CN110136193B - Rectangular box three-dimensional size measuring method based on depth image and storage medium - Google Patents
Rectangular box three-dimensional size measuring method based on depth image and storage medium Download PDFInfo
- Publication number
- CN110136193B CN110136193B CN201910379796.9A CN201910379796A CN110136193B CN 110136193 B CN110136193 B CN 110136193B CN 201910379796 A CN201910379796 A CN 201910379796A CN 110136193 B CN110136193 B CN 110136193B
- Authority
- CN
- China
- Prior art keywords
- rectangular box
- depth
- map
- depth map
- gray
- 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.)
- Active
Links
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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30112—Baggage; Luggage; Suitcase
Abstract
The rectangular box three-dimensional size measuring method and the storage medium based on the depth image fully utilize the depth image information acquired by the depth camera of the depth camera and the internal parameters of the camera, and realize high measurement precision, wide application range and high universality for quickly and efficiently acquiring the three-dimensional size information of the rectangular box.
Description
Technical Field
The invention belongs to the field of computer vision measurement, and particularly relates to a rectangular box three-dimensional size measuring method based on a depth image and a storage medium.
Background
Along with the rapid development of electronic commerce, the demands and requirements of markets for logistics storage are continuously increased, information such as effective three-dimensional size of an operation object needs to be acquired in multiple links in the logistics industry, most of the operation objects in the prior art are acquired through a traditional manual mode, and the outstanding problems of large workload, complex work content, high labor cost, waste of human resources, low information acquisition efficiency and the like exist.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a rectangular box three-dimensional size measuring method and a storage medium based on a depth image, which can quickly, efficiently and accurately acquire three-dimensional size information of a rectangular box, and have the advantages of high measuring precision, wide application range and high universality.
In order to achieve the purpose, the invention adopts the following technical scheme:
the method for measuring the three-dimensional size of the rectangular box based on the depth image is characterized by comprising the following steps of: the method comprises the following steps:
a. and acquiring a depth map DS0 of the rectangular box placed in the effective shooting area through a depth camera, wherein the distance between the depth camera and the shooting plane is H.
b. Preprocessing the depth map DS0 to obtain a depth map DS2, carrying out gray processing on the depth map DS2 to obtain a gray map GS1, carrying out edge extraction operation to obtain a gray map GS4, and carrying out binarization processing to obtain a gray map GS 5.
c. A line set L consisting of n lines is obtained by utilizing a hough transformation line detection algorithm on the gray-scale image GS5, wherein n is more than or equal to 4.
d.d. creating a set of rectangular box tilt angles PASetting a polar angle threshold epsilon, and classifying the polar angle theta of any straight line in the straight line set L into a rectangular box inclination angle set PAComparing the angle difference between the polar angle of the rest of straight lines in the straight line set L and the polar angle theta of the arbitrary straight line, if the absolute value of the angle difference between the polar angles of the rest of straight lines and the arbitrary straight line is less than the polar angle threshold epsilon, then the polar angle of the straight line is classified into the rectangular box inclination angle set PAIn (1).
e. Calculating a set P of the inclination angles of the rectangular box bodyAMean of all polar angles
If it is
The DS2 is rotated clockwise about its geometric center for the depth map
If it is
The depth map DS2 is rotated counterclockwise about its geometric center
A depth map DS3 is obtained.
f. A rectangular coordinate system uov is established on the depth map DS3, and the horizontal rightward direction is a positive u-axis direction, and the vertical downward direction is a positive v-axis direction.
g. Finding all pixel points belonging to the rectangular box body in the depth map DS3 in a traversal mode, and acquiring the minimum value u on the u axis in the pixel pointsminMaximum value u on the u-axismaxMinimum value v on the v-axisminAnd maximum value v on the v-axismax。
h. Is provided with4 end points on the end surface of the rectangular box body are respectively points Pa(umin,vmin) Point Pb(umax,vmin) Point Pc(umin,vmax) And point Pd(umax,vmax) According to the coordinate values and the depth values of the 4 end points in the depth map DS3, the corresponding space point P in the three-dimensional space is calculated through the internal reference of the depth camera1(x1,y1,z1) A space point P2(x2,y2,z2) A space point P3(x3,y3,z3) And a spatial point P4(x4,y4,z4)。
i. According to the 4 space points, the length three-dimensional dimension D of the rectangular box body is calculatedLWidth three-dimensional dimension D of rectangular boxSHeight three-dimensional dimension D of rectangular box bodyH。
Compared with the prior art, the method and the device have the advantages that the depth map information acquired by the depth camera of the depth camera and the internal parameters of the camera are utilized, the three-dimensional size information of the rectangular box body can be acquired quickly and efficiently, the measurement precision is high, the application range is wide, and the universality is high.
Further, in the step g, a minimum detection height a of the rectangular box is set, the minimum detection height a is smaller than the box height H, and all pixel points with depth values smaller than (H-a) are found in a mode of traversing all pixel points in the depth map DS3, so that all pixel points of the rectangular box are obtained in the depth map DS 3.
Further, the preprocessing of the depth map DS0 includes performing a median filtering operation on the depth map DS0 to obtain a depth map DS1, and performing a flood filling operation on the depth map DS1 to obtain a depth map DS 2.
Further, the gray scale processing comprises passing
The depth map DS2 is converted into a gray map GS1, where src (x, y) is the pixel value of the depth map DS2, dst (x, y) is the pixel value of the gray map GS1, and the pixel value in the depth map DS2 is the maximumValue maxsrcThe minimum value of the pixel values in the depth map DS2 is minsrc。
Further, the step c further comprises: performing a gaussian filtering operation on the gray map GS1 to obtain a gray map GS2, performing a bilateral filtering operation on the gray map GS2 to obtain a gray map GS3, and further performing an edge extraction operation on the gray map GS3 to obtain a gray map GS 4.
Further, the calculating step in the step i is as follows: computing a spatial point P1And the spatial point P2Distance D of12Calculating a spatial point P3And the spatial point P4Distance D of34Calculating a spatial point P1And the spatial point P3Distance D of13Calculating a spatial point P2And the spatial point P4Distance D of24Calculating the distance D12And a distance D34Has a mean value of DLCalculating the distance D13And a distance D24Has a mean value of DSCalculating z1、z2、z3And z4Has a mean value of zhCalculating DH＝H-zhThe three-dimensional size of the length of the rectangular box body is DLThe width three-dimensional dimension of the rectangular box body is DSThe three-dimensional height dimension of the rectangular box body is DH。
Another object of the present invention is to provide a storage medium to which the method for measuring three-dimensional dimensions of a rectangular box based on depth images is applied, and a computer readable storage medium having stored thereon a data processing program, which when executed by a processor, implements all the steps of the method for measuring three-dimensional dimensions of a rectangular box based on depth images.
Drawings
FIG. 1 is a schematic diagram of a three-dimensional measurement method according to the present invention
FIG. 2 is a schematic diagram of a three-dimensional dimension measuring method according to the present invention
FIG. 3 is a schematic diagram of a rectangular box placed in the effective shooting area of a depth camera
Detailed Description
The technical scheme of the invention is described in the following with the accompanying drawings:
the first embodiment is as follows:
referring to fig. 1 to 3, the method for measuring the three-dimensional size of a rectangular box based on a depth image of the invention comprises the following steps:
a. the depth image DS0 of the rectangular box placed in the effective shooting area 10 is obtained by a depth camera, the distance between the depth camera and the shooting plane is H, in the shooting process, the depth camera needs to obtain the end image of the rectangular box placed on the shooting plane, specifically, in the shot image, the four line sides of the end face of the rectangular box closest to the depth camera are rectangular, the shooting direction of the depth camera is perpendicular to the corresponding end face of the rectangular box, the rectangular box placed on the shooting plane is specifically to make one end face of the rectangular box fit with the shooting plane, in this embodiment, the shooting plane is a horizontal plane or a ground, the depth camera is horizontally hung at a certain height H and the shooting direction is set to be vertically downward, the height H is larger than the height H of the rectangular box, and then the rectangular box is completely placed in the shooting area of the depth camera, the depth camera shoots and obtains a depth map DS0 of the rectangular box in a top view state, specifically, the depth map DS0 completely comprises the whole rectangular box, and preferably, four sides of the rectangular box in the top view are parallel to a frame of the depth map DS0 as much as possible.
b. The method comprises the steps of preprocessing a depth map DS0 to obtain a depth map DS2, carrying out gray level processing on the depth map DS2 to obtain a gray level map GS1, carrying out edge extraction operation to obtain a gray level map GS4, carrying out binarization processing to obtain a gray level map GS5, and enabling an obtained image to only contain a line-edge contour of a rectangular box body through gray level processing and edge extraction operation, so that the three-dimensional size of the rectangular box body can be further obtained.
c. Obtaining n straight lines L from the gray-scale image GS5 by using hough transformation straight line detection algorithm1(ρ1,θ1)，L2(ρ2,θ2)，L3(ρ3,θ3)，……，Ln(ρn,θn) The formed straight line set L ═ { L ═ L1,L2,L3,......,LnN is more than or equal to 4, and the progressive size (unit radius) in the linear searchThe size, the size of the progress size (unit angle) during the straight line search and the threshold size of the accumulation plane can be selected according to the actual situation, the image is composed of a plurality of pixels, the position of the gray-scale image GS5 at the edge line is also composed of a plurality of pixels with the same (or similar) color, the detected straight line is a straight line formed by connecting a plurality of pixels with the same (or similar) color, and the straight line which has little deviation with the edge size of the rectangular box body can be searched by setting a specific screening length during the actual operation.
d. Creating a set of rectangular box tilt angles PASetting polar angle threshold epsilon and connecting the straight line L1(ρ1,θ1) Polar angle theta of1Set of angles of inclination P of box falling into rectangular bodyAIn the straight line set L ═ { L ═ L2,L3,L4,......,LnThe polar angle θ of each straight line of2、θ3、……、θnTo find theta1All straight lines with the absolute value of the angle difference smaller than the polar angle threshold epsilon are classified into the rectangular box inclination angle set PASo that all the straight lines contained in one edge line of the rectangular box are put into the set PASet P ofAIs smaller than epsilon, preferably (0 deg., 2 deg. °)]。
e. Calculating a set P of the inclination angles of the rectangular box bodyAMean of all polar angles
If it is
The DS2 is rotated clockwise about its geometric center for the depth map
If it is
The depth map DS2 is rotated counterclockwise about its geometric center
The depth map DS3 is obtained, so that four edges of the rectangular box body in the overlooking mode are guaranteed to be parallel to the frame of the depth map DS0 as much as possible, and the position of the endpoint of the rectangular box body can be conveniently detected through a coordinate system.
f. A rectangular coordinate system uov is established on the depth map DS3, the origin o of the coordinate system is the position of the upper left corner on the depth map DS3, the horizontal right direction is the positive u-axis direction, and the vertical downward direction is the positive v-axis direction.
g. Setting the minimum detection height A of the rectangular box body, wherein the minimum detection height A is smaller than the box body height H, finding all pixel points which belong to the rectangular box body and have depth values smaller than (H-A) in a mode of traversing all pixel points in the depth map DS3, and obtaining the minimum value u on the u axis among the pixel pointsminMaximum value u on the u-axismaxMinimum value v on the v-axisminMaximum value v on the v-axismaxAnd the end point of the bottom of the rectangular box body detected by the shooting error is well eliminated by setting the condition of the pixel point with the detection depth value smaller than (H-A), so that the influence on the accuracy of obtaining the size of the rectangular box body is avoided.
h. 4 end points on the rectangular box body top view are respectively set as points Pa(umin,vmin) Point Pb(umax,vmin) Point Pc(umin,vmax) And point Pd(umax,vmax) The coordinate values and depth values in the depth map DS3 for these 4 end points and through the internal reference of the depth camera (c)x、cy、fxAnd fy) Calculating a corresponding spatial point P in three-dimensional space1(x1,y1,z1) A space point P2(x2,y2,z2) A space point P3(x3,y3,z3) And a spatial point P4(x4,y4,z4)。
i. Computing a spatial point P1And the spatial point P2Distance D of12Calculating a spatial point P3And the spatial point P4Distance D of34Calculating a spatial point P1And the spatial point P3Distance D of13Calculating a spatial point P2And the spatial point P4Euclidean distance of D24Calculating the distance D12And a distance D34Has a mean value of DLCalculating the distance D13And a distance D24Has a mean value of DSCalculating z1、z2、z3And z4Has a mean value of zhCalculating DH＝H-zhThe three-dimensional size of the length of the rectangular box body is DLThe width three-dimensional dimension of the rectangular box body is DSThe three-dimensional height dimension of the rectangular box body is DH。
Wherein the internal reference comprises an image center cxAnd cyAnd normalized focal length f in the X and Y axesxAnd fy
Compared with the prior art, the method and the device have the advantages that the depth map information acquired by the depth camera of the depth camera and the internal parameters of the camera are utilized, the three-dimensional size information of the rectangular box body can be acquired quickly and efficiently, the measurement precision is high, the application range is wide, and the universality is high.
Further, the preprocessing of the depth map DS0 includes performing a median filtering operation on the depth map DS0 to obtain a depth map DS1, where the size of the filtering template may be selected according to a specific practical situation, and performing a flood filling operation on the depth map DS1 to obtain a depth map DS 2; by preprocessing the depth map DS0 in advance, the subsequent gray processing of the depth map is facilitated.
Further, the gray scale processing comprises passing
The depth map DS2 is converted into a gray map GS1, where src (x, y) is the pixel value of the depth map DS2, dst (x, y) is the pixel value of the gray map GS1, and the maximum value of the pixel values in the depth map DS2 is maxsrcThe minimum value of the pixel values in the depth map DS2 is minsrc。
Further, the step c further comprises: performing Gaussian filtering operation on the gray-scale image GS1 to obtain a gray-scale image GS2, wherein the size and the variance of a filtering template can be selected according to specific actual conditions, performing bilateral filtering operation on the gray-scale image GS2 to obtain a gray-scale image GS3, wherein the size of a filtering kernel radius, the size of a sigmas space and the size of a similarity factor sigmar can be selected according to specific actual conditions, further performing edge extraction operation on the gray-scale image GS3 to obtain a gray-scale image GS4, wherein the size of a small threshold, the size of a large threshold and the size of a Sobel operator can be selected according to specific actual conditions, and finally performing binarization processing on the gray-scale image GS4 to obtain the gray-scale image GS 5.
Wherein by passing
And (3) performing binarization processing on the gray-scale map GS4 to obtain a gray-scale map GS5, wherein src (x, y) is a channel value of the gray-scale map GS4 before the binarization processing is performed, dst (x, y) is a channel value of the gray-scale map GS5 after the binarization processing is performed, and the threshold value thresh can be selected according to specific practical situations.
Example two:
an object of this embodiment is to provide a storage medium to which the first embodiment is applied, and a computer readable storage medium having stored thereon a data processing program, which when executed by a processor, implements all the steps of the method for measuring a three-dimensional size of a rectangular box based on a depth image according to the first embodiment.
Variations and modifications to the above-described embodiments may occur to those skilled in the art, which fall within the scope and spirit of the above description. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and some modifications and variations of the present invention should fall within the scope of the claims of the present invention. Furthermore, although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.
Claims (7)
1. The method for measuring the three-dimensional size of the rectangular box based on the depth image is characterized by comprising the following steps of: the method comprises the following steps:
a. acquiring a depth map DS0 of the rectangular box body placed in the effective shooting area through a depth camera, wherein the distance between the depth camera and a shooting plane is H;
b. preprocessing the depth map DS0 to obtain a depth map DS2, carrying out gray processing on the depth map DS2 to obtain a gray map GS1, carrying out edge extraction operation to obtain a gray map GS4, and carrying out binarization processing to obtain a gray map GS 5;
c. obtaining a straight line set L consisting of n straight lines by utilizing a hough transformation straight line detection algorithm on the gray-scale image GS5, wherein n is more than or equal to 4;
d. creating a set of rectangular box tilt angles PASetting a polar angle threshold epsilon, and classifying the polar angle theta of any straight line in the straight line set L into a rectangular box inclination angle set PAComparing the angle difference between the polar angle of the rest of straight lines in the straight line set L and the polar angle theta of the arbitrary straight line, if the absolute value of the angle difference between the polar angles of the rest of straight lines and the arbitrary straight line is less than the polar angle threshold epsilon, then the polar angle of the straight line is classified into the rectangular box inclination angle set PAPerforming the following steps;
e. calculating a set P of the inclination angles of the rectangular box bodyAMean of all polar angles
If it is
The DS2 is rotated clockwise about its geometric center for the depth map
If it is
The depth map DS2 is rotated counterclockwise about its geometric center
Obtaining a depth map DS 3;
f. a rectangular coordinate system uov is established on the depth map DS3, the horizontal rightward direction is the positive direction of the u axis, and the vertical downward direction is the positive direction of the v axis;
g. all the images belonging to the rectangular box are found in the depth map DS3 in a traversal modePixel points are obtained, and the minimum value u on the u axis in the pixel points is obtainedminMaximum value u on the u-axismaxMinimum value v on the v-axisminAnd maximum value v on the v-axismax；
h. Setting 4 end points on the end surface of the rectangular box body as points P respectivelya(umin,vmin) Point Pb(umax,vmin) Point Pc(umin,vmax) And point Pd(umax,vmax) According to the coordinate values and the depth values of the 4 end points in the depth map DS3, the corresponding space point P in the three-dimensional space is calculated through the internal reference of the depth camera1(x1,y1,z1) A space point P2(x2,y2,z2) A space point P3(x3,y3,z3) And a spatial point P4(x4,y4,z4)；
i. According to the 4 space points, the length three-dimensional dimension D of the rectangular box body is calculatedLWidth three-dimensional dimension D of rectangular boxSHeight three-dimensional dimension D of rectangular box bodyH。
2. The method for measuring the three-dimensional size of the rectangular box based on the depth image as claimed in claim 1, wherein: in the step g, the minimum detection height A of the rectangular box body is set firstly, the minimum detection height A is smaller than the box body height H, all pixel points with depth values smaller than (H-A) are found in a mode of traversing all pixel points in the depth map DS3, and therefore all pixel points of the rectangular box body are obtained in the depth map DS 3.
3. The method for measuring the three-dimensional size of the rectangular box based on the depth image as claimed in claim 1, wherein: the preprocessing of the depth map DS0 comprises the steps of performing median filtering operation on the depth map DS0 to obtain a depth map DS1, and performing flood filling operation on the depth map DS1 to obtain a depth map DS 2.
4. The base of claim 1The method for measuring the three-dimensional size of the rectangular box body in the depth image is characterized by comprising the following steps of: the gray scale processing comprises passing
The depth map DS2 is converted into a gray map GS1, where src (x, y) is the pixel value of the depth map DS2, dst (x, y) is the pixel value of the gray map GS1, and the maximum value of the pixel values in the depth map DS2 is maxsrcThe minimum value of the pixel values in the depth map DS2 is minsrc。
5. The method for measuring the three-dimensional size of the rectangular box based on the depth image as claimed in claim 1 or 4, wherein: the step c further comprises: performing Gaussian filtering operation on the gray map GS1 to obtain a gray map GS2, performing bilateral filtering operation on the gray map GS2 to obtain a gray map GS3, further performing edge extraction operation on the gray map GS3 to obtain a gray map GS4, and finally performing binarization processing on the gray map GS4 to obtain a gray map GS 5.
6. The method for measuring the three-dimensional size of the rectangular box based on the depth image as claimed in claim 1, wherein: the calculation step in the step i is as follows:
computing a spatial point P1And the spatial point P2Distance D of12Calculating a spatial point P3And the spatial point P4Distance D of34Calculating a spatial point P1And the spatial point P3Distance D of13Calculating a spatial point P2And the spatial point P4Distance D of24Calculating the distance D12And a distance D34Has a mean value of DLCalculating the distance D13And a distance D24Has a mean value of DSCalculating z1、z2、z3And z4Has a mean value of zhCalculating DH＝H-zhThe three-dimensional size of the length of the rectangular box body is DLThe width three-dimensional dimension of the rectangular box body is DSThe three-dimensional height dimension of the rectangular box body is DH。
7. A storage medium, characterized in that a computer readable storage medium has stored thereon a data processing program, which when executed by a processor, implements the steps of the depth image based cuboidal box three-dimensional dimension measuring method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910379796.9A CN110136193B (en) | 2019-05-08 | 2019-05-08 | Rectangular box three-dimensional size measuring method based on depth image and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910379796.9A CN110136193B (en) | 2019-05-08 | 2019-05-08 | Rectangular box three-dimensional size measuring method based on depth image and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110136193A CN110136193A (en) | 2019-08-16 |
| CN110136193B true CN110136193B (en) | 2021-06-11 |
Family
ID=67576766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910379796.9A Active CN110136193B (en) | 2019-05-08 | 2019-05-08 | Rectangular box three-dimensional size measuring method based on depth image and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110136193B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112197708B (en) * | 2020-08-31 | 2022-04-22 | 深圳市慧鲤科技有限公司 | Measuring method and device, electronic device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106247951A (en) * | 2016-08-29 | 2016-12-21 | 上海交通大学 | A kind of object measuring method based on depth image |
| CN108335325A (en) * | 2018-01-30 | 2018-07-27 | 上海数迹智能科技有限公司 | A kind of cube method for fast measuring based on depth camera data |
| US10134164B2 (en) * | 2014-08-28 | 2018-11-20 | Sony Corporation | Information processing apparatus, information processing system, information processing method, and program |
| CN109029618A (en) * | 2018-07-11 | 2018-12-18 | 苏州科技大学 | Monocular vision packing case volume measuring method |
| CN109186461A (en) * | 2018-07-27 | 2019-01-11 | 南京阿凡达机器人科技有限公司 | A kind of measurement method and measuring device of cabinet size |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130101158A1 (en) * | 2011-10-21 | 2013-04-25 | Honeywell International Inc. | Determining dimensions associated with an object |
| CN105551052A (en) * | 2016-01-08 | 2016-05-04 | 青岛农业大学 | White board calibration system and calibration method of digital image data |
| CN107067431B (en) * | 2017-01-16 | 2020-07-03 | 河海大学常州校区 | Kinect-based object volume calculation method |
| CN108527940B (en) * | 2018-04-12 | 2020-01-21 | 曹芸畅 | Method for manufacturing packaging box |
| CN108648230A (en) * | 2018-05-14 | 2018-10-12 | 南京阿凡达机器人科技有限公司 | A kind of package dimensions measurement method, system, storage medium and mobile terminal |
-
2019
- 2019-05-08 CN CN201910379796.9A patent/CN110136193B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10134164B2 (en) * | 2014-08-28 | 2018-11-20 | Sony Corporation | Information processing apparatus, information processing system, information processing method, and program |
| CN106247951A (en) * | 2016-08-29 | 2016-12-21 | 上海交通大学 | A kind of object measuring method based on depth image |
| CN108335325A (en) * | 2018-01-30 | 2018-07-27 | 上海数迹智能科技有限公司 | A kind of cube method for fast measuring based on depth camera data |
| CN109029618A (en) * | 2018-07-11 | 2018-12-18 | 苏州科技大学 | Monocular vision packing case volume measuring method |
| CN109186461A (en) * | 2018-07-27 | 2019-01-11 | 南京阿凡达机器人科技有限公司 | A kind of measurement method and measuring device of cabinet size |
Non-Patent Citations (1)
| Title |
|---|
| 基于投影轮廓的纸箱尺寸单目测量;刘昶 等;《沈阳理工大学学报》;20181015;第37卷(第5期);第31-37页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110136193A (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110443836B (en) | Point cloud data automatic registration method and device based on plane features | |
| CN110648367A (en) | Geometric object positioning method based on multilayer depth and color visual information | |
| CN107798326B (en) | Contour vision detection method | |
| CN107452030B (en) | Image registration method based on contour detection and feature matching | |
| CN108597009B (en) | Method for detecting three-dimensional target based on direction angle information | |
| CN112233116B (en) | Concave-convex mark visual detection method based on neighborhood decision and gray level co-occurrence matrix description | |
| CN107977996B (en) | Space target positioning method based on target calibration positioning model | |
| CN107844750A (en) | A kind of water surface panoramic picture target detection recognition methods | |
| CN113344931B (en) | Plug-in visual detection and identification method, readable storage medium and device | |
| CN115100116A (en) | Plate defect detection method based on three-dimensional point cloud | |
| CN115170669A (en) | Identification and positioning method and system based on edge feature point set registration and storage medium | |
| CN109767431A (en) | Accessory appearance defect inspection method, device, equipment and readable storage medium storing program for executing | |
| CN106340010A (en) | Corner detection method based on second-order contour difference | |
| CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
| CN115096206A (en) | Part size high-precision measurement method based on machine vision | |
| CN112489106A (en) | Video-based vehicle size measuring method and device, terminal and storage medium | |
| CN107680035B (en) | Parameter calibration method and device, server and readable storage medium | |
| CN106960184B (en) | Image positioning method for book frame | |
| CN110136193B (en) | Rectangular box three-dimensional size measuring method based on depth image and storage medium | |
| CN113192174B (en) | Picture construction method and device and computer storage medium | |
| CN108053485B (en) | Potato three-dimensional modeling method based on contour image | |
| CN116309882A (en) | Tray detection and positioning method and system for unmanned forklift application | |
| CN113409242A (en) | Intelligent monitoring method for point cloud of rail intersection bow net | |
| CN111243006A (en) | Method for measuring liquid drop contact angle and size based on image processing | |
| CN114187269B (en) | Rapid detection method for surface defect edge of small component |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |