CN1427245A - Plane measuring method based on single piece image - Google Patents
Plane measuring method based on single piece image Download PDFInfo
- Publication number
- CN1427245A CN1427245A CN 01140335 CN01140335A CN1427245A CN 1427245 A CN1427245 A CN 1427245A CN 01140335 CN01140335 CN 01140335 CN 01140335 A CN01140335 A CN 01140335A CN 1427245 A CN1427245 A CN 1427245A
- Authority
- CN
- China
- Prior art keywords
- plane
- template
- scene
- image
- method based
- 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 description 19
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 238000000691 measurement method Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 abstract description 23
- 239000011159 matrix material Substances 0.000 description 5
- 230000009466 transformation Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013076 uncertainty analysis Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
一种基于单幅图像的平面测量方法,包括步骤:在被测场景平面中放置一个模板;在被测场景中拍摄一幅或多幅含有所述模板的图像;在图像中提取已知的模板信息;计算出被测平面与像平面间的映射关系;根据此映射关系求出场景中任意一点的坐标值及任意两点间的距离。本发明提供的测量方法不需要对摄像机参数进行标定,而且具有较为简便、实用、测量精度高、鲁棒性好等特点,使基于视觉的测量方法走向实用。
A plane measurement method based on a single image, comprising the steps of: placing a template in the measured scene plane; shooting one or more images containing the template in the measured scene; extracting a known template in the image Information; calculate the mapping relationship between the measured plane and the image plane; calculate the coordinate value of any point in the scene and the distance between any two points according to the mapping relationship. The measurement method provided by the invention does not need to calibrate the camera parameters, and has the characteristics of simplicity, practicability, high measurement accuracy, good robustness, etc., making the vision-based measurement method practical.
Description
技术领域technical field
本发明涉及计算机辅助自动测量。The present invention relates to computer aided automatic measurement.
背景技术Background technique
在我们日常生活和许多领域中,测量,特别是在同一平面内两点间的测量是必不可少的,比如交通事故、刑事犯罪现场,建筑物、施工现场等,都需要进行大量的测量工作。传统方法都是采用手工测量,这种方法十分耗时,容易出现较大的测量误差,而且这种测量也容易因测量人员的主观因素产生不公正的结果。In our daily life and in many fields, measurement, especially the measurement between two points in the same plane is essential, such as traffic accidents, criminal scenes, buildings, construction sites, etc., require a lot of measurement work . The traditional method is to use manual measurement, which is very time-consuming and prone to large measurement errors, and this measurement is also prone to unfair results due to the subjective factors of the measurers.
近年来,随着计算机视觉的发展和应用,人们开始探索借助计算机视觉方法,通过图像进行测量。在这类方法中,较为典型的是通过两幅或多幅图像利用立体视觉的方法重建出被测场景的三维结构,但该方法涉及到计算机视觉领域的经典难题,即多幅图像间的匹配,因而很难投入实际应用。另一种方法是事先在场景平面中人工测量4个以上控制点的信息并以此来计算空间平面与像平面间的投影矩阵,然后通过单幅图像进行测量,这种方法的测量精度与控制点的选取精度、位置和数量直接相关,但在实际应用中,有时控制点很难选取,而且也无法保证控制点的测量精度。In recent years, with the development and application of computer vision, people have begun to explore the use of computer vision methods to measure through images. In this type of method, it is typical to reconstruct the three-dimensional structure of the scene under test by two or more images using stereo vision, but this method involves a classic problem in the field of computer vision, that is, the matching between multiple images. , so it is difficult to put into practical application. Another method is to manually measure the information of more than 4 control points in the scene plane in advance to calculate the projection matrix between the space plane and the image plane, and then measure through a single image. The measurement accuracy and control of this method The selection accuracy, location and number of points are directly related, but in practical applications, sometimes it is difficult to select control points, and the measurement accuracy of control points cannot be guaranteed.
发明内容Contents of the invention
本发明的目的在于提供一种较为简便、实用并具有较高测量精度和鲁棒性的基于单幅图像的测量方法。The purpose of the present invention is to provide a measurement method based on a single image that is relatively simple, practical, has high measurement accuracy and robustness.
为实现上述目的,基于单幅图像的平面测量方法包括步骤:In order to achieve the above purpose, the plane measurement method based on a single image includes steps:
在被测场景平面中放置一个模板;Place a template in the scene plane under test;
在被测场景中拍摄一幅或多幅含有所述模板的图像;taking one or more images containing the template in the scene under test;
在图像中提取已知的模板信息;Extract known template information in the image;
计算出被测平面与像平面间的映射关系;Calculate the mapping relationship between the measured plane and the image plane;
根据此映射关系求出场景中任意一点的坐标值及任意两点间的距离。Calculate the coordinate value of any point in the scene and the distance between any two points according to this mapping relationship.
本发明提供的测量方法不需要对摄像机参数进行标定,而且具有较为简便、实用、测量精度高、鲁棒性好等特点,使基于视觉的测量方法走向实用。The measurement method provided by the invention does not need to calibrate the camera parameters, and has the characteristics of simplicity, practicability, high measurement accuracy, good robustness, etc., making the vision-based measurement method practical.
附图说明Description of drawings
图1是几种模板示意图;Figure 1 is a schematic diagram of several templates;
图2是本测量方法的流程图;Fig. 2 is the flowchart of this measuring method;
图3是实施例的测量场景图。Fig. 3 is a measurement scene diagram of the embodiment.
发明的具体实施方式Specific Embodiments of the Invention
本发明采用一种简易平面模板,在该模板内含有4条或4条以上直线或线段,模板的大小可根据被测场景的大小选取合适的尺寸,对模板的材料没有特殊要求,附图1给出了几种常用的模板实例。将该模板放在被测场景平面中,用普通照相机或数码相机拍摄一幅图像即可进行测量,而且不需要对摄像机参数进行标定,若能从不同角度拍摄多幅图像,则可从中选取一幅较好的进行测量或综合利用同一被测量在多幅图像中的测量值以便提高测量精度。The present invention adopts a simple plane template, which contains 4 or more straight lines or line segments. The size of the template can be selected according to the size of the scene to be measured. There is no special requirement for the material of the template. Accompanying drawing 1 Several commonly used template examples are given. Put this template in the scene plane to be measured, take an image with an ordinary camera or a digital camera for measurement, and do not need to calibrate the camera parameters, if you can take multiple images from different angles, you can choose one of them Use a better image to measure or comprehensively use the measurement values of the same measured object in multiple images to improve the measurement accuracy.
该方法有效地避免了控制点的选取问题,在求取被测平面与像平面间的映射关系时直接利用模板上的直线信息,可以有效地提高测量精度,同时简化了图像处理的难度,有利于提高整个测量过程的自动化程度。对于一幅图像,该方法主要包括图像获取、模板特征提取、计算变换矩阵以及测量等步骤组成,如图2所示,各步的具体说明如下:1.获取图像This method effectively avoids the selection of control points, and directly uses the straight line information on the template when calculating the mapping relationship between the measured plane and the image plane, which can effectively improve the measurement accuracy and simplify the difficulty of image processing. It is beneficial to improve the automation degree of the whole measurement process. For an image, the method mainly includes steps such as image acquisition, template feature extraction, calculation of transformation matrix, and measurement, as shown in Figure 2. The specific description of each step is as follows: 1. Acquire the image
将该模板放在被测场景平面中,用普通照相机或数码相机拍摄一幅或多幅图像,并借助扫描仪或某些专用接口设备将图像输入计算机。2.模板特征提取Put the template in the plane of the scene to be tested, take one or more images with an ordinary camera or a digital camera, and input the images into the computer with the help of a scanner or some special interface equipment. 2. Template feature extraction
通过自动或人机交互方法从图像中提取出所需的模板信息,即模板上的直线参数。其中,可以用Canny或Robert、Sobel等边缘检测算子提取边缘信息,然后用Hough变换或最小二乘、极大似然估计等方法求取直线参数。3.计算变换矩阵Extract the required template information from the image by automatic or human-computer interaction method, that is, the straight line parameters on the template. Among them, Canny, Robert, Sobel and other edge detection operators can be used to extract edge information, and then Hough transform, least squares, maximum likelihood estimation and other methods can be used to obtain line parameters. 3. Calculate the transformation matrix
本方法所采用的模板上的直线或线段信息是可测量的,并将其测量参数存入计算机。根据模板上的直线或线段与第2步所提取出的图像直线或线段的对应关系,求出场景平面到图像平面的映射关系矩阵M。4.测量The straight line or line segment information on the template adopted by the method is measurable, and its measurement parameters are stored in the computer. According to the corresponding relationship between the straight line or line segment on the template and the image straight line or line segment extracted in the second step, the mapping relationship matrix M from the scene plane to the image plane is obtained. 4. Measure
对于图像上的任意一点,利用第3步求出的映射关系矩阵的逆变换M-1,就可以求出场景中对应点的坐标值,进而可以算出场景中任意两点间的距离。同时,可以根据对各步骤的不确定性分析给出每个测量结果的误差范围。For any point on the image, the coordinate value of the corresponding point in the scene can be obtained by using the inverse transformation M -1 of the mapping relationship matrix obtained in the third step, and the distance between any two points in the scene can be calculated. At the same time, the error range of each measurement result can be given according to the uncertainty analysis of each step.
实施例Example
如图3所示为一被测场景的图像,图中模板由两个矩形组成。按照本发明所述的方法,在图像中自动提取两个矩形的八条边并计算出被测平面与像平面间的映射关系,在图像中用鼠标任选两点,就可以利用这一映射关系直接从图像求出场景中这两点间的距离。例如:D1,D2的真实长度分别为77.85cm和189.78cm,用本发明方法所得出的测量值分别为77.72cm和191.02cm,测量的相对误差分别为0.17%和0.65%,这是完全可以达到测量精度要求的。Figure 3 is an image of a tested scene, in which the template is composed of two rectangles. According to the method of the present invention, eight sides of two rectangles are automatically extracted in the image and the mapping relationship between the measured plane and the image plane is calculated, and the mapping relationship can be used by selecting two points in the image with the mouse Find the distance between these two points in the scene directly from the image. For example: D1, the true length of D2 are respectively 77.85cm and 189.78cm, and the measured value that draws with the inventive method is respectively 77.72cm and 191.02cm, and the relative error of measurement is respectively 0.17% and 0.65%, and this is fully achievable required for measurement accuracy.
Claims (3)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 01140335 CN1284961C (en) | 2001-12-17 | 2001-12-17 | Plane Measurement Method Based on Single Image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 01140335 CN1284961C (en) | 2001-12-17 | 2001-12-17 | Plane Measurement Method Based on Single Image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN1427245A true CN1427245A (en) | 2003-07-02 |
CN1284961C CN1284961C (en) | 2006-11-15 |
Family
ID=4675806
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 01140335 Expired - Fee Related CN1284961C (en) | 2001-12-17 | 2001-12-17 | Plane Measurement Method Based on Single Image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN1284961C (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100348948C (en) * | 2003-12-16 | 2007-11-14 | 湖南师范大学 | Image pickup range finder for field events and range finding method |
CN101630409B (en) * | 2009-08-17 | 2011-07-27 | 北京航空航天大学 | Hand-eye vision calibration method for robot hole boring system |
CN102589523A (en) * | 2011-01-11 | 2012-07-18 | 香港理工大学深圳研究院 | Method and equipments for remotely monitoring displacement of building |
-
2001
- 2001-12-17 CN CN 01140335 patent/CN1284961C/en not_active Expired - Fee Related
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100348948C (en) * | 2003-12-16 | 2007-11-14 | 湖南师范大学 | Image pickup range finder for field events and range finding method |
CN101630409B (en) * | 2009-08-17 | 2011-07-27 | 北京航空航天大学 | Hand-eye vision calibration method for robot hole boring system |
CN102589523A (en) * | 2011-01-11 | 2012-07-18 | 香港理工大学深圳研究院 | Method and equipments for remotely monitoring displacement of building |
Also Published As
Publication number | Publication date |
---|---|
CN1284961C (en) | 2006-11-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110443836B (en) | A method and device for automatic registration of point cloud data based on plane features | |
CN109087274B (en) | Electronic device defect detection method and device based on multi-dimensional fusion and semantic segmentation | |
JP5699788B2 (en) | Screen area detection method and system | |
Henricsson et al. | 3-D building reconstruction with ARUBA: a qualitative and quantitative evaluation | |
US7421125B1 (en) | Image analysis, editing and search techniques | |
CN110119680A (en) | A kind of electrical cabinet wiring automatic errordetecting system based on image recognition | |
JP2017534046A (en) | Building height calculation method, apparatus and storage medium | |
CN111986170A (en) | Defect detection algorithm based on Mask R-CNN (deep neural network) | |
CN106595496A (en) | Man-machine interaction part size flexibility vision measurement method | |
CN105809168A (en) | Image fuzzy identification method of standard constant temperature bath glass thermometer | |
CN1224938C (en) | Method of measuring scene and geometric data of bodies inside the scene via single frame of image | |
CN101488224A (en) | Characteristic point matching method based on relativity measurement | |
CN107092905B (en) | A method for locating an instrument to be identified for a power inspection robot | |
CN105423975A (en) | Calibration system and method of large-size workpiece | |
CN108876842A (en) | A kind of measurement method, system, equipment and the storage medium of sub-pixel edge angle | |
CN116152697A (en) | Three-dimensional model measuring method and related device for concrete structure cracks | |
CN106023201B (en) | A kind of dimension measurement method for gular transparent polybag | |
CN114397090A (en) | Method for quickly measuring parallelism of optical axis of continuous zooming camera | |
CN1427245A (en) | Plane measuring method based on single piece image | |
CN111462242B (en) | A Rectangular Pin Chip Positioning Method Based on Improved Deformable Part Model | |
CN1427246A (en) | Single sight plane measuring method based on parallel lines | |
Frangione et al. | Multi-step approach for automated scaling of photogrammetric micro-measurements | |
CN111861887A (en) | Method and system for detecting forming quality of dental crown and storage medium | |
CN118552576B (en) | Method, equipment, medium and product for detecting needle mark touch edge in chip Pad | |
CN110619650A (en) | Edge point extraction method and device based on line structure laser point cloud |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
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: 20061115 Termination date: 20171217 |
|
CF01 | Termination of patent right due to non-payment of annual fee |