CN103776419A - Binocular-vision distance measurement method capable of widening measurement range - Google Patents
Binocular-vision distance measurement method capable of widening measurement rangeDownload PDFInfo
- Publication number
- CN103776419A CN103776419ACN201410035353.5ACN201410035353ACN103776419ACN 103776419 ACN103776419 ACN 103776419ACN 201410035353 ACN201410035353 ACN 201410035353ACN 103776419 ACN103776419 ACN 103776419A
- Authority
- CN
- China
- Prior art keywords
- image
- short
- focus
- depth
- parallax
- 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
- 238000005259measurementMethods0.000titleclaimsabstractdescription18
- 238000000691measurement methodMethods0.000titledescription2
- 238000000034methodMethods0.000claimsabstractdescription27
- 230000003287optical effectEffects0.000claimsabstractdescription7
- 239000011159matrix materialSubstances0.000claimsdescription10
- 230000015572biosynthetic processEffects0.000claimsdescription6
- 238000003786synthesis reactionMethods0.000claimsdescription6
- 238000006243chemical reactionMethods0.000claimsdescription3
- 230000000717retained effectEffects0.000claimsdescription3
- 238000009434installationMethods0.000abstractdescription2
- 238000003384imaging methodMethods0.000description3
- 230000000007visual effectEffects0.000description2
- 230000009286beneficial effectEffects0.000description1
- 238000009435building constructionMethods0.000description1
- 230000007812deficiencyEffects0.000description1
- 238000010586diagramMethods0.000description1
- 238000012986modificationMethods0.000description1
- 230000004048modificationEffects0.000description1
- 238000006467substitution reactionMethods0.000description1
Images
Classifications
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C3/00—Measuring distances in line of sight; Optical rangefinders
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
- G01C11/06—Interpretation of pictures by comparison of two or more pictures of the same area
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Multimedia (AREA)
- Measurement Of Optical Distance (AREA)
Abstract
Translated fromChineseDescription
Translated fromChinese技术领域technical field
本发明涉及视觉测量领域，具体涉及一种提高测量范围的双目视觉测距方法。The invention relates to the field of visual measurement, in particular to a binocular vision ranging method for improving the measurement range.
背景技术Background technique
常用的测距方法有超声波测距、激光测距、红外测距、光学测距等，主要应用于军事、工业测量、建筑施工等领域。目前常用的视觉测量技术主要有以下3种方法：双目立体视觉法、结构光法、几何光学法。Commonly used ranging methods include ultrasonic ranging, laser ranging, infrared ranging, optical ranging, etc., which are mainly used in military, industrial measurement, building construction and other fields. Currently commonly used visual measurement techniques mainly include the following three methods: binocular stereo vision method, structured light method, and geometric optics method.
双目立体视觉测距具有非接触、自动测量、对人眼无害等优点。最常用的是平行光轴模型，两摄像机相距一个基线距离水平放置，先通过畸变校正和极线校正，使得同一特征点在两图像只有水平视差，利用图像配准的方法得到对应点的视差，利用视差和深度的关系最终得到场景中物点的深度信息。Binocular stereo vision ranging has the advantages of non-contact, automatic measurement, and harmless to human eyes. The most commonly used is the parallel optical axis model. The two cameras are placed horizontally at a baseline distance. First, through distortion correction and epipolar correction, the same feature point has only horizontal parallax in the two images. The parallax of the corresponding point is obtained by image registration method. Using the relationship between disparity and depth, the depth information of the object points in the scene is finally obtained.
结构光测距需要一个投影光源和摄像机，两者相距一个基线距离，通过确定场景物点反射光源的成像位置和投影角等参数，获得场景的深度信息。Structured light ranging requires a projection light source and a camera, which are separated by a baseline distance. The depth information of the scene is obtained by determining the imaging position and projection angle of the reflected light source of the scene object point and other parameters.
几何光学法包括聚焦法和离焦法。聚焦法通过调整摄像机的像距，使得成像平面在被测点处聚焦，在已知像距和焦距的条件下，通过透镜成像公式求取物距。离焦法利用物点不聚焦时图像的模糊程度获取深度信息。Geometric optics includes focusing and defocusing methods. The focusing method adjusts the image distance of the camera so that the imaging plane is focused at the measured point. Under the condition of known image distance and focal length, the object distance is obtained through the lens imaging formula. The defocus method uses the blurred degree of the image when the object point is not in focus to obtain depth information.
发明内容Contents of the invention
为了克服现有技术存在的缺点与不足，本发明提供一种提高测量范围的双目视觉测距方法，本发明克服现有技术中固定安装的双目相机利用短焦镜头测距深度短，利用长焦镜头测距视角小的问题。In order to overcome the shortcomings and deficiencies of the prior art, the present invention provides a binocular vision ranging method that improves the measurement range. The telephoto lens has a small viewing angle.
本发明采用如下技术方案：The present invention adopts following technical scheme:
一种提高测量范围的双目视觉测距方法，包括如下步骤：A binocular vision ranging method for improving the measurement range, comprising the steps of:
S1采用具有固定基线长度的平行光轴结构的双目相机分别拍摄一组短焦图像及一组长焦图像；所述一组短焦图像包括两张，分别是左目相机及右目相机拍摄，所述一组长焦图像包括两张，分别是左目相机及右目相机拍摄；S1 uses a binocular camera with a parallel optical axis structure with a fixed baseline length to shoot a set of short-focus images and a set of long-focus images respectively; the set of short-focus images includes two images, which are respectively taken by the left-eye camera and the right-eye camera. The above-mentioned group of telephoto images includes two, which are respectively taken by the left-eye camera and the right-eye camera;
S2寻找相互匹配的短焦图像对应点组a和长焦图像对应点组b，并且匹配好一组同时属于短焦图像和长焦图像的对应点组c；S2 finds the corresponding point group a of the short-focus image and the corresponding point group b of the telephoto image that match each other, and matches a set of corresponding point groups c that belong to both the short-focus image and the telephoto image;
S3若短焦图像视角较大，需进行畸变校正后进入S4，否则直接进入S4；In S3, if the angle of view of the short-focus image is large, it needs to perform distortion correction and then enter S4, otherwise directly enter S4;
S4利用短焦图像的对应点组a和长焦图像对应点组b分别对短焦图像和长焦图像计算单应矩阵进行极线校正，得到仅存在水平视差的两张图像；S4 using the corresponding point group a of the short-focus image and the corresponding point group b of the telephoto image to respectively calculate the homography matrix of the short-focus image and the telephoto image to perform epipolar correction, and obtain two images with only horizontal parallax;
S5对于极线校正后的短焦图像，利用深度和视差的公式求解深度，判断是否在视差可信范围，若在可信范围内则保留所求深度，否则继续查看该短焦图像的对应点是否都在对应点组c里，若是，则利用长焦图像的对应点组b的视差求解深度，否则不保留该深度信息。S5 For the epipolar-corrected short-focus image, use the formula of depth and parallax to solve the depth, and judge whether it is within the credible range of parallax. If it is within the credible range, keep the required depth; otherwise, continue to check the corresponding point of the short-focus image Whether they are all in the corresponding point group c, if so, use the parallax of the corresponding point group b of the telephoto image to calculate the depth, otherwise the depth information will not be retained.
所述S4中还包括针对短焦图像，将畸变校正和极线校正的两个离散坐标表格合并一个。The S4 also includes merging the two discrete coordinate tables for distortion correction and epipolar line correction into one for the short-focus image.
所述将畸变校正和极线校正的两个离散坐标表格合并成一个，具体采用线性插值的方法，具体为：The two discrete coordinate tables of distortion correction and epipolar line correction are combined into one, specifically using the method of linear interpolation, specifically:
针对X坐标：X1为畸变校正表格，X2为极线校正表格，X3为合成表，floor代表不大于该浮点数的最大整数，i代表第i行，j代表第j列，则转换公式为X3(i,j)=X2(i,floor(X1(i,j)))+(X2(i,1+floor(X1(i,j)))-X2(i,floor(X1(i,j))))*(X1(i,j)-floor(X1(i,j)))For the X coordinate: X1 is the distortion correction table, X2 is the epipolar line correction table, X3 is the synthesis table, floor represents the largest integer not greater than the floating point number, i represents the i-th row, and j represents the j-th column, then the conversion formula is X3 (i,j)=X2 (i,floor(X1 (i,j)))+(X2 (i,1+floor(X1 (i,j)))-X2 (i,floor (X1 (i,j))))*(X1 (i,j)-floor(X1 (i,j)))
针对Y坐标：Y1为畸变校正表格，Y2为极线校正表格，Y3为合成表Y3(i,j)=Y2(floor(Y1(i,j)),j)+(Y2(1+floor(Y1(i,j)),j)-Y2(floor(Y1(i,j)),j))*(Y1(i,j)-floor(Y1(i,j)))。For the Y coordinate: Y1 is the distortion correction table, Y2 is the epipolar line correction table, Y3 is the synthesis table Y3 (i,j)=Y2 (floor(Y1 (i,j)),j)+(Y2 ( 1+floor(Y1 (i,j)),j)-Y2 (floor(Y1 (i,j)),j))*(Y1 (i,j)-floor(Y1 (i, j))).
所述极线校正具体为：The polar line correction is specifically:
S4.1分别求解短焦图像和长焦图像的基本矩阵，基本矩阵的特征向量为极点；S4.1 Solve the basic matrix of the short-focus image and the long-focus image respectively, and the eigenvector of the basic matrix is a pole;
S4.2分别将短焦图像和长焦图像的极点旋转到x轴并且移到无穷远使得两图像的极线与x轴平行，再对其中短焦图像中任一幅图像和长焦图像中任一幅图像进行y方向的线性缩放，得到用于短焦图像和长焦图像极线校正的单应矩阵；S4.2 Rotate the poles of the short-focus image and the telephoto image to the x-axis and move them to infinity so that the epipolar lines of the two images are parallel to the x-axis, and then any one of the short-focus images and the telephoto image Any image is linearly scaled in the y direction to obtain a homography matrix for epipolar correction of the short-focus image and the telephoto image;
S4.3求解极线校正后的图像离散浮点坐标表格X2和Y2，X2和Y2为极线校正的X坐标表格和Y坐标表格。S4.3 Solving the discrete floating-point coordinate tables X2 and Y2 of the epipolar-corrected image, where X2 and Y2 are the X-coordinate table and the Y-coordinate table of the polar-line correction.
还包括预先获取视差和深度关系，并根据该关系，确定不同焦距下的视差可信范围。It also includes obtaining the relationship between the parallax and the depth in advance, and according to the relationship, determining the credible range of the parallax at different focal lengths.
所述根据视差和深度的关系，确定不同焦距下的视差可信范围，具体为：利用某个已知深度的物体在不同距离下建立视差和深度的对应关系，再使用曲线拟合得到稠密的对应关系，最后根据视差相差1个像素对应深度相差的实际距离选定视差可信范围。According to the relationship between parallax and depth, determine the credible range of parallax at different focal lengths, specifically: use an object with a known depth to establish the corresponding relationship between parallax and depth at different distances, and then use curve fitting to obtain dense Correspondence, and finally select the credible range of parallax according to the actual distance of the depth difference corresponding to the difference of 1 pixel in the parallax.
S3中所述畸变校正具体为：The distortion correction described in S3 is specifically:
S3.1拍摄棋盘格图像；S3.1 Take a checkerboard image;
S3.2将棋盘格图像中心平移移到原点，利用桶形失真校正公式S3.2 Translate the center of the checkerboard image to the origin, and use the barrel distortion correction formula
x1=x(1+k1x2+k2y2)x1 =x(1+k1 x2 +k2 y2 )
y1=y(1+k1x2+k2y2)；调整参数k1和k2，遍历所有离散整数坐标得到畸变校正的离散浮点坐标表格X1和Y1，其中x和y是原始棋盘格图像的浮点坐标，x1和y1是畸变校正后棋盘格图像的离散整数坐标，X1和Y1为畸变校正的X坐标表格和Y坐标表格。y1 =y(1+k1 x2 +k2 y2 ); adjust parameters k1 and k2 , traverse all discrete integer coordinates to obtain distortion-corrected discrete floating-point coordinate tables X1 and Y1, where x and y are the original The floating point coordinates of the checkerboard image, x1 and y1 are the discrete integer coordinates of the checkerboard image after distortion correction, and X1 and Y1 are the X coordinate table and Y coordinate table of the distortion correction.
本发明具有如下有益效果：The present invention has following beneficial effects:
（1）在双目相机安装固定的情况下，能够保持大范围测量视角的同时提高深度的测量；(1) When the binocular camera is installed and fixed, it can maintain a wide range of measurement angle of view while improving depth measurement;
（2）利用已知深度的物体在不同距离下建立视差和深度的对应关系，并利用曲线拟合得到稠密的对应关系，提高测量的准确度；(2) Use objects of known depth to establish the corresponding relationship between parallax and depth at different distances, and use curve fitting to obtain a dense corresponding relationship to improve the accuracy of measurement;
（3）无需对摄像机进行内部参数和外部参数的标定。(3) There is no need to calibrate the internal and external parameters of the camera.
附图说明Description of drawings
图1是本发明一种提高测量范围的双目视觉测距方法的工作流程图；Fig. 1 is a kind of work flowchart of the binocular vision ranging method that improves measuring range of the present invention;
图2是本发明双目相机的安装示意图；Fig. 2 is the installation schematic diagram of binocular camera of the present invention;
图3是本发明的获取视差和深度关系的流程图；Fig. 3 is the flow chart of obtaining parallax and depth relation of the present invention;
图4是本发明当短焦图像进行畸变校正和极线校正的流程图。FIG. 4 is a flowchart of distortion correction and epipolar line correction for short-focus images according to the present invention.
具体实施方式Detailed ways
下面结合实施例及附图，对本发明作进一步地详细说明，但本发明的实施方式不限于此。The present invention will be described in further detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.
实施例Example
一种提高测量范围的双目视觉测距方法，如图2所示，硬件结构包括两个相机镜头，该镜头具有变焦功能，用于获取短焦和长焦图像，两个镜头平行排列，位于左边的为左目相机，位于右边的为右目相机，保证两个相机为平行光轴结构。A binocular vision ranging method to improve the measurement range, as shown in Figure 2, the hardware structure includes two camera lenses, the lens has a zoom function, used to obtain short-focus and long-focus images, the two lenses are arranged in parallel, located at The one on the left is the left-eye camera, and the one on the right is the right-eye camera, ensuring that the two cameras have a parallel optical axis structure.
如图1所示，具体包括如下步骤：As shown in Figure 1, it specifically includes the following steps:
S1采用具有固定基线长度的平行光轴结构的双目相机分别拍摄一组短焦图像及一组长焦图像；所述一组短焦图像包括两张，分别是左目相机及右目相机拍摄，所述一组长焦图像包括两张，分别是左目相机及右目相机拍摄；S1 uses a binocular camera with a parallel optical axis structure with a fixed baseline length to shoot a set of short-focus images and a set of long-focus images respectively; the set of short-focus images includes two images, which are respectively taken by the left-eye camera and the right-eye camera. The above-mentioned group of telephoto images includes two, which are respectively taken by the left-eye camera and the right-eye camera;
S2寻找相互匹配的短焦图像对应点组a和长焦图像对应点组b，并且匹配好一组同时属于短焦图像和长焦图像的对应点组c；S2 finds the corresponding point group a of the short-focus image and the corresponding point group b of the telephoto image that match each other, and matches a set of corresponding point groups c that belong to both the short-focus image and the telephoto image;
所述寻找相互匹配对应点有三种方法，第一种为人工寻找兴趣点+人工匹配，第二种为人工寻找兴趣点+自动匹配，例如SAD块匹配/归一化互相关，第三种自动寻找特征点+自动匹配，例如SIFT/SURF+SAD+RANSAC方法。There are three ways to find the corresponding points of mutual matching, the first is to manually find the points of interest + manual matching, the second is to manually find the points of interest + automatic matching, such as SAD block matching / normalized cross-correlation, the third is automatic Find feature points + automatic matching, such as SIFT/SURF+SAD+RANSAC method.
S3若短焦图像视角过大，需进行畸变校正后进入S4，否则直接进入S4，如图4所示，所述畸变校正具体为：If the angle of view of the short-focus image is too large in S3, it needs to perform distortion correction and then enter S4, otherwise directly enter S4, as shown in Figure 4, the distortion correction is specifically:
S3.1拍摄棋盘格图像；S3.1 Take a checkerboard image;
S3.2将棋盘格图像中心平移移到原点，利用桶形失真校正公式S3.2 Translate the center of the checkerboard image to the origin, and use the barrel distortion correction formula
x1=x(1+k1x2+k2y2)x1 =x(1+k1 x2 +k2 y2 )
y1=y(1+k1x2+k2y2)y1 =y(1+k1 x2 +k2 y2 )
调整参数k1和k2，遍历所有离散整数坐标得到畸变校正的离散浮点坐标表格X1和Y1，其中x和y是原始棋盘格图像的浮点坐标，x1和y1是畸变校正后棋盘格图像的离散整数坐标，X1和Y1为畸变校正的X坐标表格和Y坐标表格。Adjust the parameters k1 and k2 to traverse all the discrete integer coordinates to obtain the distortion-corrected discrete floating-point coordinate tables X1 and Y1, where x and y are the floating-point coordinates of the original checkerboard image, and x1 and y1 are the distortion-corrected checkerboard image The discrete integer coordinates of , X1 and Y1 are the distortion-corrected X-coordinate table and Y-coordinate table.
S4利用短焦图像的对应点组a和长焦图像对应点组b分别对短焦图像和长焦图像计算得到2个3*3单应矩阵进行极线校正，得到仅存在水平视差的两张图像，所述短焦图像包括未进行畸变校正的短焦图像或已进行畸变校正的短焦图像。S4 Use the corresponding point group a of the short-focus image and the corresponding point group b of the telephoto image to calculate two 3*3 homography matrices for the short-focus image and the telephoto image respectively, and perform epipolar correction to obtain two images with only horizontal parallax The short-focus image includes a short-focus image without distortion correction or a short-focus image with distortion correction.
所述极线校正具体为：The polar line correction is specifically:
S4.1分别求解进行畸变校正后的短焦图像或未进行畸变校正的短焦图像和长焦图像的基本矩阵，基本矩阵的特征向量为极点；S4.1 Respectively solve the basic matrix of the short-focus image after distortion correction or the short-focus image and long-focus image without distortion correction, and the eigenvector of the basic matrix is a pole;
S4.2将短焦图像组和长焦图像组的极点旋转到x轴并且移到无穷远使得两图像的极线与x轴平行，再对每组图像中任一幅图像进行y方向的线性缩放，得到能够用于短焦图像和长焦图像极线校正的2个3×3单应矩阵；S4.2 Rotate the poles of the short-focus image group and the telephoto image group to the x-axis and move them to infinity so that the polar lines of the two images are parallel to the x-axis, and then perform y-direction rotation on any image in each group of images Linear scaling to obtain two 3×3 homography matrices that can be used for epipolar correction of short-focus images and telephoto images;
S4.3遍历所有离散整数坐标，求解极线校正后的图像离散浮点坐标表格X2和Y2，X2和Y2为极线校正的X坐标表格和Y坐标表格；S4.3 traverse all the discrete integer coordinates, and solve the epipolar-corrected image discrete floating-point coordinate tables X2 and Y2, where X2 and Y2 are the polar-corrected X-coordinate table and Y-coordinate table;
S5获取视差和深度关系，并根据该关系，确定不同焦距下的视差可信范围。S5 acquires the relationship between the parallax and the depth, and according to the relationship, determines the credible range of the parallax at different focal lengths.
如图3所示，具体为：在不同的距离下拍摄某已知深度物体的双目图像，对图像进行前述的畸变和极线校正后；通过获取两张图像的对应点，建立对应点的离散视差和深度对应关系；再使用曲线拟合得到稠密的视差和深度关系，最后根据视差相差1个像素对应深度相差的实际距离选定视差可信范围。As shown in Figure 3, the specific steps are: take a binocular image of a known depth object at different distances, and perform the aforementioned distortion and epipolar correction on the image; by obtaining the corresponding points of the two images, establish the corresponding point Discrete the corresponding relationship between parallax and depth; then use curve fitting to obtain the dense parallax and depth relationship, and finally select the credible range of parallax according to the actual distance of the depth difference corresponding to the difference of 1 pixel in the parallax.
S6对于极线校正后的短焦图像，利用深度和视差的公式求解深度，判断是否在视差可信范围，若在可信范围内则保留所求深度，否则继续查看该短焦图像的对应点是否都在对应点组c里，若是，则利用长焦图像的对应点组b的视差求解深度，否则不保留该深度信息。S6 For the epipolar-corrected short-focus image, use the formula of depth and parallax to solve the depth, and judge whether it is within the credible range of parallax. If it is within the credible range, keep the required depth; otherwise, continue to check the corresponding point of the short-focus image. Whether they are all in the corresponding point group c, if so, use the parallax of the corresponding point group b of the telephoto image to calculate the depth, otherwise the depth information will not be retained.
进一步，在S4中针对短焦图像，将畸变校正和极线校正的两个离散坐标表格合并成一个。Further, in S4, for the short-focus image, the two discrete coordinate tables for distortion correction and epipolar line correction are combined into one.
具体为：Specifically:
针对X坐标：X1为畸变校正表格，X2为极线校正表格，X3为合成表，floor代表不大于该浮点数的最大整数，i代表第i行，j代表第j列，则转换公式为X3(i,j)=X2(i,floor(X1(i,j)))+(X2(i,1+floor(X1(i,j)))-X2(i,floor(X1(i,j))))*(X1(i,j)-floor(X1(i,j)))。针对Y坐标：Y1为畸变校正表格，Y2为极线校正表格，Y3为合成表Y3(i,j)=Y2(floor(Y1(i,j)),j)+(Y2(1+floor(Y1(i,j)),j)-Y2(floor(Y1(i,j)),j))*(Y1(i,j)-floor(Y1(i,j)))。For the X coordinate: X1 is the distortion correction table, X2 is the epipolar line correction table, X3 is the synthesis table, floor represents the largest integer not greater than the floating point number, i represents the i-th row, and j represents the j-th column, then the conversion formula is X3 (i,j)=X2 (i,floor(X1 (i,j)))+(X2 (i,1+floor(X1 (i,j)))-X2 (i,floor (X1 (i,j))))*(X1 (i,j)-floor(X1 (i,j))). For the Y coordinate: Y1 is the distortion correction table, Y2 is the epipolar line correction table, Y3 is the synthesis table Y3 (i,j)=Y2 (floor(Y1 (i,j)),j)+(Y2 ( 1+floor(Y1 (i,j)),j)-Y2 (floor(Y1 (i,j)),j))*(Y1 (i,j)-floor(Y1 (i, j))).
上述实施例为本发明较佳的实施方式，但本发明的实施方式并不受所述实施例的限制，其他的任何未背离本发明的精神实质与原理下所作的改变、修饰、替代、组合、简化，均应为等效的置换方式，都包含在本发明的保护范围之内。The above-mentioned embodiment is a preferred embodiment of the present invention, but the embodiment of the present invention is not limited by the embodiment, and any other changes, modifications, substitutions and combinations made without departing from the spirit and principle of the present invention , simplification, all should be equivalent replacement methods, and are all included in the protection scope of the present invention.
Claims (7)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410035353.5ACN103776419B (en) | 2014-01-24 | 2014-01-24 | A kind of binocular distance measurement method improving measurement range |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410035353.5ACN103776419B (en) | 2014-01-24 | 2014-01-24 | A kind of binocular distance measurement method improving measurement range |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103776419Atrue CN103776419A (en) | 2014-05-07 |
| CN103776419B CN103776419B (en) | 2016-01-06 |
Family
ID=50568945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410035353.5AExpired - Fee RelatedCN103776419B (en) | 2014-01-24 | 2014-01-24 | A kind of binocular distance measurement method improving measurement range |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103776419B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200450A (en)* | 2014-08-25 | 2014-12-10 | 华南理工大学 | Infrared thermal image resolution enhancing method |
| CN104539934A (en)* | 2015-01-05 | 2015-04-22 | 京东方科技集团股份有限公司 | Image collecting device and image processing method and system |
| CN105783731A (en)* | 2016-03-08 | 2016-07-20 | 上海易景信息科技有限公司 | Method for measuring length of measured object by means of double cameras |
| CN106225723A (en)* | 2016-07-25 | 2016-12-14 | 浙江零跑科技有限公司 | A kind of many trains splice angle measuring method based on backsight binocular camera |
| CN107036579A (en)* | 2016-11-17 | 2017-08-11 | 上海航天控制技术研究所 | A kind of target relative positioning method based on monocular liquid lens optical system |
| CN107688174A (en)* | 2017-08-02 | 2018-02-13 | 北京纵目安驰智能科技有限公司 | A kind of image distance-finding method, system, storage medium and vehicle-mounted visually-perceptible equipment |
| WO2018077218A1 (en)* | 2016-10-31 | 2018-05-03 | 杭州海康威视数字技术股份有限公司 | Depth measuring method and system |
| CN108492325A (en)* | 2018-03-27 | 2018-09-04 | 长春理工大学 | A kind of image registration device, method for registering images and the system of non co axial imaging |
| CN109091099A (en)* | 2018-05-11 | 2018-12-28 | 上海交通大学 | The high definition miniature electronic endoscopic system of binocular vision |
| CN111210468A (en)* | 2018-11-22 | 2020-05-29 | 中移（杭州）信息技术有限公司 | Image depth information acquisition method and device |
| CN111292367A (en)* | 2020-02-18 | 2020-06-16 | 青岛联合创智科技有限公司 | Binocular camera depth map generation method with variable baseline |
| CN111951339A (en)* | 2020-07-15 | 2020-11-17 | 苏州易航远智智能科技有限公司 | Image processing method for disparity calculation using heterogeneous binocular cameras |
| CN112129262A (en)* | 2020-09-01 | 2020-12-25 | 珠海市一微半导体有限公司 | Visual ranging method and visual navigation chip of multi-camera group |
| CN112700502A (en)* | 2020-12-29 | 2021-04-23 | 西安电子科技大学 | Binocular camera system and binocular camera space calibration method |
| CN114519748A (en)* | 2022-04-20 | 2022-05-20 | 清华大学 | Leg-foot kinematics calibration method, system, equipment and medium of four-foot robot |
| CN115641368A (en)* | 2022-10-31 | 2023-01-24 | 安徽农业大学 | Method for extracting characteristics of defocused checkerboard image for calibration |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090141260A1 (en)* | 2007-11-30 | 2009-06-04 | Nissan Motor Co., Ltd. | Distance measurement system and distance measurement method |
| JP2011145143A (en)* | 2010-01-14 | 2011-07-28 | Ricoh Co Ltd | Distance measuring device and distance measuring method |
| CN103236082A (en)* | 2013-04-27 | 2013-08-07 | 南京邮电大学 | Quasi-three dimensional reconstruction method for acquiring two-dimensional videos of static scenes |
| CN103292710A (en)* | 2013-05-27 | 2013-09-11 | 华南理工大学 | Distance measuring method applying binocular visual parallax error distance-measuring principle |
- 2014
- 2014-01-24CNCN201410035353.5Apatent/CN103776419B/ennot_activeExpired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090141260A1 (en)* | 2007-11-30 | 2009-06-04 | Nissan Motor Co., Ltd. | Distance measurement system and distance measurement method |
| JP2011145143A (en)* | 2010-01-14 | 2011-07-28 | Ricoh Co Ltd | Distance measuring device and distance measuring method |
| CN103236082A (en)* | 2013-04-27 | 2013-08-07 | 南京邮电大学 | Quasi-three dimensional reconstruction method for acquiring two-dimensional videos of static scenes |
| CN103292710A (en)* | 2013-05-27 | 2013-09-11 | 华南理工大学 | Distance measuring method applying binocular visual parallax error distance-measuring principle |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200450B (en)* | 2014-08-25 | 2017-08-25 | 华南理工大学 | A kind of thermal-induced imagery definition enhancing method |
| CN104200450A (en)* | 2014-08-25 | 2014-12-10 | 华南理工大学 | Infrared thermal image resolution enhancing method |
| CN104539934A (en)* | 2015-01-05 | 2015-04-22 | 京东方科技集团股份有限公司 | Image collecting device and image processing method and system |
| US9712808B2 (en) | 2015-01-05 | 2017-07-18 | Boe Technology Group Co., Ltd. | Image acquisition device and image processing method and system |
| CN105783731A (en)* | 2016-03-08 | 2016-07-20 | 上海易景信息科技有限公司 | Method for measuring length of measured object by means of double cameras |
| CN106225723B (en)* | 2016-07-25 | 2019-03-29 | 浙江零跑科技有限公司 | A kind of hinged angle measuring method of multiple row vehicle based on backsight binocular camera |
| CN106225723A (en)* | 2016-07-25 | 2016-12-14 | 浙江零跑科技有限公司 | A kind of many trains splice angle measuring method based on backsight binocular camera |
| CN108020200A (en)* | 2016-10-31 | 2018-05-11 | 杭州海康威视数字技术股份有限公司 | A kind of depth measurement method and system |
| WO2018077218A1 (en)* | 2016-10-31 | 2018-05-03 | 杭州海康威视数字技术股份有限公司 | Depth measuring method and system |
| US11209268B2 (en) | 2016-10-31 | 2021-12-28 | Hangzhou Hikvision Digital Technology Co., Ltd. | Depth measuring method and system |
| CN108020200B (en)* | 2016-10-31 | 2020-02-28 | 杭州海康威视数字技术股份有限公司 | Depth measurement method and system |
| CN107036579A (en)* | 2016-11-17 | 2017-08-11 | 上海航天控制技术研究所 | A kind of target relative positioning method based on monocular liquid lens optical system |
| CN107688174A (en)* | 2017-08-02 | 2018-02-13 | 北京纵目安驰智能科技有限公司 | A kind of image distance-finding method, system, storage medium and vehicle-mounted visually-perceptible equipment |
| CN108492325A (en)* | 2018-03-27 | 2018-09-04 | 长春理工大学 | A kind of image registration device, method for registering images and the system of non co axial imaging |
| CN109091099A (en)* | 2018-05-11 | 2018-12-28 | 上海交通大学 | The high definition miniature electronic endoscopic system of binocular vision |
| CN111210468A (en)* | 2018-11-22 | 2020-05-29 | 中移（杭州）信息技术有限公司 | Image depth information acquisition method and device |
| CN111210468B (en)* | 2018-11-22 | 2023-07-11 | 中移（杭州）信息技术有限公司 | A method and device for acquiring image depth information |
| CN111292367A (en)* | 2020-02-18 | 2020-06-16 | 青岛联合创智科技有限公司 | Binocular camera depth map generation method with variable baseline |
| CN111292367B (en)* | 2020-02-18 | 2023-04-07 | 青岛联合创智科技有限公司 | Binocular camera depth map generation method with variable baseline |
| CN111951339A (en)* | 2020-07-15 | 2020-11-17 | 苏州易航远智智能科技有限公司 | Image processing method for disparity calculation using heterogeneous binocular cameras |
| CN112129262A (en)* | 2020-09-01 | 2020-12-25 | 珠海市一微半导体有限公司 | Visual ranging method and visual navigation chip of multi-camera group |
| CN112700502A (en)* | 2020-12-29 | 2021-04-23 | 西安电子科技大学 | Binocular camera system and binocular camera space calibration method |
| CN112700502B (en)* | 2020-12-29 | 2023-08-01 | 西安电子科技大学 | Binocular camera system and binocular camera space calibration method |
| CN114519748A (en)* | 2022-04-20 | 2022-05-20 | 清华大学 | Leg-foot kinematics calibration method, system, equipment and medium of four-foot robot |
| CN115641368A (en)* | 2022-10-31 | 2023-01-24 | 安徽农业大学 | Method for extracting characteristics of defocused checkerboard image for calibration |
| CN115641368B (en)* | 2022-10-31 | 2024-06-04 | 安徽农业大学 | Out-of-focus checkerboard image feature extraction method for calibration |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103776419B (en) | 2016-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103776419B (en) | A kind of binocular distance measurement method improving measurement range | |
| CN102176755B (en) | Control method and device based on eye movement three-dimensional display angle | |
| CN106709865B (en) | Depth image synthesis method and device | |
| CN109285189B (en) | A fast calculation method of linear trajectory without binocular synchronization | |
| CN203616781U (en) | Binocular three-dimensional reconstruction visual system based on slide guide rails | |
| JP2019510234A (en) | Depth information acquisition method and apparatus, and image acquisition device | |
| CN109084959B (en) | An Optical Axis Parallelism Correction Method Based on Binocular Ranging Algorithm | |
| CN207766424U (en) | A shooting device and imaging device | |
| CN106896343B (en) | Servo follow-up machine vision device and dynamic tracking ranging method | |
| CN101272511A (en) | Method and device for acquiring image depth information and image pixel information | |
| Zhou et al. | A two-step calibration method of lenslet-based light field cameras | |
| CN102368137B (en) | Embedded calibrating stereoscopic vision system | |
| JP2013513095A (en) | Method and system for obtaining an improved stereo image of an object | |
| CN114359406A (en) | Calibration of auto-focusing binocular camera, 3D vision and depth point cloud calculation method | |
| CN106651957B (en) | Monocular vision object space localization method based on template | |
| CN101858741A (en) | A method of zoom distance measurement based on single camera | |
| Patel et al. | Distance measurement system using binocular stereo vision approach | |
| CN101858742A (en) | A single-camera-based fixed-focus ranging method | |
| CN114383543B (en) | WAAM molten pool three-dimensional reconstruction method | |
| CN108981608A (en) | A kind of Novel wire Constructed Lighting Vision System and scaling method | |
| CN105258673A (en) | Target range finding method and apparatus based on binocular synthetic aperture focus image | |
| CN103134444B (en) | The varifocal three-dimension measuring system of double-view field | |
| JP2013224895A (en) | Three dimensional measuring device | |
| CN105139336B (en) | A kind of method of multichannel full-view image conversion ball curtain flake film | |
| CN105137606B (en) | Stereo vision imaging apparatus and method based on DMD |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20160106 |