in the step 21，L2，...，Lj，...，LMJ is more than or equal to 1 and less than or equal to M, manual marking is carried out, LjFrom NjDot
Figure BDA0000041151670000047
I is not less than 1 and not more than NjLet a straight line
Figure BDA0000041151670000048
And a straight line
Figure BDA0000041151670000049
At a point of intersection of
Figure BDA00000411516700000410
Coordinates of (2)Is the center of distortion of the wide-angle image;
4. determining a set of optimal parameters for the wide-angle camera lens calibration of the ATM
(1) For a certain set of parameters in the distortion correction parameter library
Figure BDA00000411516700000413
All the characteristic points on each curve are calculated by using the following formula
Figure BDA00000411516700000414
Corrected image coordinates
Figure BDA00000411516700000415
<math><mfenced open='{' close=''><mtable><mtr><mtd><msup><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mi>s</mi></msubsup><mo>=</mo><mrow><mo>(</mo><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mi>s</mi></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>1</mn><mi>j</mi></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr><mtr><mtd><msup><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mi>s</mi></msubsup><mo>=</mo><mrow><mo>(</mo><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mi>s</mi></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>2</mn><mi>j</mi></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr></mtable></mfenced></math>
Wherein,
Figure BDA0000041151670000052
the distortion measure of the image after the image is corrected by the set of coefficients is:
<math><mrow><mi>DE</mi><mo>_</mo><mi>k</mi><mo>=</mo><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>j</mi><mo>&le;</mo><mi>M</mi></mrow></munder><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>i</mi><mo>&le;</mo><msub><mi>N</mi><mi>j</mi></msub></mrow></munder><mfrac><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mrow><mo>&prime;</mo><mo>&prime;</mo></mrow></msup><mo>|</mo><mo>|</mo></mrow><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>q</mi><mn>0</mn><mi>s</mi></msubsup><mo>|</mo><mo>|</mo></mrow></mfrac></mrow></math>
the smallest of these s distortion measures is denoted DE _ k*The set of parameters to which it corresponds is noted
Figure BDA0000041151670000054
If DE _ k*Less than a predetermined threshold value of 10 ∈-2Then this groupThe optimal correction parameters of the wide-angle camera lens of the ATM are obtained. Otherwise, the parameters are set
Figure BDA0000041151670000056
Is set to an initial value, i.e.
Figure BDA0000041151670000057
Figure BDA0000041151670000058
Figure BDA0000041151670000059
Figure BDA00000411516700000510
At this time, the distortion center q0Has the coordinates ofMake a straight lineAnd a straight line
Figure BDA00000411516700000513
At a point of intersection of
Figure BDA00000411516700000514
(2) The correction parameter k obtained in the previous step is adjusted by the following two formulas1，k2，u0，v0Value of }:
<math><mfenced open='{' close=''><mtable><mtr><mtd><msub><mi>k</mi><mn>1</mn></msub><mo>=</mo><msub><mi>k</mi><mn>1</mn></msub><mo>+</mo><msub><mi>&alpha;</mi><mn>1</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>cos</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr><mtr><mtd><msub><mi>k</mi><mn>2</mn></msub><mo>=</mo><msub><mi>k</mi><mn>2</mn></msub><mo>+</mo><msub><mi>&alpha;</mi><mn>2</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>sin</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr></mtable></mfenced></math>
<math><mfenced open='{' close=''><mtable><mtr><mtd><msub><mi>u</mi><mn>0</mn></msub><mo>=</mo><msub><mi>u</mi><mn>0</mn></msub><mo>+</mo><msub><mi>&beta;</mi><mn>1</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>cos</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr><mtr><mtd><msub><mi>v</mi><mn>0</mn></msub><mo>=</mo><msub><mi>v</mi><mn>0</mn></msub><mo>+</mo><msub><mi>&beta;</mi><mn>2</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>sin</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr></mtable></mfenced></math>
wherein alpha is1And alpha2Are each k1And k2Iteration step size of, beta1And beta2Are each u0And v0The iteration step size of.
(3) Calculating the characteristic points on each straight line according to the new correction parameter values obtained in the step (2)
Figure BDA00000411516700000517
Corrected image coordinates
Figure BDA00000411516700000518
<math><mfenced open='{' close=''><mtable><mtr><mtd><msup><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msub><mi>u</mi><mn>0</mn></msub><mo>=</mo><mrow><mo>(</mo><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msub><mi>u</mi><mn>0</mn></msub><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msub><mi>k</mi><mn>1</mn></msub><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr><mtr><mtd><msup><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msub><mi>v</mi><mn>0</mn></msub><mo>=</mo><mrow><mo>(</mo><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msub><mi>v</mi><mn>0</mn></msub><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msub><mi>k</mi><mn>2</mn></msub><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr></mtable></mfenced></math>
Wherein,
Figure BDA00000411516700000520
and then calculating the distortion measure of the corrected image:
<math><mrow><mi>DE</mi><mo>_</mo><mi>k</mi><mo>=</mo><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>j</mi><mo>&le;</mo><mi>M</mi></mrow></munder><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>i</mi><mo>&le;</mo><msub><mi>N</mi><mi>j</mi></msub></mrow></munder><mfrac><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mrow><mo>&prime;</mo><mo>&prime;</mo></mrow></msup><mo>|</mo><mo>|</mo></mrow><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msub><mi>q</mi><mn>0</mn></msub><mo>|</mo><mo>|</mo></mrow></mfrac></mrow></math>
if DE _ k is smaller than the preset threshold value epsilon to 10-2Let us order
Figure BDA00000411516700000522
Figure BDA00000411516700000523
Figure BDA00000411516700000524
Figure BDA00000411516700000525
Then this group is
Figure BDA00000411516700000526
The optimal correction parameters of the wide-angle camera lens of the ATM are obtained. Otherwise, turning to (2)
5. Correcting the wide-angle image of the ATM based on the optimal correction parameters obtained in the step 4:
according to the correction parameter
Figure BDA0000041151670000061
And assigning a pixel value of the distorted image coordinate (u, v) to a corresponding point of the corrected image coordinate (u ', v') (if u ", v" is not an integer, they are made integer by rounding) by the following formula:
<math><mfenced open='{' close=''><mtable><mtr><mtd><msup><mi>u</mi><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mo>*</mo></msubsup><mo>=</mo><mrow><mo>(</mo><mi>u</mi><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mo>*</mo></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>1</mn><mo>*</mo></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr><mtr><mtd><msup><mi>v</mi><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mo>*</mo></msubsup><mo>=</mo><mrow><mo>(</mo><mi>v</mi><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mo>*</mo></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>2</mn><mo>*</mo></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr></mtable></mfenced></math>
wherein,when the corrected image has no pixel value at (u ', v'), the pixel value at (u ', v') is obtained by an interpolation algorithm.
The invention can effectively correct various ATM wide-angle lenses by establishing different types of ATM wide-angle lens correction parameter libraries of different manufacturers. Particularly, if the correction parameter information of the wide-angle camera to be corrected is in the lens correction parameter library established by us, the wide-angle camera to be corrected can quickly and accurately correct the wide-angle image without iteration; if the correction parameter information of the wide-angle camera is not in a lens correction parameter library established by people, iteration can be carried out by taking the group of parameters with the minimum distortion measure as initial values, so that the optimal correction parameters can be quickly and accurately obtained, and the wide-angle lens image can be accurately corrected based on the group of optimal parameters.
The above embodiments are provided only for illustrating the present invention and not for limiting the present invention, and those skilled in the art can make various changes or modifications without departing from the spirit and scope of the present invention, and therefore all equivalent technical solutions are within the scope of the present invention.

Claims (5)

1. A method for correcting the distortion of a wide-angle camera lens of an ATM is characterized by comprising the following steps:
according to a camera calibration method based on a moving plane template, the wide-angle camera lens correction parameters of ATM machines of different manufacturers and different models are solved, wherein the parameters comprise a transverse distortion parameter k1Longitudinal distortion parameter k2Center of transverse distortion u0And a center of longitudinal distortion v0Establishing a library according to the correction parameters of the wide-angle camera lens of the ATM of different manufacturers and different models:
in the inclusion ofShooting a wide-angle image in a scene with a plurality of straight lines, and carrying out M curves L on the image1，L2，...，Lj，...，LMJ is more than or equal to 1 and less than or equal to M, manual marking is carried out, LjFrom NjDot
Figure FDA0000041151660000011
I is not less than 1 and not more than NjLet a straight line
Figure FDA0000041151660000012
And a straight line
Figure FDA0000041151660000013
At a point of intersection of
Figure FDA0000041151660000014
Coordinates of (2)
Figure FDA0000041151660000015
Is the center of distortion of the wide-angle image;
determining a set of optimal parameters for the wide-angle camera lens calibration of the ATM
According to the correction parameter
Figure FDA0000041151660000017
And assigning a pixel value of the distorted image coordinate (u, v) to a corresponding point of the corrected image coordinate (u ', v') by the following formula:
<math><mfenced open='{' close=''><mtable><mtr><mtd><msup><mi>u</mi><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mo>*</mo></msubsup><mo>=</mo><mrow><mo>(</mo><mi>u</mi><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mo>*</mo></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>1</mn><mo>*</mo></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr><mtr><mtd><msup><mi>v</mi><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mo>*</mo></msubsup><mo>=</mo><mrow><mo>(</mo><mi>v</mi><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mo>*</mo></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>2</mn><mo>*</mo></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr></mtable></mfenced></math>
wherein,
Figure FDA0000041151660000019
a corrected image is obtained.
2. An ATM wide-angle camera lens distortion correction method according to claim 1, characterized in that:
determining a group of optimal parameters for correcting the wide-angle camera lens of the ATM
Figure FDA00000411516600000110
Comprises the following substeps:
to a certain set of parameters in the distortion correction parameter library
Figure FDA00000411516600000111
All the feature occupancies on each curve were calculated using the following formula
Figure FDA00000411516600000112
Corrected image coordinates
Figure FDA00000411516600000113
<math><mfenced open='{' close=''><mtable><mtr><mtd><msup><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mi>s</mi></msubsup><mo>=</mo><mrow><mo>(</mo><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msubsup><mi>u</mi><mn>0</mn><mi>s</mi></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>1</mn><mi>j</mi></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr><mtr><mtd><msup><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mi>s</mi></msubsup><mo>=</mo><mrow><mo>(</mo><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msubsup><mi>v</mi><mn>0</mn><mi>s</mi></msubsup><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msubsup><mi>k</mi><mn>2</mn><mi>j</mi></msubsup><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr></mtable></mfenced></math>
Wherein,
Figure FDA00000411516600000115
and correcting the image by using the set of coefficients, wherein the distortion measure of the corrected image is as follows:
<math><mrow><mi>DE</mi><mo>_</mo><mi>k</mi><mo>=</mo><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>j</mi><mo>&le;</mo><mi>M</mi></mrow></munder><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>i</mi><mo>&le;</mo><msub><mi>N</mi><mi>j</mi></msub></mrow></munder><mfrac><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mrow><mo>&prime;</mo><mo>&prime;</mo></mrow></msup><mo>|</mo><mo>|</mo></mrow><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msubsup><mi>q</mi><mn>0</mn><mi>s</mi></msubsup><mo>|</mo><mo>|</mo></mrow></mfrac></mrow></math>
the smallest of these s distortion measures is denoted DE _ k*The set of parameters to which it corresponds is noted
Figure FDA00000411516600000117
If DE _ k*Less than a predetermined threshold value epsilon, the group
Figure FDA0000041151660000021
The optimal correction parameters of the wide-angle camera lens of the ATM are obtained; otherwise, the parameters are setIs set to an initial value, i.e.
Figure FDA0000041151660000023
Figure FDA0000041151660000025
At this time, the distortion center q0Has the coordinates of
Figure FDA0000041151660000027
Make a straight line
Figure FDA0000041151660000028
And a straight line
Figure FDA0000041151660000029
At a point of intersection of
Figure FDA00000411516600000210
Secondly, the correction parameter k obtained in the previous step is adjusted by the following two formulas1，k2，u0，v0Value of }:
<math><mfenced open='{' close=''><mtable><mtr><mtd><msub><mi>k</mi><mn>1</mn></msub><mo>=</mo><msub><mi>k</mi><mn>1</mn></msub><mo>+</mo><msub><mi>&alpha;</mi><mn>1</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>cos</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr><mtr><mtd><msub><mi>k</mi><mn>2</mn></msub><mo>=</mo><msub><mi>k</mi><mn>2</mn></msub><mo>+</mo><msub><mi>&alpha;</mi><mn>2</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>sin</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr></mtable></mfenced></math>
<math><mfenced open='{' close=''><mtable><mtr><mtd><msub><mi>u</mi><mn>0</mn></msub><mo>=</mo><msub><mi>u</mi><mn>0</mn></msub><mo>+</mo><msub><mi>&beta;</mi><mn>1</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>cos</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr><mtr><mtd><msub><mi>v</mi><mn>0</mn></msub><mo>=</mo><msub><mi>v</mi><mn>0</mn></msub><mo>+</mo><msub><mi>&beta;</mi><mn>2</mn></msub><mi>DE</mi><mo>_</mo><mi>k</mi><mo>|</mo><mi>sin</mi><mo>&angle;</mo><msub><mi>q</mi><mn>0</mn></msub><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>|</mo></mtd></mtr></mtable></mfenced></math>
wherein alpha is1And alpha2Are each k1And k2Iteration step size of, beta1And beta2Are each u0And v0The iteration step size of (2);
thirdly, calculating characteristic points on each straight line according to the new correction parameter values obtained in the step (2)Corrected image coordinates
Figure FDA00000411516600000214
<math><mfenced open='{' close=''><mtable><mtr><mtd><msup><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msub><mi>u</mi><mn>0</mn></msub><mo>=</mo><mrow><mo>(</mo><msubsup><mi>u</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msub><mi>u</mi><mn>0</mn></msub><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msub><mi>k</mi><mn>1</mn></msub><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr><mtr><mtd><msup><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msub><mi>v</mi><mn>0</mn></msub><mo>=</mo><mrow><mo>(</mo><msubsup><mi>v</mi><mi>i</mi><mi>j</mi></msubsup><mo>-</mo><msub><mi>v</mi><mn>0</mn></msub><mo>)</mo></mrow><mrow><mo>(</mo><mn>1</mn><mo>+</mo><msub><mi>k</mi><mn>2</mn></msub><msup><mi>r</mi><mn>2</mn></msup><mo>)</mo></mrow></mtd></mtr></mtable></mfenced></math>
Wherein,
Figure FDA00000411516600000216
and then calculating the distortion measure of the corrected image:
<math><mrow><mi>DE</mi><mo>_</mo><mi>k</mi><mo>=</mo><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>j</mi><mo>&le;</mo><mi>M</mi></mrow></munder><munder><mi>max</mi><mrow><mn>1</mn><mo>&le;</mo><mi>i</mi><mo>&le;</mo><msub><mi>N</mi><mi>j</mi></msub></mrow></munder><mfrac><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mrow><mo>&prime;</mo><mo>&prime;</mo></mrow></msup><mo>|</mo><mo>|</mo></mrow><mrow><mo>|</mo><mo>|</mo><msup><msubsup><mi>q</mi><mi>i</mi><mi>j</mi></msubsup><mo>&prime;</mo></msup><mo>-</mo><msub><mi>q</mi><mn>0</mn></msub><mo>|</mo><mo>|</mo></mrow></mfrac></mrow></math>
if DE _ k is less than the predetermined threshold ε
Figure FDA00000411516600000218
Figure FDA00000411516600000219
Figure FDA00000411516600000221
Then this group is
Figure FDA00000411516600000222
The optimal correction parameters of the wide-angle camera lens of the ATM are obtained; otherwise, the process turns to step two.
3. An ATM wide-angle camera lens distortion correction method according to claim 2, characterized in that: the preset threshold epsilon is as follows: 10 ∈ ═ 10-2。
4. An ATM wide-angle camera lens distortion correction method according to claim 1, wherein:
establishing a library according to the distortion correction parameters of the wide-angle camera lens of the ATM of different manufacturers and different models:
Figure FDA00000411516600000223
s is more than or equal to 1 and less than or equal to S, and S groups of parameters are provided in total, wherein each group of parameters comprises the transverse distortion degree
Figure FDA00000411516600000224
Degree of longitudinal distortion
Figure FDA00000411516600000225
Center of distortionThe number of the four parameters is four,and
Figure FDA00000411516600000228
respectively, a transverse distortion center and a longitudinal distortion center.
5. An ATM wide-angle camera lens distortion correction method according to any one of claims 1 to 4, wherein: when there is no pixel value at (u ', v'), the pixel value at (u ', v') is found by an interpolation algorithm.
CN2010106089631A 2010-12-28 2010-12-28 Method for correcting wide-angle camera lens distortion of automatic teller machine (ATM) Expired - Fee Related CN102075785B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2010106089631A CN102075785B (en) 2010-12-28 2010-12-28 Method for correcting wide-angle camera lens distortion of automatic teller machine (ATM)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2010106089631A CN102075785B (en) 2010-12-28 2010-12-28 Method for correcting wide-angle camera lens distortion of automatic teller machine (ATM)

Publications (2)

Publication Number Publication Date
CN102075785A true CN102075785A (en) 2011-05-25
CN102075785B CN102075785B (en) 2012-05-23

Family

ID=44034106

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2010106089631A Expired - Fee Related CN102075785B (en) 2010-12-28 2010-12-28 Method for correcting wide-angle camera lens distortion of automatic teller machine (ATM)

Country Status (1)

Country Link
CN (1) CN102075785B (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103065318A (en) * 2012-12-30 2013-04-24 深圳普捷利科技有限公司 Curved surface projection method and device of multi-camera panorama system
CN103258328A (en) * 2013-04-27 2013-08-21 浙江大学 Method for locating distorted center of wide-field lens
CN104182933A (en) * 2013-05-28 2014-12-03 东北大学 Wide-angle lens image distortion correcting method based on reverse division model
CN104363986A (en) * 2014-10-31 2015-02-18 华为技术有限公司 Image processing method and device
CN105096329A (en) * 2015-08-20 2015-11-25 厦门雅迅网络股份有限公司 Method for accurately correcting ultra-wide-angle lens
CN106878700A (en) * 2015-12-11 2017-06-20 财团法人工业技术研究院 Wide-angle lens correction system and method thereof
CN107657595A (en) * 2015-06-30 2018-02-02 广东欧珀移动通信有限公司 A kind of distortion correction method and mobile terminal and related media production
CN108629810A (en) * 2017-03-23 2018-10-09 展讯通信（上海）有限公司 Scaling method, device and the terminal of binocular camera
CN109949230A (en) * 2017-12-20 2019-06-28 艾迪普（北京）文化科技股份有限公司 Wide angle cameras distortion rendering method based on image recognition
CN110378963A (en) * 2018-12-04 2019-10-25 北京京东振世信息技术有限公司 Camera parameter scaling method and device
CN112284292A (en) * 2020-12-01 2021-01-29 吉林大学 Automobile morphology measurement system distortion coefficient measuring instrument based on equal rocker arm mechanism
CN116245748A (en) * 2022-12-23 2023-06-09 珠海视熙科技有限公司 Distortion correction method, device, equipment, system and storage medium for ring-looking lens

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002218454A (en) * 2001-01-19 2002-08-02 Make Softwear:Kk Automatic photograph vending machine
CN101118648A (en) * 2007-05-22 2008-02-06 南京大学 Road conditions video camera marking method under traffic monitoring surroundings
CN101276465A (en) * 2008-04-17 2008-10-01 上海交通大学 Method for automatically split-jointing wide-angle image
CN101425181A (en) * 2008-12-15 2009-05-06 浙江大学 Panoramic view vision auxiliary parking system demarcating method
CN101685532A (en) * 2008-09-24 2010-03-31 中国科学院自动化研究所 Method for correcting simple linear wide-angle lens

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002218454A (en) * 2001-01-19 2002-08-02 Make Softwear:Kk Automatic photograph vending machine
CN101118648A (en) * 2007-05-22 2008-02-06 南京大学 Road conditions video camera marking method under traffic monitoring surroundings
CN101276465A (en) * 2008-04-17 2008-10-01 上海交通大学 Method for automatically split-jointing wide-angle image
CN101685532A (en) * 2008-09-24 2010-03-31 中国科学院自动化研究所 Method for correcting simple linear wide-angle lens
CN101425181A (en) * 2008-12-15 2009-05-06 浙江大学 Panoramic view vision auxiliary parking system demarcating method

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103065318A (en) * 2012-12-30 2013-04-24 深圳普捷利科技有限公司 Curved surface projection method and device of multi-camera panorama system
CN103065318B (en) * 2012-12-30 2016-08-03 深圳普捷利科技有限公司 The curved surface projection method and device of multiple-camera panorama system
CN103258328A (en) * 2013-04-27 2013-08-21 浙江大学 Method for locating distorted center of wide-field lens
CN103258328B (en) * 2013-04-27 2015-12-09 浙江大学 A kind of center of distortion localization method of wide visual field camera lens
CN104182933A (en) * 2013-05-28 2014-12-03 东北大学 Wide-angle lens image distortion correcting method based on reverse division model
CN104363986A (en) * 2014-10-31 2015-02-18 华为技术有限公司 Image processing method and device
US10262400B2 (en) 2014-10-31 2019-04-16 Huawei Technologies Co., Ltd. Image processing method and device using reprojection error values
CN107657595A (en) * 2015-06-30 2018-02-02 广东欧珀移动通信有限公司 A kind of distortion correction method and mobile terminal and related media production
CN105096329A (en) * 2015-08-20 2015-11-25 厦门雅迅网络股份有限公司 Method for accurately correcting ultra-wide-angle lens
CN105096329B (en) * 2015-08-20 2020-05-12 厦门雅迅网络股份有限公司 Method for accurately correcting image distortion of ultra-wide-angle camera
CN106878700B (en) * 2015-12-11 2018-11-20 财团法人工业技术研究院 wide-angle lens correction system and method thereof
CN106878700A (en) * 2015-12-11 2017-06-20 财团法人工业技术研究院 Wide-angle lens correction system and method thereof
CN108629810A (en) * 2017-03-23 2018-10-09 展讯通信（上海）有限公司 Scaling method, device and the terminal of binocular camera
CN108629810B (en) * 2017-03-23 2020-09-18 展讯通信（上海）有限公司 Calibration method and device of binocular camera and terminal
CN109949230A (en) * 2017-12-20 2019-06-28 艾迪普（北京）文化科技股份有限公司 Wide angle cameras distortion rendering method based on image recognition
CN110378963A (en) * 2018-12-04 2019-10-25 北京京东振世信息技术有限公司 Camera parameter scaling method and device
CN112284292A (en) * 2020-12-01 2021-01-29 吉林大学 Automobile morphology measurement system distortion coefficient measuring instrument based on equal rocker arm mechanism
CN112284292B (en) * 2020-12-01 2021-07-30 吉林大学 Automobile morphology measurement system distortion coefficient measuring instrument based on equal rocker arm mechanism
CN116245748A (en) * 2022-12-23 2023-06-09 珠海视熙科技有限公司 Distortion correction method, device, equipment, system and storage medium for ring-looking lens
CN116245748B (en) * 2022-12-23 2024-04-26 珠海视熙科技有限公司 Distortion correction method, device, equipment, system and storage medium for ring-looking lens

Also Published As

Publication number Publication date
CN102075785B (en) 2012-05-23

Similar Documents

Publication Publication Date Title
CN102075785B (en) Method for correcting wide-angle camera lens distortion of automatic teller machine (ATM)
CN110909693B (en) 3D face living body detection method, device, computer equipment and storage medium
CN104484648B (en) Robot variable visual angle obstacle detection method based on outline identification
CN108765328B (en) High-precision multi-feature plane template and distortion optimization and calibration method thereof
CN107833181B (en) Three-dimensional panoramic image generation method based on zoom stereo vision
CN111784778B (en) Binocular camera external parameter calibration method and system based on linear solving and nonlinear optimization
CN106228528B (en) A kind of multi-focus image fusing method based on decision diagram and rarefaction representation
CN106570899B (en) Target object detection method and device
CN108550166B (en) Spatial target image matching method
CN110009690A (en) Binocular stereo vision image measuring method based on polar curve correction
CN111028205B (en) Eye pupil positioning method and device based on binocular distance measurement
CN105654476A (en) Binocular calibration method based on chaotic particle swarm optimization algorithm
CN109215118B (en) Incremental motion structure recovery optimization method based on image sequence
CN107133986A (en) A kind of camera calibration method based on two-dimensional calibrations thing
CN104677277A (en) Method and system measuring geometric attribute of object or distance
CN115330876B (en) Target template graph matching and positioning method based on twin network and central position estimation
CN110120013A (en) A kind of cloud method and device
CN110910456A (en) Stereo camera dynamic calibration algorithm based on Harris angular point mutual information matching
CN111325828A (en) Three-dimensional face acquisition method and device based on three-eye camera
CN105678088B (en) A kind of adjustment optimization algorithm of target gauge head
CN117522803A (en) Bridge component accurate positioning method based on binocular vision and target detection
CN112434559A (en) Robot identification and positioning method
CN104156952B (en) A kind of image matching method for resisting deformation
CN113920196A (en) Visual positioning method and device and computer equipment
CN106228593A (en) A kind of image dense Stereo Matching method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20120523

Termination date: 20161228

CF01 Termination of patent right due to non-payment of annual fee