CN110136193A - Cubold cabinet three-dimensional dimension measurement method and storage medium based on depth image - Google Patents
Cubold cabinet three-dimensional dimension measurement method and storage medium based on depth image Download PDFInfo
- Publication number
- CN110136193A CN110136193A CN201910379796.9A CN201910379796A CN110136193A CN 110136193 A CN110136193 A CN 110136193A CN 201910379796 A CN201910379796 A CN 201910379796A CN 110136193 A CN110136193 A CN 110136193A
- Authority
- CN
- China
- Prior art keywords
- cubold
- cabinet
- depth
- depth map
- grayscale image
- 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
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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
Cubold cabinet three-dimensional dimension measurement method and storage medium disclosed by the invention based on depth image, make full use of the internal reference of depth map information acquired in the depth camera of depth camera and camera, realize that the three-dimensional dimension information measurement precision for quickly and efficiently getting cubold cabinet is high, the scope of application is wider, and versatility is high.
Description
Technical field
The invention belongs to computer vision measurement fields, and in particular to the cubold cabinet three-dimensional dimension based on depth image is surveyed
Amount method and storage medium.
Background technique
With the fast development of e-commerce, demand and requirement of the market to logistic storage are continuously increased, and logistic industry
In multiple links be required to obtain operation object the information such as its effective three-dimensional dimension, but at present in industry it is most of all
It is to realize to obtain by traditional manual type, there are heavy workload, action is cumbersome, human cost is high, human resources are unrestrained
Take and the outstanding problems such as information acquisition efficiency is low.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of, and the cubold cabinet based on depth image is three-dimensional
Dimension measurement method and storage medium can rapidly and efficiently accurately acquire the three-dimensional dimension information measurement precision of cubold cabinet
Height, the scope of application is wider, and versatility is high.
In order to achieve the above object, the invention adopts the following technical scheme:
Cubold cabinet three-dimensional dimension measurement method based on depth image, it is characterised in that: the following steps are included:
A. the depth map DS0 for the cubold cabinet being placed in effective shooting area, depth camera are obtained by depth camera
With at a distance from camera plane be H.
B. pretreatment is carried out to depth map DS0 and gray proces obtains grayscale image GS1, and carried out edge extraction operation and obtain
Grayscale image GS4, and carry out binary conversion treatment and obtain grayscale image GS5.
C. the straight line set L as composed by n straight line is obtained using hough transformation line detection algorithm to grayscale image GS5,
Wherein n >=4.
D.d. cubold cabinet inclination angle set P is createdA, and polar angle threshold epsilon is set, by straight line set L it is any always
The polar angle θ of line is included into cubold cabinet inclination angle set PAIn, compare the polar angle of remaining straight line and the arbitrary line in straight line set L
Polar angle θ differential seat angle, if the polar angle angle absolute value of the difference of remaining straight line be less than polar angle threshold epsilon, by the polar angle of the straight line
It is included into cubold cabinet inclination angle set PAIn.
E. cubold cabinet inclination angle set P is calculatedAIn all polar angles mean valueIfThen to depth map DS2 around it
Geometric center rotates clockwiseIfThen depth map DS2 is rotated counterclockwise around its geometric centerObtain depth
Scheme DS3.
F. rectangular coordinate system uov is established on depth map DS3, direction is u axis positive direction, vertically downward direction horizontally to the right
For v axis positive direction.
G. all pixels point for belonging to cubold cabinet is found by traversal mode in depth map DS3, and obtains these pixels
Minimum value u in point on u axismin, maximum value u on u axismax, minimum value v on v axisminAnd the maximum on v axis
Value vmax。
H. it is respectively point P that 4 endpoints in cubold casing end face, which are arranged,a(umin,vmin), point Pb(umax,vmin), point Pc(umin,
vmax) and point Pd(umax,vmax), it is taken the photograph according to coordinate value of above-mentioned 4 endpoints in depth map DS3 and depth value and by depth
As the internal reference of head calculates corresponding spatial point P in three dimensions1(x1,y1,z1), spatial point P2(x2,y2,z2), spatial point
P3(x3,y3,z3) and spatial point P4(x4,y4,z4)。
I. according to above-mentioned 4 spatial points, the length three-dimensional dimension D of then cubold cabinet is calculatedL, the width three of cubold cabinet
Tie up dimension DS, the high levels of three-dimensional dimension D of cubold cabinetH。
Compared with prior art, depth map information acquired in the of the invention point of depth camera using depth camera and
The internal reference of camera realizes that the three-dimensional dimension information measurement precision for quickly and efficiently getting cubold cabinet is high, and the scope of application is wider,
Versatility is high.
Further, in step g, the minimum detection height A of cubold cabinet is first set, the minimum detection height A is less than
Box height h, all pixels point finds all depth values less than (H-A) by way of traversing in depth map DS3
Pixel, to obtain all pixels point of rectangular box in depth map DS3.
Further, carrying out pretreatment to depth map DS0 includes carrying out median filtering operation to depth map DS0 to obtain depth
Scheme DS1, unrestrained water padding is carried out to depth map DS1 and obtains depth map DS2.
Further, the gray proces include passing throughDepth map DS2 is turned
It is changed to grayscale image GS1, wherein src (x, y) is the pixel value of depth map DS2, and dst (x, y) is the pixel value of grayscale image GS1, deep
Pixel value maximum value is max in degree figure DS2src, pixel value minimum value is min in depth map DS2src。
Further, the step c further include: gaussian filtering is carried out to grayscale image GS1 and operates to obtain grayscale image GS2, it is right
Grayscale image GS2 carries out bilateral filtering and operates to obtain grayscale image GS3, and then carries out edge extraction operation to grayscale image GS3 and obtain ash
Degree figure GS4.
Further, the calculating step in step i are as follows: calculate spatial point P1With spatial point P2Distance D12, calculate space
Point P3With spatial point P4Distance D34, calculate spatial point P1With spatial point P3Distance D13, calculate spatial point P2With spatial point P4
Distance D24, calculate distance D12With distance D34Mean value be DL, calculate distance D13With distance D24Mean value be DS, calculate z1、z2、
z3And z4Mean value be zh, calculate DH=H-zh, then the length three-dimensional dimension of cubold cabinet is DL, the width three-dimensional ruler of cubold cabinet
Very little is DS, the high levels of three-dimensional of cubold cabinet is having a size of DH。
Another object of the present invention is to provide the cubold cabinet three-dimensional dimension surveys described in a kind of application based on depth image
The storage medium of amount method is stored with data processor on computer readable storage medium, and the data processor is located
Manage all steps that such as cubold cabinet three-dimensional dimension measurement method based on depth image is realized when device executes.
Detailed description of the invention
Fig. 1 is the schematic diagram of three-dimensional dimension measurement method of the present invention
Fig. 2 is the schematic diagram of three-dimensional dimension measurement method of the present invention
Fig. 3 is that cubold cabinet is placed in the schematic diagram in the effective shooting area of depth camera
Specific embodiment
Below in conjunction with Detailed description of the invention technical solution of the present invention:
Embodiment one:
Referring to Fig. 1 to Fig. 3, the cubold cabinet three-dimensional dimension measurement method of the invention based on depth image, including it is following
Step:
A. the depth map DS0 for the cubold cabinet being placed in effective shooting area 10, depth phase are obtained by depth camera
Machine is H at a distance from camera plane, and in shooting process, depth camera will get the end for placing cubold cabinet in camera plane
Face image, specifically, the four line sides of cubold cabinet and depth camera apart from nearest end face are squares in the image of shooting
Shape, can be vertical by depth camera shooting direction end face corresponding with cubold cabinet, places the cubold cabinet in camera plane
It is bonded a wherein end face for cubold cabinet with camera plane, in the present embodiment, the camera plane is horizontal plane
Or ground, depth camera is horizontally suspended in certain altitude H and sets its shooting direction to straight down, height H is greater than square
Cubold cabinet, is then put into the shooting area of the depth camera of depth camera, depth camera by the height h of shape cabinet completely
Shooting obtains the depth map DS0 of the overlooking state of cubold cabinet, specifically, making in depth map DS0 completely comprising entire cubold case
Body, the four edges under preferably overlooking cubold cabinet are parallel with the frame of depth map DS0 as far as possible.
B. pretreatment is carried out to depth map DS0 and gray proces obtains grayscale image GS1, and carried out edge extraction operation and obtain
Grayscale image GS4, and carry out binary conversion treatment and obtain grayscale image GS5, by gray proces and edge extraction operation, make to be obtained
Image only include cubold cabinet line edge profile, convenient for further obtaining the three-dimensional dimension of cubold cabinet.
C. grayscale image GS5 is obtained using hough transformation line detection algorithm by n straight line L1(ρ1,θ1), L2(ρ2,
θ2), L3(ρ3,θ3) ... ..., Ln(ρn,θn) composed by straight line set L={ L1,L2,L3,......,Ln, wherein n >=4, directly
The threshold of progress size (unit angle) size and cumulative plane when size (unit radius) size, linear search of improving when line search
Value size can be selected according to specific actual conditions, and since image is made of multiple pixels, grayscale image GS5 is located at edge line
Position also be made of the pixel of multiple identical (or approximate) colors, the detected straight line of institute for by multiple same colors (or
It is approximate) the straight line that is linked to be of pixel, when practical operation can by be arranged specific screening length search for cubold cabinet edge
The little straight line of dimensional discrepancy.
D. cubold cabinet inclination angle set P is createdA, and polar angle threshold epsilon is set, by straight line L1(ρ1,θ1) polar angle θ1It is included into
Cubold cabinet inclination angle set PAIn, in straight line set L={ L2,L3,L4,......,LnEach straight line polar angle θ2、
θ3、……、θnIn find and θ1All straight lines that angle absolute value of the difference is less than polar angle threshold epsilon are included into cubold cabinet and incline
Oblique angle set PAIn, so that all straight lines for including in an edge line of cubold cabinet be made to be put into set PA, set PAIn it is straight
The relative deviation angle of line be less than ε, the ε be preferably (0 °, 2 °].
E. cubold cabinet inclination angle set P is calculatedAIn all polar angles mean valueIfThen to depth map DS2 around it
Geometric center rotates clockwiseIfThen depth map DS2 is rotated counterclockwise around its geometric centerObtain depth
Scheme DS3, to ensure that the four edges under overlooking cubold cabinet are parallel with the frame of depth map DS0 as far as possible, also facilitates subsequent
The position of cubold cabinet endpoint is detected by coordinate system.
F. rectangular coordinate system uov is established on depth map DS3, coordinate origin o is upper left position on depth map DS3,
Direction is u axis positive direction horizontally to the right, and vertically downward direction is v axis positive direction.
G. the minimum detection height A of cubold cabinet is set, minimum detection height A is less than box height h, by depth map
The mode that all pixels point is traversed in DS3 finds all pixels for belonging to rectangular box that all depth values are less than (H-A)
Point, and obtain the minimum value u in these pixels on u axismin, maximum value u on u axismax, minimum value on v axis
vmin, maximum value v on v axismax, by the condition of pixel of the setting detection depth value less than (H-A), preferably eliminate
Due to the endpoint of the error-detecting cubold bottom of box of shooting, the precision for influencing to obtain cubold box sizes is avoided.
H. it is respectively point P that 4 endpoints on cubold cabinet top view, which are arranged,a(umin,vmin), point Pb(umax,vmin), point Pc
(umin,vmax) and point Pd(umax,vmax), for coordinate value and depth value of this 4 endpoints in depth map DS3 and pass through depth
Internal reference (the c of camerax、cy、fxAnd fy) calculate corresponding spatial point P in three dimensions1(x1,y1,z1), spatial point P2
(x2,y2,z2), spatial point P3(x3,y3,z3) and spatial point P4(x4,y4,z4)。
I. spatial point P is calculated1With spatial point P2Distance D12, calculate spatial point P3With spatial point P4Distance D34, calculate empty
Between point P1With spatial point P3Distance D13, calculate spatial point P2With spatial point P4Euclidean distance D24, calculate distance D12With distance
D34Mean value be DL, calculate distance D13With distance D24Mean value be DS, calculate z1、z2、z3And z4Mean value be zh, calculate DH=
H-zh, then the length three-dimensional dimension of cubold cabinet is DL, the width three-dimensional dimension of cubold cabinet is DS, the height three of cubold cabinet
Dimension is having a size of DH。
Wherein, the internal reference includes picture centre cxAnd cyAnd the normalization focal length f in X-axis and Y-axisxAnd fy
Compared with prior art, depth map information acquired in the of the invention point of depth camera using depth camera and
The internal reference of camera realizes that the three-dimensional dimension information measurement precision for quickly and efficiently getting cubold cabinet is high, and the scope of application is wider,
Versatility is high.
Further, carrying out pretreatment to depth map DS0 includes carrying out median filtering operation to depth map DS0 to obtain depth
Scheme DS1, wherein the size of Filtering Template can be selected according to specific actual conditions, carried out unrestrained water to depth map DS1 and filled out
It fills operation and obtains depth map DS2；By being pre-processed in advance to depth map DS0, depth map is carried out at gray scale convenient for subsequent
Reason.
Further, the gray proces include passing throughDepth map DS2 is turned
It is changed to grayscale image GS1, wherein src (x, y) is the pixel value of depth map DS2, and dst (x, y) is the pixel value of grayscale image GS1, deep
Pixel value maximum value is max in degree figure DS2src, pixel value minimum value is min in depth map DS2src。
Further, the step c further include: gaussian filtering is carried out to grayscale image GS1 and operates to obtain grayscale image GS2,
The size and variance size of middle Filtering Template can be selected according to specific actual conditions, be carried out to grayscale image GS2 bilateral
Filtering operation obtains grayscale image GS3, and wherein filtering core radius size, sigmas space size and similar factors sigmar size can
It is selected according to specific actual conditions, and then edge extraction operation is carried out to grayscale image GS3 and obtains grayscale image GS4, it is medium and small
Threshold size, big threshold size and Sobel operator size can be selected according to specific actual conditions, finally to grayscale image GS4
It carries out binary conversion treatment and obtains grayscale image GS5.
Wherein pass throughBinary conversion treatment is carried out to grayscale image GS4 to obtain
Grayscale image GS5, wherein src (x, y) is the channel value of grayscale image GS4 before carrying out binary conversion treatment, and dst (x, y) is to carry out two-value
The channel value of grayscale image GS5, threshold value thresh can be selected according to specific actual conditions after change processing.
Embodiment two:
The purpose of the present embodiment is that a kind of storage medium of Application Example one is provided, on computer readable storage medium
It is stored with data processor, is realized when the data processor is executed by processor if embodiment one is based on depth image
Cubold cabinet three-dimensional dimension measurement method all steps.
According to the disclosure and teachings of the above specification, those skilled in the art in the invention can also be to above-mentioned embodiment party
Formula is changed and is modified.Therefore, the invention is not limited to the specific embodiments disclosed and described above, to of the invention
Some modifications and changes should also be as falling into the scope of the claims of the present invention.In addition, although being used in this specification
Some specific terms, these terms are merely for convenience of description, does not limit the present invention in any way.
Claims (7)
1. the cubold cabinet three-dimensional dimension measurement method based on depth image, it is characterised in that: the following steps are included:
A. the depth map DS0 for the cubold cabinet being placed in effective shooting area, depth camera and bat are obtained by depth camera
The distance for taking the photograph plane is H；
B. pretreatment is carried out to depth map DS0 and gray proces obtains grayscale image GS1, and carried out edge extraction operation and obtain gray scale
Scheme GS4, and carries out binary conversion treatment and obtain grayscale image GS5；
C. the straight line set L as composed by n straight line is obtained using hough transformation line detection algorithm to grayscale image GS5, wherein
n≥4；
D. cubold cabinet inclination angle set P is createdA, and polar angle threshold epsilon is set, by the polar angle of any one straight line in straight line set L
θ is included into cubold cabinet inclination angle set PAIn, compare the polar angle θ of the polar angle of remaining straight line and the arbitrary line in straight line set L
Differential seat angle, if the polar angle angle absolute value of the difference of remaining straight line be less than polar angle threshold epsilon, the polar angle of the straight line is included into square
Body cabinet inclination angle set PAIn；
E. cubold cabinet inclination angle set P is calculatedAIn all polar angles mean valueIfThen to depth map DS2 around its geometry
Center rotates clockwiseIfThen depth map DS2 is rotated counterclockwise around its geometric centerObtain depth map DS3；
F. rectangular coordinate system uov is established on depth map DS3, direction is u axis positive direction, vertically downward direction v horizontally to the right
Axis positive direction；
G. all pixels point for belonging to cubold cabinet is found by traversal mode in depth map DS3, and is obtained in these pixels
Minimum value u on u axismin, maximum value u on u axismax, minimum value v on v axisminAnd the maximum value on v axis
vmax；
H. it is respectively point P that 4 endpoints in cubold casing end face, which are arranged,a(umin,vmin), point Pb(umax,vmin), point Pc(umin,vmax)
And point Pd(umax,vmax), according to coordinate value of above-mentioned 4 endpoints in depth map DS3 and depth value and pass through depth camera
Internal reference calculate corresponding spatial point P in three dimensions1(x1,y1,z1), spatial point P2(x2,y2,z2), spatial point P3(x3,
y3,z3) and spatial point P4(x4,y4,z4)；
I. according to above-mentioned 4 spatial points, the length three-dimensional dimension D of then cubold cabinet is calculatedL, the width three-dimensional ruler of cubold cabinet
Very little DS, the high levels of three-dimensional dimension D of cubold cabinetH。
2. the cubold cabinet three-dimensional dimension measurement method according to claim 1 based on depth image, it is characterised in that: step
In rapid g, the minimum detection height A of cubold cabinet is first set, the minimum detection height A is less than box height h, by depth
The mode that all pixels point is traversed in figure DS3 finds the pixel that all depth values are less than (H-A), thus in depth map
The all pixels point of DS3 acquisition rectangular box.
3. the cubold cabinet three-dimensional dimension measurement method according to claim 1 based on depth image, it is characterised in that: right
Depth map DS0 carry out pretreatment include to depth map DS0 carry out median filtering operation obtain depth map DS1, to depth map DS1 into
The unrestrained water padding of row obtains depth map DS2.
4. the cubold cabinet three-dimensional dimension measurement method according to claim 1 based on depth image, it is characterised in that: institute
Stating gray proces includes passing throughGrayscale image GS1 is converted to depth map DS2, wherein
Src (x, y) is the pixel value of depth map DS2, and dst (x, y) is the pixel value of grayscale image GS1, and pixel value is maximum in depth map DS2
Value is maxsrc, pixel value minimum value is min in depth map DS2src。
5. the cubold cabinet three-dimensional dimension measurement method according to claim 1 or 4 based on depth image, feature exist
In: the step c further include: gaussian filtering is carried out to grayscale image GS1 and operates to obtain grayscale image GS2, grayscale image GS2 is carried out double
Side filtering operation obtains grayscale image GS3, and then carries out edge extraction operation to grayscale image GS3 and obtain grayscale image GS4, finally to ash
Degree figure GS4 carries out binary conversion treatment and obtains grayscale image GS5.
6. the cubold cabinet three-dimensional dimension measurement method according to claim 1 based on depth image, it is characterised in that: step
Calculating step in rapid i are as follows:
Calculate spatial point P1With spatial point P2Distance D12, calculate spatial point P3With spatial point P4Distance D34, calculate spatial point P1
With spatial point P3Distance D13, calculate spatial point P2With spatial point P4Distance D24, calculate distance D12With distance D34Mean value be
DL, calculate distance D13With distance D24Mean value be DS, calculate z1、z2、z3And z4Mean value be zh, calculate DH=H-zh, then cubold
The length three-dimensional dimension of cabinet is DL, the width three-dimensional dimension of cubold cabinet is DS, the high levels of three-dimensional of cubold cabinet is having a size of DH。
7. a kind of storage medium, which is characterized in that be stored with data processor, the data on computer readable storage medium
The cubold cabinet based on depth image as described in any one of claims 1 to 5 is realized when processing routine is executed by processor
The step of three-dimensional dimension measurement method.
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 true CN110136193A (en) | 2019-08-16 |
| CN110136193B 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) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112197708A (en) * | 2020-08-31 | 2021-01-08 | 深圳市慧鲤科技有限公司 | Measuring method and device, electronic device and storage medium |
| CN114882343A (en) * | 2022-05-30 | 2022-08-09 | 深圳市优必选科技股份有限公司 | Slope detection method, robot and storage medium |
Citations (10)
| 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 |
| CN106247951A (en) * | 2016-08-29 | 2016-12-21 | 上海交通大学 | A kind of object measuring method based on depth image |
| CN107067431A (en) * | 2017-01-16 | 2017-08-18 | 河海大学常州校区 | A kind of object volume computational methods based on Kinect |
| 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 |
| CN108527940A (en) * | 2018-04-12 | 2018-09-14 | 曹芸畅 | A kind of manufacturing method of packing 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 |
| 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 |
-
2019
- 2019-05-08 CN CN201910379796.9A patent/CN110136193B/en active Active
Patent Citations (10)
| 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 |
| US10134164B2 (en) * | 2014-08-28 | 2018-11-20 | Sony Corporation | Information processing apparatus, information processing system, information processing method, and program |
| 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 |
| CN106247951A (en) * | 2016-08-29 | 2016-12-21 | 上海交通大学 | A kind of object measuring method based on depth image |
| CN107067431A (en) * | 2017-01-16 | 2017-08-18 | 河海大学常州校区 | A kind of object volume computational methods based on Kinect |
| 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 |
| CN108527940A (en) * | 2018-04-12 | 2018-09-14 | 曹芸畅 | A kind of manufacturing method of packing 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 |
| 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 |
|---|
| 刘昶 等: "基于投影轮廓的纸箱尺寸单目测量", 《沈阳理工大学学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112197708A (en) * | 2020-08-31 | 2021-01-08 | 深圳市慧鲤科技有限公司 | Measuring method and device, electronic device and storage medium |
| CN114882343A (en) * | 2022-05-30 | 2022-08-09 | 深圳市优必选科技股份有限公司 | Slope detection method, robot and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110136193B (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110443836B (en) | A method and device for automatic registration of point cloud data based on plane features | |
| CN104484648B (en) | Robot variable viewing angle obstacle detection method based on contour recognition | |
| CN107424143B (en) | Mining belt conveyor coal quantity detection method based on binocular stereoscopic vision depth perception | |
| CN111223133B (en) | Registration method of heterogeneous images | |
| CN103744086B (en) | A kind of high registration accuracy method of ground laser radar and close-range photogrammetry data | |
| CN113177977A (en) | Non-contact three-dimensional human body size measuring method | |
| CN108597009B (en) | Method for detecting three-dimensional target based on direction angle information | |
| CN102708370B (en) | Method and device for extracting multi-view angle image foreground target | |
| CN106683173A (en) | A Method of Improving the Density of 3D Reconstruction Point Cloud Based on Neighborhood Block Matching | |
| CN105913489A (en) | Indoor three-dimensional scene reconstruction method employing plane characteristics | |
| CN110672020A (en) | A method for measuring the height of standing trees based on monocular vision | |
| CN107767456A (en) | A kind of object dimensional method for reconstructing based on RGB D cameras | |
| CN103106688A (en) | Indoor three-dimensional scene rebuilding method based on double-layer rectification method | |
| CN103226814A (en) | Medicine bottle foreign matter detection method based on medical visual detection robot image correction | |
| CN115375842A (en) | Plant three-dimensional reconstruction method, terminal and storage medium | |
| CN106504277A (en) | A kind of improved ICP points cloud autoegistration method | |
| CN109859137B (en) | Wide-angle camera irregular distortion global correction method | |
| CN104268880A (en) | Depth information obtaining method based on combination of features and region matching | |
| CN103116892A (en) | Linear solving of video camera internal parameters by utilizing two intersected same circles and common tangent | |
| CN114372992A (en) | Edge corner point detection four-eye vision algorithm based on moving platform | |
| CN110136193A (en) | Cubold cabinet three-dimensional dimension measurement method and storage medium based on depth image | |
| CN111126418A (en) | An Oblique Image Matching Method Based on Plane Perspective Projection | |
| CN106384363A (en) | Fast adaptive weight stereo matching algorithm | |
| CN116883590A (en) | Three-dimensional face point cloud optimization method, medium and system | |
| CN108053485B (en) | Potato three-dimensional modeling method based on contour image |
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 |