CN100416590C - Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic - Google Patents
Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic Download PDFInfo
- Publication number
- CN100416590C CN100416590C CNB2005100865093A CN200510086509A CN100416590C CN 100416590 C CN100416590 C CN 100416590C CN B2005100865093 A CNB2005100865093 A CN B2005100865093A CN 200510086509 A CN200510086509 A CN 200510086509A CN 100416590 C CN100416590 C CN 100416590C
- Authority
- CN
- China
- Prior art keywords
- threshold
- point
- weeds
- crop
- row
- 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
Landscapes
- Soil Working Implements (AREA)
- Image Analysis (AREA)
Abstract
Using position and texture character, the disclosed method in use for identifying farm weed in seedling stage of crop includes following steps: (1) using digital video camera to collect video of seedling stage of drilling crop in farm and seedling of weed on video file; then, through cable, connecting digital video camera to the video collection card inside computer in order to export collected video file and obtaining frame of image form exported video file; (2) using computer to segment between green plant and background of soil; (3) using character of position to identify weed between rows; (4) using texture character to identify weed in rows; (5) weed map between rows of crop, and weed map in rows of crop are added to obtain weed map in farm.
Description
Technical field
The present invention relates to precision agriculture mechanized equipment automatic control technology field, be specifically related to a kind of weeds in field information method of identification automatically.
Background technology
Weeds in field and crop competition moisture and nutrient are occupied the space, influence the crop photosynthesis effect, disturb plant growth; As untimely control, can cause grain yield seriously to descend.According to estimates, China only between drilling crops wheat paddock the crop smothering area reach 1,000 ten thousand hectares, a year grain yield is lost more than 4,000,000,000 kilograms.
Chemical weed control has become main weeding system.In developed country, the amount of application of herbicide accounts for the over half of the total amount of application of agricultural chemicals; Over nearly 20 years, the herbicide application amount of China increases rapidly, and year total amount consumed is nearly 470,000 tons now.
At present, the use-pattern of chemical herbicide is commonly the large tracts of land of extensive style and sprays, and the distribution density of weeds on average only accounts for 30%, and therefore a large amount of agricultural chemicals has caused waste, has also caused serious ecological environmental pollution.Therefore, the demand of precision agriculture of variable rate spray application becomes the research focus.Realize variable spray medicine, primarily solve the weeds in field automatic recognition problem.
The weeds in field recognition methods has personal monitoring, remote sensing monitoring and three kinds of approach of near-earth image monitoring.1) personal monitoring is before the operation of spray medicine, utilization GPS or other positioning system, the position of the weeds in field that artificial record is automatically seen, be depicted as the weeds distribution plan then, this method exists inefficiency, labour intensity to rely on artificial experience greatly, fully, in the observation of the large tracts of land weeds growth of cereal crop seedlings, it is powerless that the personal monitoring seems.2) though remote sensing monitoring has overcome many drawbacks of personal monitoring, still,, be mainly used in several weeds that large tracts of land takes place in the identification certain growth phase because the space and the spectral resolution of remote sensing images is lower, cause the weeds discrimination lower and bearing accuracy is low.3) and the near-earth image monitoring method is to utilize machine vision technique under the nearer condition in distance ground, catch, handle and analyze the information of the crop, weeds and the background that are comprised in the image of field, and automatically identifying weeds, this method can reach higher weeds discrimination.But this method is normally utilized the color distinction of crop and weeds to carry out weeds and is discerned automatically.Because the unevenness of field illumination, and the close problem of the color of weeds and crop, the discrimination to weeds is lower automatically with color, and the automatic discrimination of these method weeds is usually less than 80%.
Summary of the invention
(1) technical matters that will solve
The purpose of this invention is to provide a kind of discrimination height, and can discern the method for crops seedling stage weeds in field fast and automatically.
(2) technical scheme
In order to achieve the above object, the present invention takes following method step:
1) during the employing Digital Video is with the video acquisition of drilling crops seedling stage field crops seedling and weeds seedling to DV earlier; Then, by cable Digital Video and with the video acquisition card connection that is installed in the computing machine, the video file of derive gathering obtains two field picture from the video file of deriving;
2) utilize computing machine to carry out cutting apart of green plants and Soil Background:
According to " super green method ", promptly cut apart green plants and Soil Background with the color threshold index;
3) utilize position feature identification inter-row weed:
According to the pixel histogram of green plants, extract the center line and the width of crop row, thus the identification inter-row weed;
4) utilize weeds in the textural characteristics identification row:
Crop center line with extraction is a benchmark, chooses texture block to both sides, calculates the textural characteristics of green plants, weeds in the identification row;
5) crop row is mixed with that weeds add computing in sketch and the crop row, obtains weeds in field figure.
In step 1), also comprise 24 the RGB original color image in drilling crops seedling stage field, according to super green colour index Extra-Green=2G-R-B, be converted to 8 gray level image; Using the Otsu method then is bianry image with 8 greyscale image transitions, i.e. black white image, and wherein, green plants is prospect-white, soil is background-black.
In step 3), also comprise the substantially invariable position feature of crop row distance according to crop, by the statistics column direction,, obtain the histogram f (x) that the plant pixel distributes promptly along crop row direction plant number of picture elements:
x=0,1,2,…W-1
Wherein, f (x, y) the presentation video picture element (x, gray-scale value y), W are the width of image, H is the height of image;
According to the pixel histogram of green plants, determine the position and the line width at crop row center automatically, the plant pixel that is positioned at outside the line width is inter-row weed:
A) if histogrammic 1 P of pixel (x)>=threshold, then this point may be a measuring point;
B) if first measuring point (i=0) then has:
As P (x-5)<threshold﹠amp; ﹠amp; During P (x+5)>threshold, x is the left margin point, the ascent stage, writes down this point;
As P (x-5)>threshold﹠amp; ﹠amp; During P (x+5)<threshold, x is the right margin point, and descending branch writes down this point;
As P (x-5)>threshold﹠amp; ﹠amp; During P (x+5)>threshold, x is the left margin point, the ascent stage, writes down this point;
C) if not first measuring point (i!=0), then has
As P (x-5)<threshold﹠amp; ﹠amp; P (x+5)>threshold﹠amp; ﹠amp; Previous point is the descending branch point, and x is the left margin point, the ascent stage, writes down this point;
As P (x-5)>threshold﹠amp; ﹠amp; P (x+5)<threshold﹠amp; ﹠amp; Previous point is the ascent stage point, and x is the right margin point, and descending branch writes down this point.
In step 4), also comprise with the crop row center line being that benchmark is chosen texture block, in the gray scale of the H of 8 green plantss color component, extract the gray level co-occurrence matrixes of texture block respectively:
Wherein, i=f (x
1, y
1), j=f (x
2, y
2), and (x is arranged
2, y
2)=(x
1, y
1)+(dcos θ, dsin θ)
D, θ represent that respectively pixel is to spacing walk-off angle degree; The molecule on equal sign the right be have certain spatial relationship, gray-scale value is respectively g
1And g
2The number that pixel is right, denominator are the right summation number (# represents quantity) of pixel;
Extract second moment, entropy, contrast, homogeneity and these 5 textural characteristics parameters of correlativity, utilize the classification of each piece of K-mean cluster method discriminatory analysis that does not have the supervision characteristic then, thus weeds in the identification row.
(3) beneficial effect
Since adopted seedling stage crop and position and the textural characteristics of weeds combine with Computer Image Processing, therefore, has the discrimination height, and, can discern the weeds in field distribution situation fast and automatically, and according to this distribution situation, implement variable farm chemical applying, thereby, save a large amount of agricultural chemicals, alleviate the pollution of ecologic environment; Simultaneously, alleviated people's labour intensity.
Description of drawings
Fig. 1 is a theory diagram of the present invention.
Fig. 2 is the process flow diagram of determining algorithm automatically at crop row of the present invention center.
Fig. 3 is to be the process flow diagram of the texture block Feature Extraction algorithm of benchmark with the crop row center line among the present invention.
Embodiment
Following examples are used to illustrate the present invention, but are not used for limiting the scope of the invention.
As shown in Figure 1, during the employing Digital Video is with the video acquisition of drilling crops seedling stage field crops seedling and weeds seedling to DV earlier; Then, by cable Digital Video and with the 1 394 video acquisition card connection that are installed in the computing machine, the video of derive gathering is the video file of * .avi form; From the video file of deriving, obtain two field picture.
To the two field picture that obtains, according to the position and the textural characteristics of drilling crops seedling stage field crops seedling and weeds seedling, identification drilling crop weeds in field.Embodiment is as follows:
1),, is converted to the gray level image of 8bit according to super green colour index Extra-Green=2G-R-B to drilling crops seedling stage field 24bit RGB original color image;
2) utilization Otsu method is a bianry image with the greyscale image transitions of 8bit, and green plants is prospect (white), and soil is background (black);
3) the pixel histogram of green plants in statistics column direction (along the crop row direction) bianry image, the histogrammic horizontal ordinate of pixel is the width of image, ordinate is the plant number of picture elements in every row;
4) according to the histogrammic maximal value of pixel, determine the threshold value on crop row border, threshold value is tentatively determined the border, the left and right sides of crop row thus;
5) according to the width on border, the left and right sides, remove pseudo-border, finally determine the border, the left and right sides of crop row, and determine the position of center line and the crop line number of crop row in view of the above;
6) mark is positioned at the inter-row weed (grey, 100) outside the border, the crop row left and right sides;
7) bianry image and 24bit RGB original color image add computing, and the green plants zone that mapping is cut apart obtains the green plants coloured image in original image, and green plants is original rgb value, and Soil Background is black (0);
8) according to color space RGB-〉conversion formula of HIS, calculate the 8bit gray level image of the colourity H of green plants coloured image;
9) position with the crop row center line extracted is a benchmark, and the texture block of 16 * 16 sizes is extracted on the border successively to the left and right respectively, calculates second moment, entropy, contrast, homogeneity and the correlativity of each texture block;
10) utilization K-mean cluster analysis algorithm calculates each eigenwert to distances of clustering centers, and picture element is included into that minimum class of distance, weeds in identification crop and the row, and mark is positioned at the weeds (grey, 100) of crop row;
11) crop row is mixed with that weeds figure adds computing in sketch and the crop row, obtains weeds in field figure.
Below in conjunction with Fig. 2, Fig. 3, automatically determining algorithm and be that the texture block Feature Extraction algorithm of benchmark is further described specifically with the crop row center line the crop row center.
1, determining automatically based on the histogrammic crop row of pixel center
According to the substantially invariable position feature of crop row distance,, obtain the histogram f (x) that the plant pixel distributes earlier by statistics column direction (along the crop row direction) plant number of picture elements:
Wherein, f (x, y) the presentation video picture element (x, gray-scale value y), W are the width of image, H is the height of image.
Then, according to the histogrammic maximal value of the pixel of green plants, determine the boundary segmentation threshold value threshold of crop row:
threshold=Max(f(x))/2
Then, according to pixel histogram and the boundary segmentation threshold value threshold of green plants, determine the boundary position of crop row automatically:
1) if histogrammic 1 P of pixel (x)>=threshold, then this point may be a frontier point;
2) if first frontier point (i=0) then has:
When P (x+5)>threshold, x is left margin point flag1=TRUE, and ascent stage flag2=TRUE writes down this C[i]=x;
When P (x-5)>threshold and P (x+5)<threshold, x is right margin point flag1=FALSE, and descending branch flag2=FALSE writes down this C[i]=x;
3) if not first frontier point (i!=0), then has
When P (x-5)<threshold and P (x+5)>threshold and previous point are descending branch point flag2=FALSE, x is ascent stage frontier point flag2=TRUE, writes down this C[i]=x;
When P (x-5)>threshold and P (x+5)<threshold and previous point are ascent stage point flag2=TRUE, x is descending branch frontier point flag2=FALSE, writes down this C[i]=x.
At last, according to the pixel histogram of green plants and the boundary position C[i of crop row], determine the position of the central row of crop row automatically:
1) if first frontier point C[i] be left margin flag1=TRUE, then crop row center L[k is asked in circulation as follows]: when (C[i+1]-C[i])>20, L[k]=(C[i+1]+C[i]))/2
2) if first frontier point C[i] be right margin flag1=FALSE, then crop row center L[k is asked in circulation as follows]: when (C[i+2]-C[i+1])>20, L[k]=(C[i+2]+C[i+1]))/2
2, weeds identification employing is the texture block Feature Extraction algorithm of benchmark with the crop row center line in the row:
Be benchmark with the centre line L [k] of obtaining crop row earlier, calculate the texture block number respectively to the left and right:
Nl=(L[k]-Rw[2k])/Bw
Nr=(Rw[2k+1]-L[k])/Bw
Wherein, Nl and Nr are respectively the texture block number on the left side and the right of datum line, Rw[] be the border of the crop row obtained, Bw is the width of texture block.
Then, count Nl and Nr, in the gray-scale map of the H color component of the green plants of 8bit, take out each texture block successively, be stored in the intermediate images piece of prior distribution, calculate the gray level co-occurrence matrixes of this texture block according to texture block:
Wherein, i=f (x
1, y
1), j=f (x
2, y
2), and (x is arranged
2, y
2)=(x
1, y
1)+(dcos θ, dsin θ)
D, θ difference remarked pixel is to spacing walk-off angle degree (θ generally gets 0 °, and 45 °, 90 °, 135 ° make things convenient for computing).The molecule on equal sign the right be have certain spatial relationship, gray-scale value is respectively g
1And g
2The number that pixel is right, denominator are the right summation number (# represents quantity) of pixel.
Then, according to the gray level co-occurrence matrixes that calculates, extract energy, contrast, entropy, unfavourable balance square and these 5 textural characteristics parameters of correlativity:
1) energy:
2) contrast:
(k
1, k
2Be positive integer)
3) entropy:
4) unfavourable balance square:
5) correlativity:
μ in the formula
1, μ
2, σ
1, σ
2Be defined as respectively:
At last, according to the maximal value Lmax and the minimum value Lmin of the textural characteristics parameter of being calculated, the textural characteristics parameter F of asking for is carried out normalization:
When Lmax-Lmin=0, F1=0.
Weeds figure adds computing in inter-row weed figure that obtains by above-mentioned algorithm and the crop row, promptly obtains weeds in field figure.
Above method discrimination height has solved that weeds and crop are all green and the technical matters that is difficult to differentiate; Simultaneously, can discern weeds in field fast and automatically, thereby, for next step variable farm chemical applying provides foundation.
Claims (4)
1. method of utilizing position and textural characteristics to discern the crops seedling stage weeds in field automatically is characterized in that following steps are arranged:
1) adopt earlier Digital Video with the video acquisition of drilling crops seedling stage field crops seedling and weeds seedling in the Digital Video file; Then, by cable Digital Video and with the video acquisition card connection that is installed in the computing machine, the video file of derive gathering obtains two field picture from the video file of deriving;
2) utilize computing machine to carry out cutting apart of green plants and Soil Background:
According to " super green method ", promptly cut apart green plants and Soil Background with the color threshold index;
3) utilize position feature identification inter-row weed:
According to the pixel histogram of green plants, extract the center line and the width of crop row, thus the identification inter-row weed;
4) utilize weeds in the textural characteristics identification row:
Crop center line with extraction is a benchmark, chooses texture block to both sides, calculates the textural characteristics of green plants, weeds in the identification row;
5) crop row is mixed with that weeds figure adds computing in sketch and the crop row, obtains weeds in field figure.
2. a kind of method of utilizing position and textural characteristics to discern the crops seedling stage weeds in field automatically as claimed in claim 1 is characterized in that:
In step 2) in, also comprise drilling crops seedling stage field 24bit RGB original color image according to super green colour index Extra-Green=2G-R-B, is converted to the gray level image of 8bit; Using big Tianjin threshold method then is bianry image with the greyscale image transitions of 8bit, i.e. black white image, and wherein, green plants is prospect-white, soil is background-black.
3. a kind of method of utilizing position and textural characteristics to discern the crops seedling stage weeds in field automatically as claimed in claim 1 is characterized in that:
In step 3), also comprise by the statistics column direction,, obtaining the histogram f (x) that the plant pixel distributes promptly along crop row direction plant number of picture elements according to the substantially invariable position feature of crop row distance:
x=0,1,2,…W-1
Wherein, f (x, y) the presentation video picture element (x, gray-scale value y), W are the width of image, H is the height of image;
According to the pixel histogram of green plants, determine the position and the line width at crop row center automatically, the plant pixel that is positioned at outside the line width is inter-row weed:
A) if histogrammic 1 P of pixel (x)>=threshold, then this point may be a measuring point, wherein threshold represents the boundary segmentation threshold values;
B) if first measuring point then has:
When P (x-5)<threshold and P (x+5)>threshold, x is the left margin point, the ascent stage, writes down this point;
When P (x-5)>threshold and P (x+5)<threshold, x is the right margin point, and descending branch writes down this point;
When P (x-5)>threshold and P (x+5)>threshold, x is the left margin point, the ascent stage, writes down this point;
C) if not first measuring point, then have
When P (x-5)<threshold and P (x+5)>threshold and previous point are the descending branch point, x is the left margin point, the ascent stage, writes down this point;
When P (x-5)>threshold and P (x+5)<threshold and previous point are the ascent stage point, x is the right margin point, and descending branch writes down this point.
4. a kind of method of utilizing position and textural characteristics to discern the crops seedling stage weeds in field automatically as claimed in claim 1 is characterized in that:
In step 4), also comprise with the crop row center line being that benchmark is chosen texture block, in the gray scale of the H color component of the green plants of 8bit, extract the gray level co-occurrence matrixes of texture block respectively:
Wherein, i=f (x
1, y
1), j=f (x
2, y
2), and (x is arranged
2, y
2)=(x
1, y
1)+(dcos θ, dsin θ)
D, θ represent that respectively pixel is to spacing walk-off angle degree; The molecule on equal sign the right be have certain spatial relationship, gray-scale value is respectively g
1And g
2The number that pixel is right, denominator are the right summation number of pixel, and wherein # represents quantity;
Extract energy, entropy, contrast, unfavourable balance square and these 5 textural characteristics parameters of correlativity, utilize the classification of each piece of K-mean cluster method discriminatory analysis that does not have the supervision characteristic then, thus weeds in the identification row.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2005100865093A CN100416590C (en) | 2005-09-23 | 2005-09-23 | Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2005100865093A CN100416590C (en) | 2005-09-23 | 2005-09-23 | Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic |
Publications (2)
Publication Number | Publication Date |
---|---|
CN1936919A CN1936919A (en) | 2007-03-28 |
CN100416590C true CN100416590C (en) | 2008-09-03 |
Family
ID=37954415
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2005100865093A Active CN100416590C (en) | 2005-09-23 | 2005-09-23 | Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN100416590C (en) |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11079725B2 (en) | 2019-04-10 | 2021-08-03 | Deere & Company | Machine control using real-time model |
US11178818B2 (en) | 2018-10-26 | 2021-11-23 | Deere & Company | Harvesting machine control system with fill level processing based on yield data |
RU2764872C2 (en) * | 2016-05-12 | 2022-01-21 | Басф Се | Weed detection in natural environment |
US11234366B2 (en) | 2019-04-10 | 2022-02-01 | Deere & Company | Image selection for machine control |
US11240961B2 (en) | 2018-10-26 | 2022-02-08 | Deere & Company | Controlling a harvesting machine based on a geo-spatial representation indicating where the harvesting machine is likely to reach capacity |
US20220110251A1 (en) | 2020-10-09 | 2022-04-14 | Deere & Company | Crop moisture map generation and control system |
US11467605B2 (en) | 2019-04-10 | 2022-10-11 | Deere & Company | Zonal machine control |
US11474523B2 (en) | 2020-10-09 | 2022-10-18 | Deere & Company | Machine control using a predictive speed map |
US11477940B2 (en) | 2020-03-26 | 2022-10-25 | Deere & Company | Mobile work machine control based on zone parameter modification |
US11589509B2 (en) | 2018-10-26 | 2023-02-28 | Deere & Company | Predictive machine characteristic map generation and control system |
US11592822B2 (en) | 2020-10-09 | 2023-02-28 | Deere & Company | Machine control using a predictive map |
US11635765B2 (en) | 2020-10-09 | 2023-04-25 | Deere & Company | Crop state map generation and control system |
US11641800B2 (en) | 2020-02-06 | 2023-05-09 | Deere & Company | Agricultural harvesting machine with pre-emergence weed detection and mitigation system |
US11650587B2 (en) | 2020-10-09 | 2023-05-16 | Deere & Company | Predictive power map generation and control system |
US11672203B2 (en) | 2018-10-26 | 2023-06-13 | Deere & Company | Predictive map generation and control |
US11675354B2 (en) | 2020-10-09 | 2023-06-13 | Deere & Company | Machine control using a predictive map |
US11711995B2 (en) | 2020-10-09 | 2023-08-01 | Deere & Company | Machine control using a predictive map |
US11727680B2 (en) | 2020-10-09 | 2023-08-15 | Deere & Company | Predictive map generation based on seeding characteristics and control |
US11778945B2 (en) | 2019-04-10 | 2023-10-10 | Deere & Company | Machine control using real-time model |
US11825768B2 (en) | 2020-10-09 | 2023-11-28 | Deere & Company | Machine control using a predictive map |
US11844311B2 (en) | 2020-10-09 | 2023-12-19 | Deere & Company | Machine control using a predictive map |
US11845449B2 (en) | 2020-10-09 | 2023-12-19 | Deere & Company | Map generation and control system |
US11849672B2 (en) | 2020-10-09 | 2023-12-26 | Deere & Company | Machine control using a predictive map |
US11864483B2 (en) | 2020-10-09 | 2024-01-09 | Deere & Company | Predictive map generation and control system |
US11874669B2 (en) | 2020-10-09 | 2024-01-16 | Deere & Company | Map generation and control system |
US11889787B2 (en) | 2020-10-09 | 2024-02-06 | Deere & Company | Predictive speed map generation and control system |
US11889788B2 (en) | 2020-10-09 | 2024-02-06 | Deere & Company | Predictive biomass map generation and control |
US11895948B2 (en) | 2020-10-09 | 2024-02-13 | Deere & Company | Predictive map generation and control based on soil properties |
US11927459B2 (en) | 2020-10-09 | 2024-03-12 | Deere & Company | Machine control using a predictive map |
US11946747B2 (en) | 2020-10-09 | 2024-04-02 | Deere & Company | Crop constituent map generation and control system |
US11957072B2 (en) | 2020-02-06 | 2024-04-16 | Deere & Company | Pre-emergence weed detection and mitigation system |
US11983009B2 (en) | 2020-10-09 | 2024-05-14 | Deere & Company | Map generation and control system |
Families Citing this family (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
HU3056U (en) * | 2005-04-29 | 2006-03-28 | G & G Noevenyvedelmi Es Keresk | Construction for making weed map |
CN101807252B (en) * | 2010-03-24 | 2012-03-28 | 中国农业大学 | Crop row center line extraction method and system |
CN101859375B (en) * | 2010-06-01 | 2011-12-28 | 南京林业大学 | Method for recognizing inline crops and weeds of seedling stage in farmland |
CN102339378A (en) * | 2010-07-22 | 2012-02-01 | 中国农业机械化科学研究院 | Method and device for automatically extracting cotton seeds |
CN102982533B (en) * | 2012-11-01 | 2015-03-04 | 江苏大学 | Bamboo shoot image cutting method based on computer vision |
CN103020595B (en) * | 2012-12-05 | 2015-08-12 | 汤烈 | Based on crops-weed identification and the localization method of three-dimensional time-of-flight method imaging |
CN104111653A (en) * | 2013-04-22 | 2014-10-22 | 苏州宝时得电动工具有限公司 | Automatic walking equipment and working region judgment method thereof |
CN104345734A (en) * | 2013-08-07 | 2015-02-11 | 苏州宝时得电动工具有限公司 | Automatic working system, automatic walking equipment and control method thereof |
CN103839069B (en) * | 2014-03-11 | 2017-04-12 | 浙江理工大学 | Lawn miss cutting recognition method based on image analysis |
US10165722B2 (en) * | 2014-12-05 | 2019-01-01 | Deere & Company | Scouting systems |
EP3316673B1 (en) * | 2015-07-02 | 2020-11-04 | EcoRobotix SA | Robot vehicle and method using a robot for an automatic treatment of vegetable organisms |
CN105335749B (en) * | 2015-08-28 | 2019-05-10 | 浙江理工大学 | Area limit line drawing method is not cut in meadow based on gray level co-occurrence matrixes |
CN106780585B (en) * | 2016-11-28 | 2019-07-23 | 自然资源部第二海洋研究所 | The calculation method and application of any gray level co-occurrence matrixes based on image rotation |
CN108009542B (en) * | 2017-11-01 | 2021-06-15 | 华中农业大学 | Weed image segmentation method in rape field environment |
CN108776803A (en) * | 2018-04-20 | 2018-11-09 | 中国农业大学 | The method and system of weeds in a kind of removal farmland |
CN109522929A (en) * | 2018-10-16 | 2019-03-26 | 南京农业大学 | It is a kind of based on multi-source image fusion natural environment under wheat weeds recognition methods |
CN109934256A (en) * | 2019-01-28 | 2019-06-25 | 华南农业大学 | One kind is based on GA-ANN Feature Dimension Reduction and the preferred weeds in paddy field recognition methods of SOM feature |
CN109975296A (en) * | 2019-04-18 | 2019-07-05 | 广西科技大学 | A kind of weed identification method for green leaf vegetables vegetables |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1423237A (en) * | 2001-11-16 | 2003-06-11 | 株式会社三丰 | Picture borderline detection system and method |
-
2005
- 2005-09-23 CN CNB2005100865093A patent/CN100416590C/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1423237A (en) * | 2001-11-16 | 2003-06-11 | 株式会社三丰 | Picture borderline detection system and method |
Non-Patent Citations (8)
Title |
---|
基于机器视觉的田间杂草识别技术研究进展. 毛文华,王一鸣,张小超,王月青.农业工程学报,第20卷第5期. 2004 |
基于机器视觉的田间杂草识别技术研究进展. 毛文华,王一鸣,张小超,王月青.农业工程学报,第20卷第5期. 2004 * |
基于机器视觉的苗期杂草实时分割算法. 毛文华,王一鸣,张小超,王月青.农业机械学报,第36卷第1期. 2005 |
基于机器视觉的苗期杂草实时分割算法. 毛文华,王一鸣,张小超,王月青.农业机械学报,第36卷第1期. 2005 * |
应用计算机图像处理技术识别玉米苗期田间杂草的研究. 纪寿文,王荣本,陈佳娟,赵学笃.农业工程学报,第17卷第2期. 2001 |
应用计算机图像处理技术识别玉米苗期田间杂草的研究. 纪寿文,王荣本,陈佳娟,赵学笃.农业工程学报,第17卷第2期. 2001 * |
麦田杂草的实时识别系统研究. 王月青,毛文华,王一鸣.农机化研究,第6期. 2004 |
麦田杂草的实时识别系统研究. 王月青,毛文华,王一鸣.农机化研究,第6期. 2004 * |
Cited By (35)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
RU2764872C2 (en) * | 2016-05-12 | 2022-01-21 | Басф Се | Weed detection in natural environment |
US11589509B2 (en) | 2018-10-26 | 2023-02-28 | Deere & Company | Predictive machine characteristic map generation and control system |
US11178818B2 (en) | 2018-10-26 | 2021-11-23 | Deere & Company | Harvesting machine control system with fill level processing based on yield data |
US11672203B2 (en) | 2018-10-26 | 2023-06-13 | Deere & Company | Predictive map generation and control |
US11240961B2 (en) | 2018-10-26 | 2022-02-08 | Deere & Company | Controlling a harvesting machine based on a geo-spatial representation indicating where the harvesting machine is likely to reach capacity |
US11234366B2 (en) | 2019-04-10 | 2022-02-01 | Deere & Company | Image selection for machine control |
US11467605B2 (en) | 2019-04-10 | 2022-10-11 | Deere & Company | Zonal machine control |
US11829112B2 (en) | 2019-04-10 | 2023-11-28 | Deere & Company | Machine control using real-time model |
US11778945B2 (en) | 2019-04-10 | 2023-10-10 | Deere & Company | Machine control using real-time model |
US11079725B2 (en) | 2019-04-10 | 2021-08-03 | Deere & Company | Machine control using real-time model |
US11650553B2 (en) | 2019-04-10 | 2023-05-16 | Deere & Company | Machine control using real-time model |
US11957072B2 (en) | 2020-02-06 | 2024-04-16 | Deere & Company | Pre-emergence weed detection and mitigation system |
US11641800B2 (en) | 2020-02-06 | 2023-05-09 | Deere & Company | Agricultural harvesting machine with pre-emergence weed detection and mitigation system |
US11477940B2 (en) | 2020-03-26 | 2022-10-25 | Deere & Company | Mobile work machine control based on zone parameter modification |
US11675354B2 (en) | 2020-10-09 | 2023-06-13 | Deere & Company | Machine control using a predictive map |
US11864483B2 (en) | 2020-10-09 | 2024-01-09 | Deere & Company | Predictive map generation and control system |
US11635765B2 (en) | 2020-10-09 | 2023-04-25 | Deere & Company | Crop state map generation and control system |
US11711995B2 (en) | 2020-10-09 | 2023-08-01 | Deere & Company | Machine control using a predictive map |
US11727680B2 (en) | 2020-10-09 | 2023-08-15 | Deere & Company | Predictive map generation based on seeding characteristics and control |
US11592822B2 (en) | 2020-10-09 | 2023-02-28 | Deere & Company | Machine control using a predictive map |
US11825768B2 (en) | 2020-10-09 | 2023-11-28 | Deere & Company | Machine control using a predictive map |
US11474523B2 (en) | 2020-10-09 | 2022-10-18 | Deere & Company | Machine control using a predictive speed map |
US11844311B2 (en) | 2020-10-09 | 2023-12-19 | Deere & Company | Machine control using a predictive map |
US11845449B2 (en) | 2020-10-09 | 2023-12-19 | Deere & Company | Map generation and control system |
US11849672B2 (en) | 2020-10-09 | 2023-12-26 | Deere & Company | Machine control using a predictive map |
US11650587B2 (en) | 2020-10-09 | 2023-05-16 | Deere & Company | Predictive power map generation and control system |
US11871697B2 (en) | 2020-10-09 | 2024-01-16 | Deere & Company | Crop moisture map generation and control system |
US11874669B2 (en) | 2020-10-09 | 2024-01-16 | Deere & Company | Map generation and control system |
US11889787B2 (en) | 2020-10-09 | 2024-02-06 | Deere & Company | Predictive speed map generation and control system |
US11889788B2 (en) | 2020-10-09 | 2024-02-06 | Deere & Company | Predictive biomass map generation and control |
US11895948B2 (en) | 2020-10-09 | 2024-02-13 | Deere & Company | Predictive map generation and control based on soil properties |
US11927459B2 (en) | 2020-10-09 | 2024-03-12 | Deere & Company | Machine control using a predictive map |
US11946747B2 (en) | 2020-10-09 | 2024-04-02 | Deere & Company | Crop constituent map generation and control system |
US20220110251A1 (en) | 2020-10-09 | 2022-04-14 | Deere & Company | Crop moisture map generation and control system |
US11983009B2 (en) | 2020-10-09 | 2024-05-14 | Deere & Company | Map generation and control system |
Also Published As
Publication number | Publication date |
---|---|
CN1936919A (en) | 2007-03-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100416590C (en) | Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic | |
CN109115776B (en) | Color and depth information-based plug seedling growth nondestructive monitoring method and device | |
CN102564593B (en) | Plant growth condition monitoring system based on compute vision and internet of things | |
CN110163138B (en) | Method for measuring and calculating wheat tillering density based on multispectral remote sensing image of unmanned aerial vehicle | |
CN105740759B (en) | Semilate rice information decision tree classification approach based on feature extraction in multi-temporal data | |
CN110288647B (en) | Method for monitoring irrigation area of irrigation area based on high-resolution satellite data | |
CN114818909B (en) | Weed detection method and device based on crop growth characteristics | |
CN109522929A (en) | It is a kind of based on multi-source image fusion natural environment under wheat weeds recognition methods | |
CN108710766A (en) | A kind of hothouse plants liquid manure machine tune fertilizer calculation method of parameters based on growth model | |
CN113469112B (en) | Crop growth condition image identification method and system | |
CN114067207A (en) | Vegetable seedling field weed detection method based on deep learning and image processing | |
Álamo et al. | Precision techniques for improving the management of the olive groves of southern Spain | |
CN105844632A (en) | Rice plant identification and positioning method based on machine visual sense | |
Ashourloo et al. | A novel automatic method for alfalfa mapping using time series of Landsat-8 OLI data | |
Sivakumar et al. | Agroecological zones and the assessment of crop production potential | |
CN110598514B (en) | Method for monitoring plot scale crop seeding area of land reclamation project area | |
CN113011221A (en) | Crop distribution information acquisition method and device and measurement system | |
CN111967441A (en) | Crop disease analysis method based on deep learning | |
CN115456476A (en) | Territorial space planning data acquisition and analysis system based on machine vision | |
CN102339378A (en) | Method and device for automatically extracting cotton seeds | |
CN112215522A (en) | Crop growth monitoring system, method, computer equipment and storage medium | |
CN112131952A (en) | Corn seedling stage plant number information extraction based on unmanned aerial vehicle remote sensing image | |
CN108037123A (en) | A kind of hybrid paddy rice disc type sows performance parameter accurate detecting method | |
CN115909063A (en) | Medium-resolution rice extraction method and system | |
Chakraborty et al. | Early almond yield forecasting by bloom mapping using aerial imagery and deep learning |
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 |