CN109712199A - A kind of camera simple calibrating method and device extracting two vanishing points based on A4 paper - Google Patents
A kind of camera simple calibrating method and device extracting two vanishing points based on A4 paper Download PDFInfo
- Publication number
- CN109712199A CN109712199A CN201811618007.4A CN201811618007A CN109712199A CN 109712199 A CN109712199 A CN 109712199A CN 201811618007 A CN201811618007 A CN 201811618007A CN 109712199 A CN109712199 A CN 109712199A
- Authority
- CN
- China
- Prior art keywords
- paper
- image
- point
- camera
- vanishing
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 239000000284 extract Substances 0.000 claims abstract description 16
- 230000035772 mutation Effects 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000001228 spectrum Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 abstract 1
- 230000003595 spectral effect Effects 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 5
- 238000003708 edge detection Methods 0.000 description 4
- 230000036039 immunity Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000007812 deficiency Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
本发明公开了一种基于A4纸提取二灭点的相机简易标定方法及装置，该方法包括：获取相机采集的包含A4纸的图像，并进行预处理后得到滤波去噪后的灰度图；对灰度图进行边缘提取得到边缘图像；扫描边缘图像，寻找0到1突变或1到0突变处作为边界起始点，并从找到的起始点开始搜索，把能搜索到的最长边界作为A4纸轮廓点集；采用谱多流形聚类方法将A4纸轮廓点集分为4类，并分别采用最小二乘法对这4个点集进行直线的拟合，获得4条直线；求取所得4条直线的6个交点，将坐标不在图像范围内的2个交点视为灭点；基于二灭点的相机标定方法计算出相机的内参数。本发明简单易实施，具有较好的抗噪性，可用于大众化非量测相机应用。
The invention discloses a simple camera calibration method and device for extracting two vanishing points based on A4 paper. The method includes: acquiring an image including A4 paper collected by a camera, and performing preprocessing to obtain a grayscale image after filtering and denoising; Extract the edge of the grayscale image to obtain the edge image; scan the edge image, find the 0 to 1 mutation or the 1 to 0 mutation as the starting point of the boundary, and start the search from the found starting point, and take the longest boundary that can be searched as A4 Paper contour point set; the A4 paper contour point set is divided into 4 categories by spectral multi-manifold clustering method, and the least squares method is used to fit these 4 point sets with straight lines to obtain 4 straight lines; The 6 intersection points of the 4 straight lines are regarded as the vanishing points whose coordinates are not within the image range. The camera calibration method based on the two vanishing points calculates the internal parameters of the camera. The invention is simple and easy to implement, has good noise resistance, and can be used in popular non-measurement camera applications.
Description
Technical field
The present invention relates to camera calibration more particularly to it is a kind of based on A4 paper extract two vanishing points camera simple calibrating method and
Device belongs to computer vision field.
Background technique
Popular non-metric camera application, which generally requires, demarcates camera parameter.Camera calibration experienced from needs
Traditional scaling method of accuracy flag object does the active vision scaling method of special exercise to control camera, then arrives based on image certainly
The development course of the self-calibrating method of body feature.In traditional scaling method, it is used widely based on tessellated method, still
Calibration result is influenced by X-comers detection accuracy, and there are the deficiencies of inconvenient to carry, cumbersome vulnerable to interference and template construct；Base
In active vision scaling method without place calibration object, but require control camera do accurate peculair motion, for can not essence
Really the occasion of control camera is not applicable；Camera Self-Calibration method does not need that specific control condition is arranged, only according to multiple image
Relationship direct solution camera parameter between corresponding points mainly includes Camera Self-Calibration based on vanishing point, based on plane or solid
The Camera Self-Calibration of template and self-calibration based on natural scene.
Most of camera calibration methods can only be implemented by professional person, and for ordinary populace, there are ease of use issues.
Therefore it " can gather materials on the spot ", is user friendly, camera simple calibrating method that noise immunity is strong is for popular non-metric camera
Using being undoubtedly of great significance.
The self-calibrating method of camera is because the features such as its simple and flexible and strong applicability, is concerned, wherein being demarcated based on vanishing point
Self-calibrating method due to restrictive condition it is less, it is in widespread attention and further investigation.Self-calibration side commonly based on vanishing point
Method needs to obtain the vanishing point in three directions in scene, this is often difficult to reach requirement in practical applications；By calculating multiple images
In the vanishing points of two orthogonal directions reduce constraint condition the method that carries out camera calibration, but calculated result extracts vanishing point
Accuracy it is more sensitive.Therefore, the accuracy that the easy availability of marker and vanishing point extract is the method needs based on vanishing point
The critical issue focused on solving.
Since A4 paper is easily obtained, and inherently there are two pairs of parallel edges, is suitably applied the self-calibration side based on vanishing point
Method, but in complex environment, when according to A4 paper image zooming-out sides aligned parallel line and then extracting vanishing point, it is easy to be illuminated by the light and makes an uproar with background
The influence of sound.Therefore, research has the camera simple calibrating method based on A4 paper of stronger noise immunity, for popular non-amount
Camera applications are surveyed, undoubtedly there is important theory significance and application value.
Summary of the invention
Goal of the invention: in view of the deficiencies of the prior art, it is an object of that present invention to provide one kind to extract two vanishing points based on A4 paper
Camera simple calibrating method and device, can be used for popular non-metric camera application, have it is simple easily implement, noise immunity is strong etc.
Advantage.
Technical solution: for achieving the above object, a kind of camera extracting two vanishing points based on A4 paper of the present invention
Simple calibrating method includes the following steps:
(1) image comprising A4 paper of camera acquisition is obtained, and obtains the grayscale image after filtering and noise reduction after being pre-processed；
(2) edge extracting is carried out to grayscale image and obtains edge image；
(3) edge image is scanned, finds and is used as boundary starting point at 0 to 1 mutation or 1 to 0 mutation, and from the starting found
Point starts to search for, using the longest boundary that can be searched as A4 paper profile point set；
(4) A4 paper profile point set is divided by 4 classes using spectrum multiple manifold clustering method, and least square method is respectively adopted to this
4 point sets carry out the fitting of straight line, obtain 4 straight lines；
(5) 6 intersection points of 4 straight lines of gained are sought, 2 intersection points by coordinate not in image range are considered as vanishing point；
(6) step (1) to (5) are repeated and extracts the vanishing point in multiple different shooting angles A4 paper image, calculated based on vanishing point
The intrinsic parameter of camera out.
In preferred embodiments, the pretreatment of image includes that the RGB image that will acquire is converted in the step (1)
Grayscale image, and median filter process is carried out to grayscale image.
In preferred embodiments, edge extracting, tool are carried out to grayscale image using Canny operator in the step (2)
Body includes:
(2.1) Gaussian Blur processing is carried out to image；
(2.2) gradient intensity of each pixel and direction in image are calculated；
(2.3) gradient intensity of pixel each in image is compared with the gradient put along positive and negative gradient direction, such as
The gradient intensity of fruit current point is maximum, then is reserved for marginal point；
(2.4) high and low two threshold values are set and are reserved for marginal point if the gradient magnitude of pixel has been more than high threshold,
If being lower than Low threshold, it is excluded, if fallen between, 8 pixels around the pixel is checked, if there is being higher than
High threshold, then it is left marginal point.
In preferred embodiments, A4 paper contour extraction method specifically includes in the step (3):
(3.1) scan binary map, find starting point of the pixel that is mutated from 0 to 1 of pixel value as outer boundary, pixel value from
Starting point of the pixel of 1 to 0 mutation as hole boundary；
(3.2) boundary is continued searching since the starting point found, borderline pixel is marked, in this process
Middle one unique ID of distribution gives newfound boundary, and referred to as NBD, NBD is set as 1 when initial, and one new boundary of every discovery adds
1, it is based on the longest principle of A4 paper profile, extracts the profile point set of A4 paper.
In preferred embodiments, camera is calculated by extracting the vanishing point of at least 5 A4 paper images in the step (5)
Internal reference states matrix, specifically: remember that the vanishing point of extraction indicates are as follows: System of linear equations is established according to Vanishing Point TheorySolving equations obtain matrix
It then will by square-root methodIt is decomposed intoAgain the result of decomposition is inverted to obtainFinally obtain camera intrinsic parameter
MatrixWherein subscript T indicates transposition, the 3rd row the 3rd column in 33 representing matrix of subscript.
On the other hand, a kind of camera simple calibrating device extracting two vanishing points based on A4 paper of the present invention, comprising:
Pretreatment unit for obtaining the image comprising A4 paper of camera acquisition, and obtains filtering and goes after being pre-processed
Grayscale image after making an uproar；
Edge extracting unit obtains edge image for carrying out edge extracting to grayscale image；
Contours extract unit is found and is used as boundary starting point at 0 to 1 mutation or 1 to 0 mutation for scanning edge image,
And searched for since the starting point found, using the longest boundary that can be searched as A4 paper profile point set；
Line fitting unit for A4 paper profile point set to be divided into 4 classes using spectrum multiple manifold clustering method, and is respectively adopted
Least square method carries out the fitting of straight line to this 4 point sets, obtains 4 straight lines；
Vanishing point extraction unit, 2 friendships for seeking 6 intersection points of 4 straight lines of gained, by coordinate not in image range
Point is considered as vanishing point；
And camera calibration unit, it is calculated for the vanishing point in multiple different shooting angles A4 paper image based on extraction
The intrinsic parameter of camera out.
Based on identical design, invention additionally discloses a kind of computing device, including memory, processor and it is stored in storage
On device and the computer program that can run on a processor, the computer program realize the base when being loaded on processor
The camera simple calibrating method of two vanishing points is extracted in A4 paper
The utility model has the advantages that the method provided by the invention extracted two vanishing points based on A4 paper and carry out camera simple calibrating, utilizes
The characteristics of A4 paper edge is mutually orthogonal parallel lines, by carrying out edge detection, contours extract to the image for including A4 paper
And straight line fitting, the vanishing point of plane of delineation both direction is calculated, and then the camera calibration method based on two vanishing points calculates phase
The intrinsic parameter of machine.This method is simply easily implemented, and has preferable noise immunity, can effectively eliminate background noise influence, quasi-
The parallel lines information in image is really extracted, accurate vanishing point is obtained.The camera internal reference being calculated meets accuracy requirement, can use
In popular non-metric camera application.
Detailed description of the invention
Fig. 1 is that vanishing point extracts flow chart in the embodiment of the present invention.
Fig. 2 is edge detection effect picture in the embodiment of the present invention, wherein (a) is original image, it (b) is edge detection results figure.
Fig. 3 is the A4 paper edge effect picture extracted in the embodiment of the present invention.
Fig. 4 is SMMC algorithm Clustering Effect figure in the embodiment of the present invention.
Fig. 5 is straight line fitting effect picture in the embodiment of the present invention.
Specific embodiment
In the following with reference to the drawings and specific embodiments, the present invention will be further described.
As shown in Figure 1, a kind of camera simple calibrating method that two vanishing points are extracted based on A4 paper disclosed by the embodiments of the present invention,
Mainly include the following steps:
Step 1: image preprocessing
(a) it is converted into grayscale image: grayscale image is converted by the RGB image comprising A4 paper that camera obtains first, after convenient
Continuous image procossing.
(b) median filter process: 3 × 3 median filter process is carried out to obtained grayscale image, background is weakened with this and is made an uproar
Sound reduces influence of the noise to result is extracted.
Step 2:Canny operator A4 paper edge is extracted
(a) Gaussian Blur is handled: convolution is carried out using one 5 × 5 Gauss collecting image, smoothed image is reached with this,
Noise is filtered out, the purpose of edge detection performance is improved.
(b) gradient magnitude and direction are calculated: calculating the gradient intensity of each pixel and direction in image.
(c) non-maxima suppression: for each pixel in image, by the gradient intensity of current point and along positive negative gradient
The gradient put on direction compares, if the gradient intensity of current point is the largest, is retained as marginal point.
(d) dual threshold detection and hysteresis threshold: setting ratio is that the high threshold of 2:1 or 3:1 and Low threshold further extract
Edge.If the gradient magnitude of a certain pixel has been more than high threshold, which is left edge pixel；If being lower than low threshold
Value, then the pixel, which is suppressed, excludes；If 8 neighborhood territory pixels of the pixel are checked between two threshold values, if 8 neighborhoods
There is the gradient magnitude of pixel to be higher than high threshold in range, be then left edge pixel, otherwise inhibits to exclude.Final detection effect
As shown in Figure 2.
Step 3: contours extract
(a) find boundary starting point: the bianry image of input only has 0 and 1 two kind of value, and outer boundary indicates that pixel value is 1
Connected region, the connected region that hole boundary representation pixel value is 0.Binary map is scanned, the pixel that pixel value is mutated from 0 to 1 is found
As the starting point of outer boundary, starting point of the pixel that pixel value is mutated from 1 to 0 as hole boundary.
(b) it searches for boundary: continuing searching boundary since the starting point found, borderline pixel is marked,
A unique ID is distributed during this to newfound boundary, referred to as NBD, NBD is set as 1 when initial, and every discovery one is new
Boundary add 1.Based on the longest principle of A4 paper profile, the profile point set of A4 paper is extracted.The profile extracted is as shown in Figure 3.
Step 4: straight line fitting
(a) spectrum multiple manifold cluster: using the method for spectrum multiple manifold cluster (SMMC), by the mixing point set on 4 sides of A4 paper point
For four classes, classifying quality is as shown in Figure 4.
(b) straight line fitting: after profile point set is clustered by side, one point set of each line correspondences, using least square
Method carries out the fitting of straight line to these point sets, and Fig. 5 is the result of fitting.
Step 5: extracting vanishing point
(a) according to 4 straight lines fitted, available 6 intersection points of straight line intersection intersection between lines: are calculated.
(b) coordinate judges: 4 are A4 paper angle points in 6 intersection points, and 2 are vanishing points, usually not due to the image for calibration
Biggish inclination angle is had, vanishing point is not generally possible to appear in image range, therefore according to the coordinate of point whether in image range
Inside determine which two intersection point is vanishing point.
Step 6: camera calibration
The A4 paper image that at least 5 different perspectivess are shot using camera, extracts its image vanishing point respectively, indicates are as follows:System of linear equations is established based on Vanishing Point TheorySolving equations obtain matrixIt then will by square-root methodIt is decomposed intoAgain the result of decomposition is inverted to obtain
At this timeAn invariant is differed with camera Intrinsic Matrix K, since the last one element of K is 1, so camera intrinsic parameter
Matrix
Based on identical inventive concept, a kind of camera extracting two vanishing points based on A4 paper disclosed in another embodiment of the present invention
Simple calibrating device, comprising: pretreatment unit, for obtaining the image comprising A4 paper of camera acquisition, and after being pre-processed
Grayscale image after obtaining filtering and noise reduction；Edge extracting unit obtains edge image for carrying out edge extracting to grayscale image；Profile
Extraction unit is found for scanning edge image and is used as boundary starting point at 0 to 1 mutation or 1 to 0 mutation, and from finding
Initial point starts to search for, using the longest boundary that can be searched as A4 paper profile point set；Straight line computing unit, for using spectrum multithread
A4 paper profile point set is divided into 4 classes by shape clustering method, and least square method is respectively adopted and intends this 4 point sets progress straight lines
It closes, obtains 4 straight lines；Vanishing point extraction unit, for seeking 6 intersection points of 4 straight lines of gained, by coordinate not in image range
2 intersection points be considered as vanishing point；And camera calibration unit, in multiple different shooting angles A4 paper image based on extraction
Vanishing point calculate the intrinsic parameter of camera.
Based on identical inventive concept, invention additionally discloses a kind of computing device, including memory, processor and it is stored in
On memory and the computer program that can run on a processor, the computer program is realized above-mentioned when being loaded on processor
Based on A4 paper extract two vanishing points camera simple calibrating method.
Claims (7)
1. a kind of camera simple calibrating method for extracting two vanishing points based on A4 paper, which comprises the steps of:
(1) image comprising A4 paper of camera acquisition is obtained, and obtains the grayscale image after filtering and noise reduction after being pre-processed；
(2) edge extracting is carried out to grayscale image and obtains edge image；
(3) edge image is scanned, finds and is used as boundary starting point at 0 to 1 mutation or 1 to 0 mutation, and opened from the starting point found
Begin to search for, using the longest boundary that can be searched as A4 paper profile point set；
(4) A4 paper profile point set is divided by 4 classes using spectrum multiple manifold clustering method, and least square method is respectively adopted to this 4
Point set carries out the fitting of straight line, obtains 4 straight lines；
(5) 6 intersection points of 4 straight lines of gained are sought, 2 intersection points by coordinate not in image range are considered as vanishing point；
(6) step (1) to (5) are repeated and extracts the vanishing point in multiple different shooting angles A4 paper image, phase is calculated based on vanishing point
The intrinsic parameter of machine.
2. the camera simple calibrating method according to claim 1 for extracting two vanishing points based on A4 paper, which is characterized in that described
The pretreatment of image includes that the RGB image that will acquire is converted to grayscale image, and carries out median filtering to grayscale image in step (1)
Processing.
3. the camera simple calibrating method according to claim 1 for extracting two vanishing points based on A4 paper, which is characterized in that described
Edge extracting is carried out to grayscale image using Canny operator in step (2), is specifically included:
(2.1) Gaussian Blur processing is carried out to image；
(2.2) gradient intensity of each pixel and direction in image are calculated；
(2.3) gradient intensity of pixel each in image is compared with the gradient put along positive and negative gradient direction, if worked as
The gradient intensity of preceding point is maximum, then is reserved for marginal point；
(2.4) high and low two threshold values are set and are reserved for marginal point if the gradient magnitude of pixel has been more than high threshold, if
It lower than Low threshold, is then excluded, if fallen between, checks 8 pixels around the pixel, if there is being higher than high threshold
Value, then it is left marginal point.
4. the camera simple calibrating method according to claim 1 for extracting two vanishing points based on A4 paper, which is characterized in that described
A4 paper contour extraction method specifically includes in step (3):
(3.1) binary map is scanned, starting point of the pixel that searching pixel value is mutated from 0 to 1 as outer boundary, pixel value is from 1 to 0
Starting point of the pixel of mutation as hole boundary；
(3.2) boundary is continued searching since the starting point found, borderline pixel is marked, is divided in this process
Newfound boundary is given with a unique ID, referred to as NBD, NBD is set as 1 when initial, and one new boundary of every discovery adds 1, base
In the longest principle of A4 paper profile, the profile point set of A4 paper is extracted.
5. the camera simple calibrating method according to claim 1 for extracting two vanishing points based on A4 paper, which is characterized in that described
Camera Intrinsic Matrix is calculated by extracting the vanishing point of at least 5 A4 paper images in step (5), specifically: remember the vanishing point of extraction
It indicates are as follows: System of linear equations is established according to Vanishing Point Theory Solving equations obtain matrixSo
It afterwards will by square-root methodIt is decomposed intoAgain the result of decomposition is inverted to obtainFinally obtain camera intrinsic parameter
MatrixWherein subscript T indicates transposition, the 3rd row the 3rd column in 33 representing matrix of subscript.
6. a kind of camera simple calibrating device for extracting two vanishing points based on A4 paper characterized by comprising
Pretreatment unit, for obtaining the image comprising A4 paper of camera acquisition, and after obtaining filtering and noise reduction after being pre-processed
Grayscale image；
Edge extracting unit obtains edge image for carrying out edge extracting to grayscale image；
Contours extract unit is found for scanning edge image and is used as boundary starting point at 0 to 1 mutation or 1 to 0 mutation, and from
The starting point found starts to search for, using the longest boundary that can be searched as A4 paper profile point set；
For A4 paper profile point set to be divided into 4 classes using spectrum multiple manifold clustering method, and minimum is respectively adopted in straight line computing unit
Square law carries out the fitting of straight line to this 4 point sets, obtains 4 straight lines；
Vanishing point extraction unit, 2 intersection points view for seeking 6 intersection points of 4 straight lines of gained, by coordinate not in image range
For vanishing point；
And camera calibration unit, phase is calculated for the vanishing point in multiple different shooting angles A4 paper image based on extraction
The intrinsic parameter of machine.
7. a kind of computing device including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the computer program is realized described in -5 any one according to claim 1 when being loaded on processor
Based on A4 paper extract two vanishing points camera simple calibrating method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811618007.4A CN109712199B (en) | 2018-12-28 | 2018-12-28 | Simple camera calibration method and device based on A4 paper point extraction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811618007.4A CN109712199B (en) | 2018-12-28 | 2018-12-28 | Simple camera calibration method and device based on A4 paper point extraction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109712199A true CN109712199A (en) | 2019-05-03 |
| CN109712199B CN109712199B (en) | 2020-09-08 |
Family
ID=66258895
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811618007.4A Active CN109712199B (en) | 2018-12-28 | 2018-12-28 | Simple camera calibration method and device based on A4 paper point extraction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109712199B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314941A (en) * | 2023-09-28 | 2023-12-29 | 腾讯科技（深圳）有限公司 | Image processing method, device, equipment, medium and program product |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8368762B1 (en) * | 2010-04-12 | 2013-02-05 | Adobe Systems Incorporated | Methods and apparatus for camera calibration based on multiview image geometry |
| CN103729837A (en) * | 2013-06-25 | 2014-04-16 | 长沙理工大学 | Rapid calibration method of single road condition video camera |
| CN103735269A (en) * | 2013-11-14 | 2014-04-23 | 大连民族学院 | Height measurement method based on video multi-target tracking |
| CN104809755A (en) * | 2015-04-09 | 2015-07-29 | 福州大学 | Single-image-based cultural relic three-dimensional reconstruction method |
| CN207173127U (en) * | 2017-05-06 | 2018-04-03 | 北京七视野文化创意发展有限公司 | Perspective view drawing instrument |
| CN108961182A (en) * | 2018-06-25 | 2018-12-07 | 北京大学 | Vertical direction vanishing point detection method and video positive twist method for video image |
-
2018
- 2018-12-28 CN CN201811618007.4A patent/CN109712199B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8368762B1 (en) * | 2010-04-12 | 2013-02-05 | Adobe Systems Incorporated | Methods and apparatus for camera calibration based on multiview image geometry |
| CN103729837A (en) * | 2013-06-25 | 2014-04-16 | 长沙理工大学 | Rapid calibration method of single road condition video camera |
| CN103735269A (en) * | 2013-11-14 | 2014-04-23 | 大连民族学院 | Height measurement method based on video multi-target tracking |
| CN104809755A (en) * | 2015-04-09 | 2015-07-29 | 福州大学 | Single-image-based cultural relic three-dimensional reconstruction method |
| CN207173127U (en) * | 2017-05-06 | 2018-04-03 | 北京七视野文化创意发展有限公司 | Perspective view drawing instrument |
| CN108961182A (en) * | 2018-06-25 | 2018-12-07 | 北京大学 | Vertical direction vanishing point detection method and video positive twist method for video image |
Non-Patent Citations (3)
| Title |
|---|
| XU RENJIE 等: "Improved Calibration Algorithm", 《SPRING》 * |
| 徐嵩 等: "基于矩形的摄像机自标定几何方法", 《光学学报》 * |
| 胡桂廷 等: "基于两灭点法的摄像机标定方法研究", 《电子测量技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314941A (en) * | 2023-09-28 | 2023-12-29 | 腾讯科技（深圳）有限公司 | Image processing method, device, equipment, medium and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109712199B (en) | 2020-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107301661B (en) | High-resolution remote sensing image registration method based on edge point features | |
| CN105956582B (en) | A kind of face identification system based on three-dimensional data | |
| CN107203973B (en) | Sub-pixel positioning method for center line laser of three-dimensional laser scanning system | |
| CN109543701A (en) | Vision significance method for detecting area and device | |
| CN116664559B (en) | Machine vision-based memory bank damage rapid detection method | |
| CN107767387B (en) | Contour detection method based on global modulation of variable receptive field scale | |
| CN111369605B (en) | Infrared and visible light image registration method and system based on edge features | |
| Ishikura et al. | Saliency detection based on multiscale extrema of local perceptual color differences | |
| CN103473764A (en) | Remote-sensing image target change detection method | |
| KR102073468B1 (en) | System and method for scoring color candidate poses against a color image in a vision system | |
| CN110472521B (en) | Pupil positioning calibration method and system | |
| CN101996308A (en) | Human face identification method and system and human face model training method and system | |
| CN107452030A (en) | Method for registering images based on contour detecting and characteristic matching | |
| CN103745453A (en) | Town information extraction method based on Google Earth remote sensing image | |
| CN108320310B (en) | Image sequence-based space target three-dimensional attitude estimation method | |
| Manh et al. | Small object segmentation based on visual saliency in natural images | |
| CN106683125A (en) | RGB-D image registration method based on 2D/3D mode switching | |
| Kang et al. | An adaptive fusion panoramic image mosaic algorithm based on circular LBP feature and HSV color system | |
| CN104392209B (en) | A kind of image complexity evaluation method of target and background | |
| CN106886754A (en) | Object identification method and system under a kind of three-dimensional scenic based on tri patch | |
| CN109712199A (en) | A kind of camera simple calibrating method and device extracting two vanishing points based on A4 paper | |
| Wang et al. | Automatic fundus images mosaic based on SIFT feature | |
| US10115195B2 (en) | Method and apparatus for processing block to be processed of urine sediment image | |
| CN104156956B (en) | A kind of multicorner edge detection operator method recognized based on Gauss wavelet one-dimensional peak value | |
| CN112541471B (en) | Multi-feature fusion-based shielding target identification 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 |