CN1427245A - Plane measuring method based on single piece image - Google Patents

Plane measuring method based on single piece image Download PDF

Info

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
Application number
CN 01140335
Other languages
Chinese (zh)
Other versions
CN1284961C (en
Inventor
胡占义
吴福朝
王光辉
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.)
Institute of Automation of Chinese Academy of Science
Original Assignee
Institute of Automation of Chinese Academy of Science
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 Institute of Automation of Chinese Academy of Science filed Critical Institute of Automation of Chinese Academy of Science
Priority to CN 01140335 priority Critical patent/CN1284961C/en
Publication of CN1427245A publication Critical patent/CN1427245A/en
Application granted granted Critical
Publication of CN1284961C publication Critical patent/CN1284961C/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

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。

Figure 01140335

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.

Figure 01140335

Description

基于单幅图像的平面测量方法Plane Measurement Method Based on Single Image

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)

1.一种基于单幅图像的平面测量方法,包括步骤:1. A plane measurement method based on a single image, comprising 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. 2.按权利要求1所述的基于单幅图像的平面测量方法,其特征在于所放置的模板中含有4条或4条以上直线或线段。2. The plane measuring method based on a single image according to claim 1, characterized in that the placed template contains 4 or more straight lines or line segments. 3.按权利要求2所述的基于单幅图像的平面测量方法,其特征在于所述的直线或线段是平面图形的边,如矩形、正方形、三角形等及其组合所产生的图形。3. The plane measuring method based on a single image according to claim 2, characterized in that said straight line or line segment is a side of a plane figure, such as a rectangle, a square, a triangle, etc. and the figures produced by a combination thereof.
CN 01140335 2001-12-17 2001-12-17 Plane Measurement Method Based on Single Image Expired - Fee Related CN1284961C (en)

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)

* Cited by examiner, † Cited by third party
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

Cited By (3)

* Cited by examiner, † Cited by third party
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