CN113963054A - Intelligent express box size measuring method and system based on binocular camera - Google Patents
Intelligent express box size measuring method and system based on binocular camera Download PDFInfo
- Publication number
- CN113963054A CN113963054A CN202111241872.3A CN202111241872A CN113963054A CN 113963054 A CN113963054 A CN 113963054A CN 202111241872 A CN202111241872 A CN 202111241872A CN 113963054 A CN113963054 A CN 113963054A
- Authority
- CN
- China
- Prior art keywords
- image
- camera
- binocular camera
- express box
- box
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000005259 measurement Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 238000004519 manufacturing process Methods 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000012937 correction Methods 0.000 claims description 12
- 238000013519 translation Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000000691 measurement method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The embodiment of the invention discloses an intelligent express box size measuring method and system based on a binocular camera, which adopts the binocular camera to realize a non-contact measuring mode and can realize real-time measurement on a production line; through a series of image processing algorithms, the length, the width and the height of the express box can be efficiently detected from one image in real time, and the detection precision and the robustness are high; the system constructed by the scheme can measure the sizes of the express boxes with different sizes with the same precision.
Description
Technical Field
The embodiment of the invention relates to the technical field of binocular camera distance measurement and automatic assembly lines, in particular to an intelligent express box size measuring method and system based on a binocular camera.
Background
With the development of digital economy and personalized customized production, the demand for automated intelligent pipelines is expanding day by day. In an automatic assembly line, different production tasks are distributed according to express boxes with different sizes, and a key link of non-standardized production is provided. The existing size measurement methods mainly comprise manual measurement and sensor contact measurement. The manual measurement method is time-consuming, labor-consuming, high in cost and low in efficiency, and is not suitable for the requirements of assembly line production. Although the contact measurement of the sensor can realize automatic measurement, the object to be measured needs to be placed in the measuring device statically when the measurement is carried out, and the measurement efficiency is low. Therefore, a non-contact efficient measurement mode is urgently needed, and the requirements of an automatic intelligent production line are met.
Disclosure of Invention
Therefore, the embodiment of the invention provides an intelligent express box size measuring method and system based on a binocular camera, and aims to solve the problems of time and labor waste, high cost, low measuring efficiency and the like of the conventional size measuring method.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
according to a first aspect of the embodiment of the invention, a binocular camera-based intelligent express box size measuring method is provided, and the method comprises the following steps:
collecting an express box image on a conveyor belt of a production line through a binocular camera;
detecting whether the image has an express delivery box or not, if not, continuing to acquire the image, and if so, performing distortion removal and correction processing on the image;
calculating the corrected image to obtain a disparity map;
performing vertex detection on the corrected image to obtain image coordinates of the length, width and height vertexes of the express box;
and calculating the actual size and volume of the length, width and height of the express box according to a reprojection matrix from the image coordinates to the world coordinates of the binocular camera, the disparity map and the image coordinates of the length, width and height vertexes of the express box.
Further, the method further comprises:
calibrating a left monocular camera and a right monocular camera which form the binocular camera respectively to obtain internal parameters, external parameters and distortion coefficients of the two monocular cameras;
and carrying out distortion removal processing on the image according to the internal parameters, the external parameters and the distortion coefficients of the two monocular cameras.
Further, the method further comprises:
correcting the binocular camera to obtain a rotation matrix R and a translational vector T from the left camera to the right camera;
using the rotation matrix R and the translation vector T to carry out binocular correction on calibration images acquired in advance, so that the images of the left camera and the right camera are located on the same plane;
and calculating a reprojection matrix from the image coordinates to world coordinates according to the corrected images of the left camera and the right camera.
Further, the vertex detection is carried out on the corrected image, and the image coordinates of the length, the width and the height of the express box are obtained, and the method specifically comprises the following steps:
separating the express box from the image background by using color screening and binarization processing to obtain a binarized mask image;
searching the outline of the object with the largest area in the mask image, and further searching the minimum circumscribed rectangle;
searching four points closest to the vertex of the minimum circumscribed rectangle on the object contour, and sequencing the points according to a clockwise order, namely the vertex of the maximum inscribed rectangle;
according to the obtained four vertexes, if the absolute value of the difference between the inclination angles of the left vertical side and the right vertical side and 90 degrees is larger than a preset threshold, correcting the vertexes of the vertical sides, wherein the correction method comprises the following steps: for two vertexes of a vertical edge, matching all pixel points in a certain neighborhood of one vertex with all pixel points in a certain neighborhood of the other vertex one by one, and selecting two pixel points with the inclination angle closest to 90 degrees as new vertexes after removing abnormal values;
according to the four corrected vertexes P1, P2, P3 and P4, if only two sides of the express box can be obtained and the third side cannot be obtained, a null value is output, if three sides of the express box can be obtained, an area below a straight line P3-P4 is selected in the object outline, and the vertex farthest from the straight line P3-P4 is searched in the area and is marked as a point P5, and pixel coordinates { [ (P1u, P1v), (P4u, P4v) ], [ (P4 v ), (P5 v, P5v) ], [ (P5 v ), (P3 v, P3v) ] }, namely the pixel coordinates of the three sides of the box length, width and height are searched.
Further, the method further comprises:
and processing and calculating a plurality of continuous acquired images which all contain the express box to obtain a plurality of groups of size data, and averaging the plurality of groups of data to obtain the final size and volume of the express box.
According to a second aspect of the embodiments of the present invention, there is provided a binocular camera-based intelligent express box size measurement system, the system including:
the binocular camera measuring module is used for acquiring an express box image on the assembly line conveyor belt through a binocular camera;
the processing module is used for detecting whether the express delivery box exists in the image or not, if not, image acquisition is continued, and if so, distortion removal and correction processing are carried out on the image;
calculating the corrected image to obtain a disparity map;
performing vertex detection on the corrected image to obtain image coordinates of the length, width and height vertexes of the express box;
and calculating the actual size and volume of the length, width and height of the express box according to a reprojection matrix from the image coordinates to the world coordinates of the binocular camera, the disparity map and the image coordinates of the length, width and height vertexes of the express box.
Furthermore, the binocular camera is installed on the outer side of the turning of the conveyor belt of the assembly line, and a white board is placed on the other side of the conveyor belt and serves as a background board.
According to a third aspect of embodiments of the present invention, there is provided a computer storage medium having one or more program instructions embodied therein for performing the method of any one of the above by a binocular camera based smart courier box dimension measurement system.
The embodiment of the invention has the following advantages:
according to the intelligent express box size measuring method and system based on the binocular camera, the binocular camera is adopted to achieve a non-contact measuring mode, and real-time measurement on a production line can be achieved; through a series of image processing algorithms, the length, the width and the height of the express box can be efficiently detected from one image in real time, and the detection precision and the robustness are high; the system constructed by the scheme can measure the sizes of the express boxes with different sizes with the same precision.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
Fig. 1 is a schematic flow chart of a binocular camera-based intelligent express box size measurement method provided in embodiment 1 of the present invention;
fig. 2 is a monocular camera calibration flowchart of the binocular camera-based intelligent express delivery box size measurement method provided in embodiment 1 of the present invention;
fig. 3 is a template diagram of monocular camera calibration in the method for measuring the size of an intelligent express delivery box based on a binocular camera according to embodiment 1 of the present invention;
fig. 4 is a hardware installation schematic diagram of a binocular camera-based intelligent express box size measurement method provided in embodiment 1 of the present invention;
fig. 5 is a schematic diagram of the top point of an express delivery box of the binocular camera-based intelligent express delivery box size measurement method provided in embodiment 1 of the present invention;
fig. 6 is an implementation flowchart of a binocular camera-based intelligent express box size measurement method provided in embodiment 1 of the present invention.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in fig. 1, the embodiment provides an intelligent express delivery box size measuring method based on a binocular camera by using a binocular camera ranging principle. The binocular distance measurement is a method for acquiring three-dimensional position information by acquiring two images of an object to be measured from imaging equipment at different positions and calculating the pixel difference of a matching point in the two images based on the principle of parallax. It is an inexpensive, non-contact measurement scheme. Specifically, the method mainly comprises the following steps:
s100, collecting images of the express boxes on the conveyor belt of the assembly line through a binocular camera.
Before image acquisition, monocular camera calibration, binocular camera calibration and binocular camera installation processing need to be performed on the binocular camera measurement system. Specifically, the method comprises the following steps:
1. monocular camera calibration
Before two cameras are used to form a binocular camera system (the two cameras are respectively marked as a left camera and a right camera), the monocular cameras need to be respectively calibrated. Solving internal and external parameters and distortion parameters of the camera through corresponding pixel points in a world coordinate system and an image coordinate system, wherein the specific implementation steps are as shown in figure 2:
1-1, preparing a calibration template: the calibration template is printed and attached to a flat surface, and a commonly used calibration template is shown in fig. 3.
1-2 shooting template images: a left camera and a right camera are used for shooting a plurality of template images from different angles, different inclinations and different sizes of the calibration template in the images at the same time, and more than 10 pairs of images are generally needed according to experience.
1-3, respectively executing the steps (1-4) to (1-8) on the left camera and the right camera to obtain respective internal parameters and distortion coefficients.
1-4, detecting image characteristic points: the mesh feature points of the standard template in each image are detected, and image coordinates (ui, vi) (i ═ 1,2, …) are extracted. Assuming that the physical coordinates of the upper left grid point of the template grid feature point are (0,0,0), the world coordinates (xi, yi, zi) of the grid feature point can be obtained because the template grid size is known (i ═ 1,2, …).
1-5 solving camera intrinsic parameters and extrinsic parameters: and (4) according to the image coordinates and the corresponding physical coordinates of the grid feature points extracted in the step (3), solving the internal parameters and the external parameters of the camera under the ideal distortion-free condition.
The specific calculation process is as follows:
1-6, setting the coordinate of any point in the space in the image as (u, v), and the coordinate corresponding to the world coordinate as (x, y, z), wherein according to the principle of pinhole imaging, the two coordinates satisfy:
wherein R, T are camera extrinsic parameters and K is camera intrinsic parameters.
1-7, substituting the image coordinates (ui, vi) (i ═ 1,2, …) of the image feature points obtained in the step (1-4) and the corresponding world coordinates (xi, yi, zi) (i ═ 1,2, …) into the equation (1), and solving the equation system to obtain the camera external parameters R, T and the internal parameters K.
1-8 solving distortion coefficient: and 3) according to the image coordinates and the corresponding physical coordinates of the grid characteristic points extracted in the step 3), calculating an actual distortion coefficient by using a least square method. The image distortion includes mirror image distortion and tangential distortion, and (u, v) is set as an ideal pixel coordinate, (udr,vdr) For the pixel coordinates after radial distortion, the mathematical model of radial distortion is:
(udt,vdt) For the pixel point coordinate after the tangential distortion, the mathematical model of the tangential distortion is as follows:
D=(k1,k2,k3,p1,p2) I.e. the distortion parameter.
1-9 outputs external parameters Rl, Tl, internal parameter K1, distortion parameter Dl of the left camera, external parameters Rr, Tr, internal parameter Kr, distortion parameter Dr of the right camera.
2. Binocular camera system calibration
For binocular vision, two cameras are provided, and objects to be measured can be observed from different directions. The image parallax (the difference of the pixel distances of the point to be measured in the left and right camera images) in the binocular vision brings depth information, and the real world coordinate value of the point to be measured can be calculated through the principle of triangulation. The specific implementation steps are as follows:
2-1, acquiring the template images shot in the step (1-2), and recording the images of the left camera and the right camera shot at the same time as a group.
2-2, substituting the internal parameters and distortion coefficients of the left camera and the right camera obtained in the step (1-8) into the equations (2) and (3) for each group of template images to realize image distortion removal.
2-3, respectively extracting image coordinates (uli, vli) and (uri, vri) of grid characteristic points of the left camera image and the right camera image and corresponding physical coordinates (xi, yi) of the grid characteristic points for each group of template images.
2-4 obtaining the image coordinates and corresponding physical coordinates of the left camera and the right camera from (2-3) and obtaining the left camera and the right camera internal parameters from (1-8)And T ═ Tr-RTlAnd calibrating the binocular camera to obtain a rotation matrix R and a translation vector T from the left camera to the right camera.
2-5, using the calibrated rotation matrix R and translation vector T of the binocular camera to carry out binocular correction on each group of images, so that the images of the left camera and the right camera are positioned on the same plane.
2-6, calculating a reprojection matrix from the image coordinates to the world coordinates according to the corrected left and right images. The reprojection matrix may convert two-dimensional points in the image plane to three-dimensional coordinates in the world coordinate system.
3. Binocular camera measurement system installation on automatic production line
And (3) mounting the binocular camera calibrated according to the step (1) and the step (2) on the outer side of the turning position of the conveyor belt of the automatic assembly line, wherein the distance between the binocular camera and the center of the conveyor belt is about 1-1.5 m, and the mounting height of the binocular camera is 10-20 cm higher than that of the conveyor belt. A white plate is arranged on the other side of the conveying belt to serve as a background plate, and the conveying belt is black or dark brown. The conveyer belt operation guarantees that only one express delivery case gets into in the image field of vision of binocular camera at the same moment. The binocular camera is connected to the computing terminal, and the binocular camera is controlled by the computing terminal to acquire images and calculate the size. The size of an express box which can be measured by the binocular camera measuring system is 5 cm-100 cm. A schematic of the measurement system is shown in fig. 4.
S200, detecting whether an express box exists in the image, if not, continuing to collect the image, and if so, performing distortion removal and correction processing on the image.
The image distortion removal processing specifically includes:
respectively calibrating a left monocular camera and a right monocular camera which form a binocular camera according to the calibration in the step (1) and the monocular camera calibration to obtain internal parameters, external parameters and distortion coefficients of the two monocular cameras;
and carrying out distortion removal processing on the image according to the internal parameters, the external parameters and the distortion coefficients of the two monocular cameras.
And (5) correcting the undistorted image according to the method in the step (2-5) to obtain a corrected image.
And S300, calculating the corrected image to obtain a disparity map. And performing stereo matching according to the corrected image, and calculating parallax to obtain a parallax map.
S400, carrying out vertex detection on the corrected image to obtain the image coordinates of the length, width and height vertexes of the express box.
The method specifically comprises the following steps:
4-1, separating the express box from the image background by using color screening and binarization processing to obtain a binarized mask image;
4-2, searching the outline of the object with the largest area in the mask image, and further searching the smallest circumscribed rectangle;
4-3, searching four points closest to the vertex of the minimum circumscribed rectangle on the object contour, and sequencing the points according to a clockwise order, namely the vertex of the maximum inscribed rectangle;
4-4 because the horizontal plane of the binocular camera is parallel to the conveyor belt, the vertical edges of the courier box are also vertical (noted as 90 °) in the camera image. According to the obtained four vertexes, if the absolute value of the difference between the inclination angles of the left and right vertical sides and 90 ° is greater than a preset threshold (according to experience, the threshold can be set to be 3 °), the vertexes of the vertical sides are corrected by: for two vertexes of a vertical edge, matching all pixel points in a certain neighborhood of one vertex with all pixel points in a certain neighborhood of the other vertex one by one (according to experience, a square with the side length of 3 pixels can be selected), and after removing an abnormal value, selecting two pixel points with the inclination angle closest to 90 degrees as new vertexes;
4-5, according to the four modified vertexes P1, P2, P3 and P4, if only two sides of the express box can be obtained and the third side cannot be obtained (as shown in fig. 5a, in this case, one side of the express box faces the camera), a null value is output, and if three sides of the express box can be obtained (as shown in fig. 5b, in this case, one side of the express box faces the binocular camera), a region below the straight line P3-P4 is selected in the object contour, and a vertex farthest from the straight line P3-P4 is found in the region, and is marked as a point P5, an output line P1-P4, a pixel coordinate { [ (P1u, P1v), (P4u, P4v) ], [ (P4 v ), (P5 v, P5v) ], (P5, P v, P3) is a pixel coordinate of a three-high width (P5972).
S500, calculating to obtain the actual size and the volume of the length, the width and the height of the express box according to a reprojection matrix from the image coordinates to the world coordinates of the binocular camera, a disparity map and the image coordinates of the length, the width and the height vertexes of the express box.
Correcting the binocular camera according to the calibration in the step (2) to obtain a rotation matrix R and a translation vector T from the left camera to the right camera;
performing binocular correction on the pre-collected calibration images by using the rotation matrix R and the translation vector T, so that the images of the left camera and the right camera are positioned on the same plane;
and calculating a reprojection matrix from the image coordinates to world coordinates according to the corrected images of the left camera and the right camera.
And (4) calculating to obtain the actual size of the length, the width and the height of the express box according to the reprojection matrix in the step (2-6), the calculated parallax map and the image coordinates of the length, the width and the height vertexes of the express box. And calculating according to a volume formula of the cuboid to obtain the volume of the express box. And outputting the length, width, height and volume of the express box, and continuously acquiring images to enter the next measurement, as shown in fig. 6.
Further, the method further comprises:
and processing and calculating a plurality of continuous acquired images which all contain the express box to obtain a plurality of groups of size data, and averaging the plurality of groups of data to obtain the final size and volume of the express box.
According to the intelligent express box size measuring method based on the binocular camera, the binocular camera is adopted to realize a non-contact measuring mode, and real-time measurement on a production line can be realized; through a series of image processing algorithms, the length, the width and the height of the express box can be efficiently detected from one image in real time, and the detection precision and the robustness are high; the system constructed by the scheme can measure the sizes of the express boxes with different sizes with the same precision.
Example 2
Corresponding with above-mentioned embodiment 1, this embodiment has provided an intelligence express delivery case size measurement system based on binocular camera, and this system includes:
the binocular camera measuring module is used for acquiring an express box image on the assembly line conveyor belt through a binocular camera;
the processing module is used for detecting whether the express delivery box exists in the image or not, if not, continuing to acquire the image, and if so, performing distortion removal and correction processing on the image;
calculating the corrected image to obtain a disparity map;
performing vertex detection on the corrected image to obtain image coordinates of the length, width and height vertexes of the express box;
and calculating to obtain the actual size and volume of the length, width and height of the express box according to a reprojection matrix from the image coordinates to the world coordinates of the binocular camera, the disparity map and the image coordinates of the length, width and height vertexes of the express box.
Furthermore, the binocular camera is installed on the outer side of the turning position of the conveyor belt of the assembly line, and a white board is placed on the other side of the conveyor belt and serves as a background board.
The functions executed by each component in the binocular camera-based intelligent express box size measuring system provided by the embodiment of the invention are described in detail in the embodiment 1, and therefore, redundant description is not repeated here.
Example 3
In accordance with the embodiments described above, the present embodiments provide a computer storage medium having one or more program instructions embodied therein for use by a binocular camera based intelligent courier box dimension measurement system to perform the method of embodiment 1.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (8)
1. A binocular camera-based intelligent express box size measuring method is characterized by comprising the following steps:
collecting an express box image on a conveyor belt of a production line through a binocular camera;
detecting whether the image has an express delivery box or not, if not, continuing to acquire the image, and if so, performing distortion removal and correction processing on the image;
calculating the corrected image to obtain a disparity map;
performing vertex detection on the corrected image to obtain image coordinates of the length, width and height vertexes of the express box;
and calculating the actual size and volume of the length, width and height of the express box according to a reprojection matrix from the image coordinates to the world coordinates of the binocular camera, the disparity map and the image coordinates of the length, width and height vertexes of the express box.
2. The binocular camera-based intelligent express box size measuring method of claim 1, further comprising:
calibrating a left monocular camera and a right monocular camera which form the binocular camera respectively to obtain internal parameters, external parameters and distortion coefficients of the two monocular cameras;
and carrying out distortion removal processing on the image according to the internal parameters, the external parameters and the distortion coefficients of the two monocular cameras.
3. The binocular camera-based intelligent express box size measuring method of claim 1, further comprising:
correcting the binocular camera to obtain a rotation matrix R and a translational vector T from the left camera to the right camera;
using the rotation matrix R and the translation vector T to carry out binocular correction on calibration images acquired in advance, so that the images of the left camera and the right camera are located on the same plane;
and calculating a reprojection matrix from the image coordinates to world coordinates according to the corrected images of the left camera and the right camera.
4. The binocular camera-based intelligent express delivery box size measuring method of claim 1, wherein the vertex detection is performed on the corrected image to obtain image coordinates of the length, width and height vertices of the express delivery box, and the method specifically comprises the following steps:
separating the express box from the image background by using color screening and binarization processing to obtain a binarized mask image;
searching the outline of the object with the largest area in the mask image, and further searching the minimum circumscribed rectangle;
searching four points closest to the vertex of the minimum circumscribed rectangle on the object contour, and sequencing the points according to a clockwise order, namely the vertex of the maximum inscribed rectangle;
according to the obtained four vertexes, if the absolute value of the difference between the inclination angles of the left vertical side and the right vertical side and 90 degrees is larger than a preset threshold, correcting the vertexes of the vertical sides, wherein the correction method comprises the following steps: for two vertexes of a vertical edge, matching all pixel points in a certain neighborhood of one vertex with all pixel points in a certain neighborhood of the other vertex one by one, and selecting two pixel points with the inclination angle closest to 90 degrees as new vertexes after removing abnormal values;
according to the four corrected vertexes P1, P2, P3 and P4, if only two sides of the express box can be obtained and the third side cannot be obtained, a null value is output, if three sides of the express box can be obtained, an area below a straight line P3-P4 is selected in the object outline, and the vertex farthest from the straight line P3-P4 is searched in the area and is marked as a point P5, and pixel coordinates { [ (P1u, P1v), (P4u, P4v) ], [ (P4 v ), (P5 v, P5v) ], [ (P5 v ), (P3 v, P3v) ] }, namely the pixel coordinates of the three sides of the box length, width and height are searched.
5. The binocular camera-based intelligent express box size measuring method of claim 1, further comprising:
and processing and calculating a plurality of continuous acquired images which all contain the express box to obtain a plurality of groups of size data, and averaging the plurality of groups of data to obtain the final size and volume of the express box.
6. The utility model provides an intelligence express delivery case size measurement system based on binocular camera which characterized in that, the system includes:
the binocular camera measuring module is used for acquiring an express box image on the assembly line conveyor belt through a binocular camera;
the processing module is used for detecting whether the express delivery box exists in the image or not, if not, image acquisition is continued, and if so, distortion removal and correction processing are carried out on the image;
calculating the corrected image to obtain a disparity map;
performing vertex detection on the corrected image to obtain image coordinates of the length, width and height vertexes of the express box;
and calculating the actual size and volume of the length, width and height of the express box according to a reprojection matrix from the image coordinates to the world coordinates of the binocular camera, the disparity map and the image coordinates of the length, width and height vertexes of the express box.
7. The binocular camera-based intelligent express delivery box size measuring system of claim 6, wherein the binocular camera is installed outside a turning of a conveyor belt of the assembly line, and a white board is placed on the other side of the conveyor belt to serve as a background board.
8. A computer storage medium containing one or more program instructions for performing the method of any of claims 1-5 by a binocular camera based intelligent courier box dimension measurement system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111241872.3A CN113963054A (en) | 2021-10-25 | 2021-10-25 | Intelligent express box size measuring method and system based on binocular camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111241872.3A CN113963054A (en) | 2021-10-25 | 2021-10-25 | Intelligent express box size measuring method and system based on binocular camera |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113963054A true CN113963054A (en) | 2022-01-21 |
Family
ID=79466751
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111241872.3A Pending CN113963054A (en) | 2021-10-25 | 2021-10-25 | Intelligent express box size measuring method and system based on binocular camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113963054A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114842091A (en) * | 2022-04-29 | 2022-08-02 | 广东工业大学 | Binocular egg size assembly line measuring method |
CN114897784A (en) * | 2022-04-13 | 2022-08-12 | 广东工业大学 | Monocular egg size assembly line measuring method |
-
2021
- 2021-10-25 CN CN202111241872.3A patent/CN113963054A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114897784A (en) * | 2022-04-13 | 2022-08-12 | 广东工业大学 | Monocular egg size assembly line measuring method |
CN114897784B (en) * | 2022-04-13 | 2023-02-21 | 广东工业大学 | Monocular egg size assembly line measuring method |
CN114842091A (en) * | 2022-04-29 | 2022-08-02 | 广东工业大学 | Binocular egg size assembly line measuring method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110443836B (en) | Point cloud data automatic registration method and device based on plane features | |
CN109785379B (en) | Method and system for measuring size and weight of symmetrical object | |
CN107424143B (en) | Mining belt conveyor coal quantity detection method based on binocular stereoscopic vision depth perception | |
CN107063228B (en) | Target attitude calculation method based on binocular vision | |
CN103411553B (en) | The quick calibrating method of multi-linear structured light vision sensors | |
CN109211198B (en) | Intelligent target detection and measurement system and method based on trinocular vision | |
CN106969706A (en) | Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision | |
CN113963054A (en) | Intelligent express box size measuring method and system based on binocular camera | |
CN111260720A (en) | Target height measuring system based on deep learning method | |
CN110189375B (en) | Image target identification method based on monocular vision measurement | |
CN103473771A (en) | Method for calibrating camera | |
CN103727930A (en) | Edge-matching-based relative pose calibration method of laser range finder and camera | |
CN111609801A (en) | Multi-size workpiece thickness measuring method and system based on machine vision | |
CN103700082B (en) | Image split-joint method based on dual quaterion relative orientation | |
CN112017234A (en) | Stockpile volume measurement method based on sparse point cloud reconstruction | |
CN112767497A (en) | High-robustness calibration device based on circular calibration plate and positioning method | |
CN113313116A (en) | Vision-based accurate detection and positioning method for underwater artificial target | |
CN114396875A (en) | Rectangular parcel volume measurement method based on vertical shooting of depth camera | |
CN105631868A (en) | Depth information extraction method based on image classification | |
CN110969650B (en) | Intensity image and texture sequence registration method based on central projection | |
CN115410135B (en) | Autonomous-type-carried aviation luggage feature perception reconstruction method and system and application thereof | |
CN110487254B (en) | Rapid underwater target size measuring method for ROV | |
CN110136248B (en) | Transmission shell three-dimensional reconstruction device and method based on binocular stereoscopic vision | |
CN116958218A (en) | Point cloud and image registration method and equipment based on calibration plate corner alignment | |
CN111260735A (en) | External parameter calibration method for single-shot LIDAR and panoramic camera |
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 |