CN103307979B - Based on the fruit volume measuring method of computer vision - Google Patents
Based on the fruit volume measuring method of computer vision Download PDFInfo
- Publication number
- CN103307979B CN103307979B CN201310198684.6A CN201310198684A CN103307979B CN 103307979 B CN103307979 B CN 103307979B CN 201310198684 A CN201310198684 A CN 201310198684A CN 103307979 B CN103307979 B CN 103307979B
- Authority
- CN
- China
- Prior art keywords
- point
- edge
- fruit
- ordinate
- front elevation
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of fruit volume measuring method based on computer vision, pre-service, edge extracting and adjustment is carried out by the fruit three-view diagram taken ccd video camera, carry out cutting according to front elevation edge contour and side view edge contour respectively from the cubical front created and side and obtain rectangle section collection, the relation utilizing rectangle to cut into slices between the minimum ordinate of collection point obtains minification; Utilize two interpolation algorithm to reduce by minification vertical view edge to obtain reducing edge, edge will be reduced again and obtain fruit slice sequence chart according to region-growing method, the stereoscopic three-dimensional scatter diagram that three-dimensional reconstruction obtains fruit is carried out to this sequence chart, adds up the number of pixels of this stereoscopic three-dimensional scatter diagram; The actual volume of this number of pixels of matching and fruit obtains mathematical model between the two, can calculate the volume of other fruit similar by this mathematical model.Present invention achieves the effective measurement to fruit volume, simple to operate and measuring accuracy is higher.
Description
Technical field
The present invention relates to a kind of fruit volume measuring method based on computer vision, mainly measure fruit volume from the three-view diagram of fruit, belong to image procossing, pattern-recognition and computer vision field.
Background technology
Volume has very important effect in a lot of fields as an important index, and in fruit grading, volume occupies very large proportion.There is limitation in the information that two dimensional image provides, therefore three-dimensional reconstruction visualization technique is developed rapidly.Existing volume measuring method, formula for regular object standard can ask its volume, irregularly shaped object is then had to the methods such as drainage, ultrasound volume, Laser Measuring volume and CT faultage image 3-d recovery, some time and effort consuming of these methods, some cost intensive inconvenience is promoted; Volume method of asking for based on computer vision has sub-elliptical algorithm, the reconstructed volume area method according to the superficial makings depth, the neural network volumetric estimate etc. based on contour feature, sub-elliptical algorithm and the volume accuracy obtained based on the neural network volumetric estimate method of contour feature not high, harsh according to the requirement of the reconstructed volume rule of superficial makings depth environment to external world.
Summary of the invention
In view of this, the object of the invention is to provide a kind of fruit volume measuring method based on computer vision, and realize the measurement to general fruit volume, cost is low and measuring accuracy is higher.
Technical scheme of the present invention is: based on the fruit volume measuring method of computer vision, it is characterized in that, first cut according to the front elevation edge contour of fruit and side view edge contour respectively from the cubical front created and side, obtain common factor part and be rectangle section collection; Deduct the minimum ordinate value in minimum rectangle slicing profile point with the minimum ordinate value in maximum rectangle slicing profile point, then using the absolute value of this difference as minification radix; Deduct the minimum ordinate value in minimum rectangle slicing profile point with the minimum ordinate value in every one deck rectangle slicing profile point, then using the absolute value of this difference divided by minification radix as minification; The two vertical view edge of interpolation algorithm to fruit is utilized to reduce by aforementioned minification, region-growing method is utilized to obtain the Slice Sequence figure of fruit by reducing edge, the stereoscopic three-dimensional scatter diagram of fruit is obtained by this sequence chart three-dimensional reconstruction, add up the number of pixels of this stereoscopic three-dimensional scatter diagram, this number of pixels of matching and fruit actual volume obtain mathematical model between the two, number of pixels are inputted the volume that this mathematical model can obtain fruit.
The present invention proposes a kind of fruit volume measuring method based on computer vision, it is characterized in that, the step that the method comprises is:
Step 101: obtain the front elevation of fruit, side view and vertical view by ccd video camera, adjust this three-view diagram and make every width figure be all 100
100 pixels; Read in front elevation, ask for front elevation edge; Find the coordinate of easternmost, westernmost, northernmost and southernmost 4 bearing points in front elevation edge contour point;
Step 102: read in side view, asks for side view edge, finds the coordinate of easternmost, westernmost, northernmost and southernmost 4 bearing points in side view edge contour point; With front elevation edge for standard, the position at adjustment side view edge, makes the horizontal ordinate of the bearing point northernmost in the horizontal ordinate of the bearing point northernmost in its edge contour point and front elevation edge contour point align;
Step 103: read in vertical view, asks for vertical view edge; With 4, the side view edge bearing point coordinate after 4, front elevation edge bearing point coordinate and adjustment for reference, the position at adjustment vertical view edge, makes the horizontal ordinate of the bearing point northernmost in its edge contour point aim at the ordinate of the bearing point easternmost in side view edge contour point; Adjustment vertical view edge makes the ordinate of the bearing point westernmost in the ordinate of the bearing point westernmost in its edge contour point and front elevation edge contour point align; Find the coordinate of easternmost, westernmost, northernmost and southernmost 4 bearing points in the rear vertical view edge contour point of adjustment, utilize the coordinate of these 4 bearing points to find the central point at vertical view edge;
Step 104: create
square null matrix
; Front elevation edge is corresponding
front, side view edge is corresponding
side, vertical view edge is corresponding
above;
Step 105_1: with the ordinate of the bearing point westernmost in side view edge contour point
for starting point, the ordinate of bearing point easternmost
for terminal, front elevation matrix of edge is replicated in
?
layer
,
, traveled through all
value;
Step 105_2: with the ordinate of the bearing point easternmost in front elevation edge contour point
for starting point, the ordinate of bearing point westernmost
for terminal; Will
,
be assigned to after transposition
square null matrix
; Will
carry out superposing after aiming at side view edge center point and find the coordinate of the edge contour point of both common factor parts
, t is that edge contour is counted; By above-mentioned
?
layer
reset, then will
assignment is 1, has traveled through all
value obtains side-looking edge section collection;
Step 106:
middle difference
corresponding different rectangle sections, wherein,
,
for the horizontal ordinate of the bearing point northernmost in front elevation edge contour point,
for the horizontal ordinate of the bearing point southernmost in front elevation edge contour point; Travel through the section of all rectangles, leave the minimum ordinate value in each layer rectangle slicing profile point in array
in; Find
in maximal value and minimum value, the absolute value both subtracted each other is as minification radix;
Step 107-1: respectively with
,
as starting point and terminal, by
the rectangle section of layer
transposition is also assigned to matrix after exchanging up and down
, will
minimum ordinate value in described rectangle slicing profile point and the array in step 106
in minimum value subtract each other, the result that the absolute value of the difference after subtracting each other and minification radix are divided by is as
the multiple that layer vertical view edge reduces
;
Step 107-2: utilize two interpolation algorithm to vertical view edge according to multiple
reduce, the image array after reducing is expanded to
matrix, in expansion process, the coordinate of original image matrix each point is constant, and the point of new expansion is then all filled with 0; The central point at the central point of the image after reducing and vertical view edge is aimed at and obtains matrix
; Will
with in step 107-1
central point aim at after carry out superposition and obtain matrix
,
middle general
with
common factor part be defined as border; Utilize
in the coordinate of bearing point easternmost, westernmost, southernmost and northernmost find
central point, if this central point is not for integer, turned to integer, using this central point as growth starting point; From this growth starting point,
middle to four sides growth, until looked for all values between growth starting point and border comprising growth starting point to be the coordinate of the point of 0
, p is that between growth starting point and border, all values is the number of the point of 0; Create
square null matrix
, will own
assignment is 1, has traveled through all
namely value obtains region growing Slice Sequence figure, different
corresponding zones of different growth slice map;
Step 108: draw out
middle all values be 1 select the stereoscopic three-dimensional scatter diagram namely obtaining fruit;
Step 109: statistics
in 1 number, obtain the number of pixels of fruit stereoscopic three-dimensional scatter diagram; Step 110: matching number of pixels and fruit actual volume obtain mathematical model between the two;
The number of pixels of an optional similar fruit inputs this mathematical model, can calculate the volume of this fruit.
The present invention compared with prior art has following innovative point: (1) cost of the present invention is low, does not need similar CT to scheme the same tomography sequence chart, only need the front of fruit, side and above take, simple and fast; (2) traditional volume measuring method very complicated, method of the present invention comes from Graphing of Engineering, and thinking is simply easy to promote, and measuring accuracy is relatively high.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings, wherein:
Fig. 1 is algorithm flow chart of the present invention;
Fig. 2 is the present invention 100
the fruit three-view diagram of 100 pixels;
Fig. 3 is the edge that the present invention adjusts rear fruit three-view diagram;
Fig. 4 is fruit side-looking edge cuts design sketch of the present invention;
Fig. 5 is rectangle dicing effect figure of the present invention;
Fig. 6 is that of the present invention pair of interpolation reduces superimpose rectangles dicing effect figure and region growing design sketch;
Fig. 7 is fruit stereoscopic three-dimensional scatter diagram of the present invention.
mark in figure, 021. front elevation, 022. side view, 023. vertical view, front elevation edge after 031. adjustment, 032. adjustment lateral side view edge, vertical view edge after 033. adjustment, 041. side-looking edge cuts design sketch one, 042 side-looking edge cuts design sketch two, 043. side-looking edge cuts design sketch three, 051. rectangle section one, 052. rectangle section two, 053. rectangle section three, the two interpolation in 061. vertical view edge reduces superimpose rectangles dicing effect figure mono-, 062. region growing design sketch one, the two interpolation in 063. vertical view edge reduces superimpose rectangles dicing effect figure bis-, 064. region growing design sketch two.
below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only a part of embodiment of the present invention, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.Fruit volume measuring method based on computer vision of the present invention, journey is described in detail as follows in conjunction with the accompanying drawings and embodiments:
With reference to Fig. 1, step 101,102 and 103 carries out pre-service by the fruit three-view diagram obtained ccd video camera, edge extracting and adjustment; The cube created cuts according to front elevation edge contour and side view edge contour from front and side by step 104 and 105 respectively, obtains common factor part and is rectangle section collection; The minimum ordinate value of step 106 in the minimum ordinate value in current rectangle slicing profile point and all rectangle slicing profile points subtracts each other, and the absolute value of the difference after subtracting each other is obtained minification divided by minification radix
; Step 107 utilizes two interpolation algorithm to vertical view edge by minification
carry out reducing the edge obtaining reducing; The aforesaid edge that reduces is obtained Slice Sequence figure according to region-growing method by step 108, carries out three-dimensional reconstruction obtain three-dimensional result to this Slice Sequence figure; Step 109 statistical pixel number; The actual volume of this number of pixels of step 110 matching and fruit obtains mathematical model between the two; The number of pixels of any one fruit similar is inputted this mathematical model, the volume of this fruit can be calculated.
With reference to Fig. 2, obtained the three-view diagram of fruit by ccd video camera, adjustment three-view diagram makes every width figure be all 100
100 pixels, as 021,022,023; Front elevation 021 is mapped to tone, saturation degree and brightness space (HSV) by RGB three Color Channels (RGB) and is asked for its edge; In like manner, the edge of side view 022 and the edge of vertical view 023 is asked for; Find the coordinate of easternmost, westernmost, northernmost and southernmost 4 bearing points in front elevation edge contour point, in like manner, find the coordinate of 4 bearing points in side view edge contour point.
With reference to Fig. 3, with 4 bearing point coordinates in front elevation edge 031 point for reference, adjustment side view edge, the horizontal ordinate of the bearing point northernmost in the horizontal ordinate of the bearing point northernmost in its edge contour point and front elevation edge 031 point is aligned, the side view edge 032 after being adjusted; In like manner, with the coordinate of 4 bearing points at the side view edge 032 after the coordinate of 4 bearing points in front elevation edge 031 point and adjustment for reference, adjustment vertical view edge, makes the horizontal ordinate of the bearing point northernmost in its edge contour point aim at the ordinate of the bearing point easternmost in side view edge 032 point; Adjustment vertical view edge, makes the ordinate of the bearing point westernmost in the ordinate of the bearing point westernmost in its edge contour point and front elevation edge 031 point align, the vertical view edge 033 after being adjusted; Find the coordinate of easternmost, westernmost, northernmost and southernmost 4 bearing points in vertical view edge 033 point after adjustment, utilize the coordinate of these 4 bearing points can find the central point at the vertical view edge 033 after adjustment; Create
square null matrix
; Find front elevation edge 031 point coordinate (
,
),
,
hfor front elevation edge 031 point number; With the ordinate of the bearing point westernmost in side view edge 032 point
for starting point, the ordinate of bearing point easternmost
for terminal; To own
assignment is 1, has traveled through all
value.
With reference to 041,043,045 of Fig. 4, with the ordinate of the bearing point easternmost in front elevation edge 031 point
for starting point, the ordinate of bearing point westernmost
for terminal; Will
be assigned to after transposition
square null matrix
,
; Will
carry out superposition after aiming at the central point at side view edge 032 and obtain matrix
, different
corresponding different
.
With reference to 042,044,046 of Fig. 4, find
in
with the coordinate of the edge contour point of the common factor part at side view edge 032
,
tfor edge contour is counted; By above-mentioned
?
layer
reset, then will
assignment is 1, has traveled through all
obtain side-looking edge section collection; Different
corresponding different side-looking edge sections.
With reference to Fig. 5,
middle difference
corresponding different rectangle sections,
,
for the horizontal ordinate of the bearing point northernmost in front elevation edge 031 point,
for the horizontal ordinate of the bearing point southernmost in front elevation edge 031 point; 051,052,053 difference is represented
rectangle section during value; Travel through the section of all rectangles, leave the minimum ordinate value of each layer rectangle slicing profile point in array
in; Find
in maximal value and minimum value, using the absolute value of the difference after both subtract each other as minification radix.
With reference to Fig. 6, respectively with
,
as starting point and terminal, by
the rectangle section of layer
transposition is also assigned to matrix after exchanging up and down
, will
minimum ordinate value in described rectangle slicing profile point deducts
in minimum value, absolute value and the minification radix of the difference after subtracting each other are divided by, using the result after being divided by as
the multiple that layer vertical view edge reduces
; Utilize two interpolation algorithm to vertical view edge 033 according to multiple
reduce, the image array after reducing is expanded to
matrix, in expansion process, the coordinate of original image matrix each point is constant, and the point of new expansion is then all filled with 0; Matrix is obtained after being aimed at by the central point at the central point of the image after reducing and vertical view edge
; Will
with
central point aim at after carry out superposition and obtain matrix
, different layers
as figure 061 and 063; ?
middle by matrix
with
the outline definition of common factor part be border; Utilize
the coordinate of bearing point easternmost, westernmost, southernmost and northernmost find its central point, if this central point is not integer, turned to integer, using this central point as growth starting point; From growth starting point,
middle to four sides growth, look for all values between growth starting point and border comprising growth starting point to be the coordinate of the point of 0
,
pbetween representative growth starting point and border, all values is the number of the point of 0; Create
square null matrix
, will
assignment is 1, has traveled through all
value, obtain region growing Slice Sequence figure, the section of different layers is as figure 062 and 064.
With reference to Fig. 7, judge
in value whether be 1, if 1 draw out this point until
institute has a little all traveled through, and obtains the stereoscopic three-dimensional scatter diagram of fruit; Statistics
in 1 number, obtain the number of pixels of the stereoscopic three-dimensional figure of fruit, this number of pixels of matching and fruit actual volume obtain mathematical model between the two; The number of pixels of an optional similar fruit inputs this mathematical model, can calculate the volume of this fruit.
To the above-mentioned explanation of the disclosed embodiments, professional and technical personnel in the field are realized or uses the present invention.To be apparent for those skilled in the art to the multiple amendment of these embodiments, General Principle as defined herein can without departing from the spirit or scope of the present invention, realize in other embodiments.Therefore, the present invention can not be restricted to these embodiments shown in this article, but will meet the widest scope consistent with principle disclosed herein and features of novelty.
Claims (1)
1. based on the fruit volume measuring method of computer vision, it is characterized in that, first cut according to the front elevation edge contour of fruit and side view edge contour respectively from the cubical front created and side, obtain common factor part and be rectangle section collection; Deduct the minimum ordinate value in minimum rectangle slicing profile point with the minimum ordinate value in maximum rectangle slicing profile point, then using the absolute value of this difference as minification radix; Deduct the minimum ordinate value in minimum rectangle slicing profile point with the minimum ordinate value in every one deck rectangle slicing profile point, then using the absolute value of this difference divided by minification radix as minification; The two vertical view edge of interpolation algorithm to fruit is utilized to reduce by aforementioned minification, region-growing method is utilized to obtain the Slice Sequence figure of fruit by reducing edge, the stereoscopic three-dimensional scatter diagram of fruit is obtained by this sequence chart three-dimensional reconstruction, add up the number of pixels of this stereoscopic three-dimensional scatter diagram, this number of pixels of matching and fruit actual volume obtain mathematical model between the two, number of pixels are inputted the volume that this mathematical model can obtain fruit.
2.fruit volume measuring method based on computer vision according to claim 1, it is characterized in that, concrete steps are:
Step 101: obtain the front elevation of fruit, side view and vertical view by ccd video camera, adjust this three-view diagram and make every width figure be all 100
100 pixels; Read in front elevation, ask for front elevation edge; Find the coordinate of easternmost, westernmost, northernmost and southernmost 4 bearing points in front elevation edge contour point;
Step 102: read in side view, asks for side view edge, finds the coordinate of easternmost, westernmost, northernmost and southernmost 4 bearing points in side view edge contour point; With front elevation edge for standard, the position at adjustment side view edge, makes the horizontal ordinate of the bearing point northernmost in the horizontal ordinate of the bearing point northernmost in its edge contour point and front elevation edge contour point align;
Step 103: read in vertical view, asks for vertical view edge; With 4, the side view edge bearing point coordinate after 4, front elevation edge bearing point coordinate and adjustment for reference, the position at adjustment vertical view edge, makes the horizontal ordinate of the bearing point northernmost in its edge contour point aim at the ordinate of the bearing point easternmost in side view edge contour point; Adjustment vertical view edge makes the ordinate of the bearing point westernmost in the ordinate of the bearing point westernmost in its edge contour point and front elevation edge contour point align; Find the coordinate of easternmost, westernmost, northernmost and southernmost 4 bearing points in the rear vertical view edge contour point of adjustment, utilize the coordinate of these 4 bearing points to find the central point at vertical view edge;
Step 104: create
square null matrix
; Front elevation edge is corresponding
front, side view edge is corresponding
side, vertical view edge is corresponding
above;
Step 105_1: with the ordinate of the bearing point westernmost in side view edge contour point
for starting point, the ordinate of bearing point easternmost
for terminal, front elevation matrix of edge is replicated in
?
layer
,
, traveled through all
value;
Step 105_2: with the ordinate of the bearing point easternmost in front elevation edge contour point
for starting point, the ordinate of bearing point westernmost
for terminal; Will
,
be assigned to after transposition
square null matrix
; Will
carry out superposing after aiming at side view edge center point and find the coordinate of the edge contour point of both common factor parts
,
tfor edge contour is counted; By above-mentioned
?
layer
reset, then will
assignment is 1, has traveled through all
value obtains side-looking edge section collection;
Step 106:
middle difference
corresponding different rectangle sections, wherein,
,
for the horizontal ordinate of the bearing point northernmost in front elevation edge contour point,
for the horizontal ordinate of the bearing point southernmost in front elevation edge contour point; Travel through the section of all rectangles, leave the minimum ordinate value in each layer rectangle slicing profile point in array
in; Find
in maximal value and minimum value, the absolute value both subtracted each other is as minification radix;
Step 107-1: respectively with
,
as starting point and terminal, by
the rectangle section of layer
transposition is also assigned to matrix after exchanging up and down
, will
minimum ordinate value in described rectangle slicing profile point and the array in step 106
in minimum value subtract each other, the result that the absolute value of the difference after subtracting each other and minification radix are divided by is as
the multiple that layer vertical view edge reduces
;
Step 107-2: utilize two interpolation algorithm to vertical view edge according to multiple
reduce, the image array after reducing is expanded to
matrix, in expansion process, the coordinate of original image matrix each point is constant, and the point of new expansion is then all filled with 0; The central point at the central point of the image after reducing and vertical view edge is aimed at and obtains matrix
; Will
with in step 107-1
central point aim at after carry out superposition and obtain matrix
,
middle general
with
common factor part be defined as border; Utilize
in the coordinate of bearing point easternmost, westernmost, southernmost and northernmost find
central point, if this central point is not for integer, turned to integer, using this central point as growth starting point; From this growth starting point,
middle to four sides growth, until looked for all values between growth starting point and border comprising growth starting point to be the coordinate of the point of 0
,
pfor all values between growth starting point and border is the number of the point of 0; Create
square null matrix
, will own
assignment is 1, has traveled through all
namely value obtains region growing Slice Sequence figure, different
corresponding zones of different growth slice map;
Step 108: draw out
middle all values be 1 select the stereoscopic three-dimensional scatter diagram namely obtaining fruit;
Step 109: statistics
in 1 number, obtain the number of pixels of fruit stereoscopic three-dimensional scatter diagram;
Step 110: matching number of pixels and fruit actual volume obtain mathematical model between the two;
The number of pixels of an optional similar fruit inputs this mathematical model, can calculate the volume of this fruit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310198684.6A CN103307979B (en) | 2013-05-27 | 2013-05-27 | Based on the fruit volume measuring method of computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310198684.6A CN103307979B (en) | 2013-05-27 | 2013-05-27 | Based on the fruit volume measuring method of computer vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103307979A CN103307979A (en) | 2013-09-18 |
| CN103307979B true CN103307979B (en) | 2015-09-30 |
Family
ID=49133474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310198684.6A Expired - Fee Related CN103307979B (en) | 2013-05-27 | 2013-05-27 | Based on the fruit volume measuring method of computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103307979B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038879A (en) * | 2017-12-12 | 2018-05-15 | 众安信息技术服务有限公司 | A kind of volume of food method of estimation and its device |
| CN110060294A (en) * | 2019-04-30 | 2019-07-26 | 中国农业科学院农业环境与可持续发展研究所 | A kind of yield assessment method of fruit tree crop |
| JP6945109B2 (en) * | 2020-02-28 | 2021-10-06 | 株式会社宝計機製作所 | Volume measuring method for spherical crops, volume measuring device using it, and inspection device for "lifting" |
| CN113222939B (en) * | 2021-05-14 | 2023-04-07 | 广东工业大学 | Food image volume calculation method based on thumbnail calibration |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101509761A (en) * | 2009-03-16 | 2009-08-19 | 北京市农林科学院 | Egg volume and surface area detecting method |
| CN102042814A (en) * | 2010-06-24 | 2011-05-04 | 中国人民解放军国防科学技术大学 | Projection auxiliary photographing measurement method for three-dimensional topography of large storage yard |
| CN103017689A (en) * | 2012-12-31 | 2013-04-03 | 华北电力大学（保定） | Static contact angle calculation method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2397389A1 (en) * | 2002-08-09 | 2004-02-09 | Djemel Ziou | Image model based on n-pixels and defined in algebraic topology, and applications thereof |
-
2013
- 2013-05-27 CN CN201310198684.6A patent/CN103307979B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101509761A (en) * | 2009-03-16 | 2009-08-19 | 北京市农林科学院 | Egg volume and surface area detecting method |
| CN102042814A (en) * | 2010-06-24 | 2011-05-04 | 中国人民解放军国防科学技术大学 | Projection auxiliary photographing measurement method for three-dimensional topography of large storage yard |
| CN103017689A (en) * | 2012-12-31 | 2013-04-03 | 华北电力大学（保定） | Static contact angle calculation method |
Non-Patent Citations (4)
| Title |
|---|
| Advances in machine vision applications for automatic inspection and quality evaluation of fruits and vegetables;Sergio Cubero etal;《Food Bioprocess Technol》;20111231;全文 * |
| 基于机器视觉的面包体积及形状测量系统的研究;李国华等;《天津科技大学学报》;20040331;第19卷(第1期);1全文 * |
| 基于机器视觉的鸡蛋体积与表面积计算方法;周平等;《农业机械学报》;20100531;第41卷(第5期);全文 * |
| 基于计算机视觉的苹果质量检测;刘刚等;《安徽农业科学》;20120831;第40卷(第8期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103307979A (en) | 2013-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102902355B (en) | The space interaction method of mobile device | |
| CN105205866B (en) | City threedimensional model fast construction method based on point off density cloud | |
| US7983474B2 (en) | Geospatial modeling system and related method using multiple sources of geographic information | |
| CN103606151B (en) | Based on the virtual geographical scene method for auto constructing on a large scale of imaging point cloud | |
| MX2022006805A (en) | Systems and methods for modeling structures using point clouds derived from stereoscopic image pairs. | |
| CN106709947A (en) | RGBD camera-based three-dimensional human body rapid modeling system | |
| CN103307979B (en) | Based on the fruit volume measuring method of computer vision | |
| JP2015108621A5 (en) | Non-primary computer-readable medium storing method, image processing apparatus, and program for extracting plane from three-dimensional point cloud | |
| CN102096818B (en) | Object-oriented automatic extracting method and system for outline and parameter of remote sensing image crown | |
| CN105303616B (en) | Embossment modeling method based on single photo | |
| CN106910216B (en) | A kind of grid surface based on ship hull plate point cloud data determines method and device | |
| CN103810729B (en) | A kind of based on isocontour raster image vector quantized method | |
| CN102509348A (en) | Method for showing actual object in shared enhanced actual scene in multi-azimuth way | |
| CN105005988B (en) | A kind of solid matching method based on interactive image segmentation | |
| CN103940407A (en) | Method used for gully erosion extraction based on landform and remote sensing image fusion technology | |
| CN104424642A (en) | Detection method and detection system for video salient regions | |
| CN103714549A (en) | Stereo image object segmentation method based on rapid local matching | |
| CN103985128A (en) | Three-dimensional matching method based on color intercorrelation and self-adaptive supporting weight | |
| CN104408733A (en) | Object random walk-based visual saliency detection method and system for remote sensing image | |
| CN104778691B (en) | Three-dimensional point cloud data processing method | |
| CN113093216A (en) | Irregular object measurement method based on laser radar and camera fusion | |
| CN106203429A (en) | Based on the shelter target detection method under binocular stereo vision complex background | |
| CN103198475A (en) | Full-focus synthetic aperture perspective imaging method based on multilevel iteration visualization optimization | |
| CN102799646A (en) | Multi-view video-oriented semantic object segmentation method | |
| CN104268941A (en) | Hot spot forming method and device for simulated three-dimensional map |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150930 Termination date: 20160527 |