CN109886094A - A kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device - Google Patents
A kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device Download PDFInfo
- Publication number
- CN109886094A CN109886094A CN201910016222.5A CN201910016222A CN109886094A CN 109886094 A CN109886094 A CN 109886094A CN 201910016222 A CN201910016222 A CN 201910016222A CN 109886094 A CN109886094 A CN 109886094A
- Authority
- CN
- China
- Prior art keywords
- plant
- ridge
- seedling
- obtains
- 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.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the present invention provides a kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device, obtains the Aerial Images of target area, and carry out ridge to cell identification and background segment to the Aerial Images, obtains the plant image of no background；By the plant image rotation to ridge to horizontal direction, and plant profile is searched based on preset area threshold value, obtains the plant profile of each plant；Each plant profile is traversed, and carries out skeletonizing processing respectively, obtains the stalk position of each plant；It is ranked up and clusters to stalk position based on ridge, obtain stalk position, the distance of the stalk position based on every adjacent two plants of plant judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.The growth of cereal crop seedlings seedling gesture phenotypic parameter of crop can be obtained immediately according to Aerial Images, and growth of cereal crop seedlings seedling gesture is analyzed and determined, and can the more places of multitask analyzed simultaneously, quickly positioning carried out precisely to the Seedling Characters of plant growth, it is at low cost, flexibility is high.
Description
Technical field
The present embodiments relate to technical field of agricultural information, more particularly, to a kind of acquisition point of crop growth of cereal crop seedlings seedling gesture
Analyse method and apparatus.
Background technique
As weather acute variation, land resource are reduced and population the unfavorable factors such as continues to increase and makes grain security face
Face huge challenge, increases in grain production become especially urgent.Breeding excellent variety is to realize high crop yield and keep it in stressful environmental
Under yield stability be the important channel for solving current food problem, and Cultivars just be unable to do without it is various to the crops time of infertility
The measurement and analysis of phenotypic parameter.The various aspects feelings such as genotypic and environment factor of connection crops while phenotype measurement analysis
Condition can provide valuable information to the breeding of crops, also simultaneously be to promote improved agronomic traits and improve breeding management
Effective big data support is provided, and then accelerates the process of breeding excellent variety.
Corn is to be distributed one of most wide, most, most important crops of production in the world.With the quick hair of China's economic
Exhibition increases the rigid demand of corn rapidly, and corn consumption figure in China's persistently rises to 2017 from 1.14 hundred million tons since 2000
2.21 hundred million tons.Acquisition is indispensable important of breeding excellent variety with field phenotypic data of the corn in each period is analyzed
Step.By the phenotype measuring system of high-throughput high-precision and low cost, three genotype, phenotype and environment factors are carried out
Association analysis, the urgent need that in a planned way breeding excellent variety becomes current thremmatology and phenomics are studied, the table of corn
Type character has been largely fixed the Regional suitability of kind and the stability of yield, is the weight for screening and cultivating improved seeds
Want reference standard.
The relationship research that cooperates between crop breeding phenotypic information homogenic type information is a problem, reason master
If the phenotypic information of breeding material is by being controlled at doing complicated gene and crop growth environment up to ten thousand and constantly change.
The acquisition of these phenotypic information parameters relies primarily on manual measurement at present, the disadvantage is that: worker's aging, repeats low efficiency
Property is poor, subjective error is big, so that having an impact to subsequent analysis.Therefore far from the table for meeting large area experimental plot high throughput
Type data acquisition request.Under the premise of this background, there have been correlative study and the product of some this aspects in foreign countries, are such as equipped with horizontal
The stereoscopic camera placed and be disposed vertically has carried out field measurement to multiple sorghum strains, to the high bar of field high-density planting
Crop such as sorghum carries out phenotype research；For another example construct automatic field phenotype platform, it is intended to realize in different field experiment environment
Distribution, expansible, the crop phenotype of automation analysis, be also integrated with high-throughput character phenotypic analysis algorithm based on image and
Software flow, but the above two classes platform is mainly used in the acquisition of the phenotype in fixed area, and at high cost, flexibility is poor.
Summary of the invention
The embodiment of the present invention provides a kind of a kind of crop for overcoming the above problem or at least being partially solved the above problem
Growth of cereal crop seedlings seedling gesture capturing analysis method and device.
In a first aspect, the embodiment of the present invention provides a kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method, comprising:
S1, the image for obtaining target area, and ridge is carried out to cell identification and background segment to described image, obtain no back
The plant image of scape；
S2, by the plant image rotation to ridge to horizontal direction, and based on preset area threshold value search plant profile, obtain
To the plant profile of each plant；Each plant profile is traversed, and carries out skeletonizing processing respectively, obtains the stalk position of each plant；
S3, it is ranked up and clusters to stalk position based on ridge, obtain stalk position, based on every adjacent two plants of plant
The distance of stalk position judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.
Second aspect, the embodiment of the present invention provide a kind of crop growth of cereal crop seedlings seedling gesture acquisition and analysis device, comprising:
Image collection module carries out ridge to cell for obtaining the Aerial Images of target area, and to the Aerial Images
Identification and background segment, obtain the plant image of no background；
Stalk extraction module is used for the plant image rotation to ridge to horizontal direction, and is based on preset area threshold value
Plant profile is searched, the plant profile of each plant is obtained；Each plant profile is traversed, and carries out skeletonizing processing respectively, is obtained each
The stalk position of plant；
Analysis module of being short of seedling obtains stalk position, based on every for being ranked up and being clustered to stalk position based on ridge
The distance of the stalk position of adjacent two plants of plant judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.
The third aspect, the embodiment of the present invention provides a kind of electronic equipment, including memory, processor and is stored in memory
Computer program that is upper and can running on a processor, is realized when the processor executes described program as first aspect provides
Method the step of.
Fourth aspect, the embodiment of the present invention provide a kind of non-transient computer readable storage medium, are stored thereon with calculating
Machine program is realized as provided by first aspect when the computer program is executed by processor the step of method.
The embodiment of the present invention proposes a kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device, by unmanned plane acquisition to
The Aerial Images of crop are analyzed, and are analyzed by image procossing, artificial intelligence analysis's software, it can be instant according to Aerial Images
Obtain crop growth of cereal crop seedlings seedling gesture isophenous parameter, and can the more places of multitask simultaneously analyzed, to the seedling stage property of plant growth
Shape carries out precisely quickly positioning, at low cost, flexibility is high.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the crop growth of cereal crop seedlings seedling gesture capturing analysis method schematic diagram according to the embodiment of the present invention；
Fig. 2 is the crop growth of cereal crop seedlings seedling gesture acquisition and analysis device schematic diagram according to the embodiment of the present invention；
Fig. 3 is the entity structure schematic diagram according to the electronic equipment of the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Since growth of cereal crop seedlings seedling potential analysis platform in the prior art is mainly used in the acquisition of the phenotype in fixed area, this
The Aerial Images that each embodiment acquires crop to be analyzed by unmanned plane are invented, and soft by image procossing, artificial intelligence analysis
Part is analyzed, and can obtain immediately the growth of cereal crop seedlings seedling gesture isophenous parameter of crop according to Aerial Images, and can the more places of multitask it is same
Shi Jinhang analysis.Expansion explanation and introduction will be carried out by multiple embodiments below.
Fig. 1 is a kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method provided in an embodiment of the present invention, comprising:
The image of target area is obtained, and ridge is carried out to cell identification and background segment to described image, obtains no background
Plant image；
By the plant image rotation to ridge to horizontal direction, and plant profile is searched based on preset area threshold value, obtained
The plant profile of each plant；Each plant profile is traversed, and carries out skeletonizing processing respectively, obtains the stalk position of each plant；
It is ranked up and clusters to stalk position based on ridge, obtain stalk position, the stem based on every adjacent two plants of plant
The distance of stalk position judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.
In the present embodiment, the Aerial Images that target area is obtained by unmanned plane, by constructing UAV
(Unmanned Aerial Vehicle, unmanned plane) platform and AI (Artificial Intelligence, artificial intelligence) skill
The high-throughput phenotype image capturing system of art, the image capturing system are mounted in above unmanned plane, and realize height by unmanned plane
Clear figure passes, and the high-performance computer system that high-definition image is real-time transmitted to built-in AI algorithm carries out operation；It can check at any time specified
Crops seedling stage phenotypic data information in region.
The feature that spatial resolution based on UAV platform is high, operation cost is low, environmental requirement is low and real-time is good can be quick
The high-definition image information for obtaining corn trials field is analyzed by combining the high-performance computer of AI technology that can quickly screen calculating
Valuable phenotypic data information, and then accelerate the speed of genetic improvement identification, it will also promote the hair of corn functional genomics
Exhibition.
High-throughput phenotype acquisition system based on UAV platform and AI technology can reduce the cost of phenotypic data acquisition, accelerate
There are good application prospect and economic benefit in the breeding period in Maize Genomics and phenomics research field.
Specifically, in the present embodiment, the phenotypic parameter of plant includes the size identical property of seedling, plant uniformity, is short of seedling
Whether, whole emergence rate, spacing in the rows uniformity；The individually information such as the green degree of seedling, occupied area.
In the present embodiment, by being split to Aerial Images, it is a ridge to cell with every ridge region, obtains
Plant of each ridge in cell in field, and plant is analyzed and processed, extraction phenotypic parameter and seedling number, emergence rate,
Thickness of sowing, seeding quality, coverage, leaf green grade, seedling gesture, cell uniformity and number etc. of being short of seedling.
In the present embodiment, segmentation obtains each ridge in field to after cell, passes through image procossing, pixel identification
Obtain plant phenotype parameter and seedling number, emergence rate, thickness of sowing, seeding quality, coverage, leaf green grade, seedling gesture,
Cell uniformity；When further analysis is short of seedling several, need further to obtain the distance between each adjacent two plant, to judge whether
It is short of seedling, in the present embodiment, by obtaining plant profile, plant stalk position, to be based on each adjacent two plant stalk position
Between distance, obtain the distance between each adjacent two plant.
On the basis of the above embodiments, several calculating of being short of seedling includes searching plant profile, calculating stalk position, average strain
Away from and adjacent plant between be short of seedling and count.
On the basis of the above embodiments, the image for obtaining crop growing loci, specifically includes:
The degree of overlapping for setting unmanned plane shooting interval time and front and back image, left images carries out target area more
Secondary shooting；
The image that shooting obtains is subjected to splicing and 3D is rebuild, obtains the Aerial Images in complete coverage goal region.
In the present embodiment, it before being taken photo by plane, determines and takes photo by plane region and plan course line.Course line is planned using UAV.It is setting
After having set flying height, image degree of overlapping and shooting interval, flying speed can calculate generation automatically in software.Setting front and back,
The degree of overlapping of left and right adjacent image is 80%, and sets 2s for camera shooting interval.In addition, need in view of satellite map with
It might have deviation between actual area, the region that should make to take photo by plane when planning course line is sufficiently large, to guarantee that target is completely covered in it
Region.
After obtaining shooting image, image mosaic and 3D are carried out according to preset degree of overlapping parameter and rebuild, to stitching image into
Row finishing and segmentation, obtain the Aerial Images in complete coverage goal region.
On the basis of the various embodiments described above, ridge is carried out to cell identification and background segment, specifically to the Aerial Images
Include:
Pixel segmentation is carried out to picture of taking photo by plane based on the support vector machines or random forest disaggregated model trained, identification is simultaneously
Divide non-plant pixel and plant pixel, obtains the plant image of no background.
SVM (Support Vector Machine, support vector machines) is a kind of machine learning algorithm for having supervision, is used for
Classification, regression analysis.Because SVM kernel can adapt to large-scale problem by changing scale factor, limited
Training data is concentrated, and SVM has good effect.RF (Random Forest, random forest) is a kind of ensemble learning algorithm
(Ensemble Learning Algorithm), the algorithm are based on decision Tree algorithms, Bagging algorithm and Bootstrapping
Algorithm.Sample is sampled using Bootstrapping, decision tree classification is carried out to each sample of extraction, it is comprehensive every
The classification results of one decision tree obtain final classification result by ballot.
Based on area threshold filtering, the straight-line detection of Hough transformation and method from plant row to detection to binary picture
As being handled, the weeds on each ridge are deleted, then calculate each ridge to cell plant quantity and spacing in the rows；
On the basis of the various embodiments described above, after obtaining the plant image of no background, further includes:
Ratio based on plant pixel obtains influences of plant crown coverage, and obtains each ridge to cell based on connected domain algorithm
Distance between interior plant number, and every adjacent two plant.
In the present embodiment, the calculating of Vegetation canopy coverage:
GC=Pv/Pvs* 100%
Wherein GC is vegetation coverage (%), PvFor the number of vegetation partial pixel, PvsFor pixel in field stitching image
Sum.
On the basis of the various embodiments described above, by the plant image rotation to ridge to horizontal direction, and according to preset
Area threshold is filtered compared with little profile, obtains the contour images of each plant；Each plant profile is traversed, skeletonizing is carried out to it respectively；
The central point of each profile is searched as stalk position.
On the basis of the various embodiments described above, stalk position is ranked up and is clustered to direction based on ridge, obtains stalk
Behind position, further includes:
To each ridge to the stalk position of plant carry out linear regression, the ridge being fitted is to regression straight line；By stalk
Position is projected to ridge to regression straight line, calculates separately the distance between every adjacent projections point, and will be between ridge upwards every adjacent projections point
Distance average spacing in the rows of the median as this journey plant.
Thus in the picture on the basis of the various embodiments described above, the number of being short of seedling between adjacent plant is calculated according to the following formula, and
Position the position that is short of seedling, number of being short of seedling are as follows:
MNij=round (PDij/APDi+0.5)-1
In formula, MNijFor the number of being short of seedling between+1 plant of j-th of plant in the i-th ridge and jth；PDijFor j-th of plant and
Distance between j+1 plant；APDiFor the average spacing in the rows on the i-th ridge；Round is bracket function.
On the basis of the various embodiments described above, Image Acquisition can be carried out by unmanned plane, cell phone application carries out image analysis
The image of mobile phone is passed in processing based on unmanned plane figure, and user can select the cell to be analyzed with frame, and by line of input columns, APP can
Automatically it carries out cutting and picture is passed back to cloud, carries out the statistics of each cell growth of cereal crop seedlings seedling gesture index by small Division, mobile phone.
Fig. 2 is a kind of crop growth of cereal crop seedlings seedling gesture acquisition and analysis device provided in an embodiment of the present invention, including image collection module
40, stalk extraction module 50 and analysis module 60 of being short of seedling, in which:
Image collection module 40 obtains the Aerial Images of target area, and carries out ridge to cell identification to the Aerial Images
And background segment, obtain the plant image of no background；
Stalk extraction module 50 by the plant image rotation to ridge to horizontal direction, and based on preset area threshold value search
Plant profile obtains the plant profile of each plant；Each plant profile is traversed, and carries out skeletonizing processing respectively, obtains each plant
Stalk position；
Analysis module of being short of seedling 60 is based on ridge and is ranked up and clusters to stalk position, obtains stalk position, is based on every phase
The distance of the stalk position of adjacent two plants of plant, judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.
Fig. 3 is the entity structure schematic diagram of electronic equipment provided in an embodiment of the present invention, as shown in figure 3, the electronic equipment
It may include: processor (processor) 810,820, memory communication interface (Communications Interface)
(memory) 830 and communication bus 840, wherein processor 810, communication interface 820, memory 830 pass through communication bus 840
Complete mutual communication.Processor 810 can call the meter that is stored on memory 830 and can run on processor 810
Calculation machine program, to execute the crop growth of cereal crop seedlings seedling gesture capturing analysis method of the various embodiments described above offer, for example,
S1, the Aerial Images for obtaining target area, and ridge is carried out to cell identification and background segment to the Aerial Images,
Obtain the plant image of no background；
S2, by the plant image rotation to ridge to horizontal direction, and based on preset area threshold value search plant profile, obtain
To the plant profile of each plant；Each plant profile is traversed, and carries out skeletonizing processing respectively, obtains the stalk position of each plant；
S3, it is ranked up and clusters to stalk position based on ridge, obtain stalk position, based on every adjacent two plants of plant
The distance of stalk position judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.
In addition, the logical order in above-mentioned memory 830 can be realized by way of SFU software functional unit and conduct
Independent product when selling or using, can store in a computer readable storage medium.Based on this understanding, originally
The technical solution of the inventive embodiments substantially part of the part that contributes to existing technology or the technical solution in other words
It can be embodied in the form of software products, which is stored in a storage medium, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes the present invention respectively
The all or part of the steps of a embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk
Etc. the various media that can store program code.
The embodiment of the present invention also provides a kind of non-transient computer readable storage medium, is stored thereon with computer program,
The computer program is implemented to carry out the crop growth of cereal crop seedlings seedling gesture collection analysis side of the various embodiments described above offer when being executed by processor
Method, for example,
S1, the Aerial Images for obtaining target area, and ridge is carried out to cell identification and background segment to the Aerial Images,
Obtain the plant image of no background；
S2, by the plant image rotation to ridge to horizontal direction, and based on preset area threshold value search plant profile, obtain
To the plant profile of each plant；Each plant profile is traversed, and carries out skeletonizing processing respectively, obtains the stalk position of each plant；
S3, it is ranked up and clusters to stalk position based on ridge, obtain stalk position, based on every adjacent two plants of plant
The distance of stalk position judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.
The embodiment of the present invention also provides the present embodiment and discloses a kind of computer program product, the computer program product packet
The computer program being stored in non-transient computer readable storage medium is included, the computer program includes program instruction, when
When described program instruction is computer-executed, computer is able to carry out such as above-mentioned crop growth of cereal crop seedlings seedling gesture capturing analysis method, example
Such as include:
S1, the Aerial Images for obtaining target area, and ridge is carried out to cell identification and background segment to the Aerial Images,
Obtain the plant image of no background；
S2, by the plant image rotation to ridge to horizontal direction, and based on preset area threshold value search plant profile, obtain
To the plant profile of each plant；Each plant profile is traversed, and carries out skeletonizing processing respectively, obtains the stalk position of each plant；
S3, it is ranked up and clusters to stalk position based on ridge, obtain stalk position, based on every adjacent two plants of plant
The distance of stalk position judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.
In conclusion a kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method provided in an embodiment of the present invention and device, pass through nothing
The Aerial Images of man-machine acquisition crop to be analyzed, and analyzed by image procossing, artificial intelligence analysis's software, it can be according to boat
Clap image and obtain the growth of cereal crop seedlings seedling gesture isophenous parameter of crop immediately, and can the more places of multitask analyzed simultaneously, it is raw to crop
Long Seedling Characters carry out precisely quickly positioning, at low cost, flexibility is high.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method characterized by comprising
The image of target area is obtained, and ridge is carried out to cell identification and background segment to described image, obtains the plant of no background
Strain image；
By the plant image rotation to ridge to horizontal direction, and plant profile is searched based on preset area threshold value, obtains each plant
The plant profile of strain；Each plant profile is traversed, and carries out skeletonizing processing respectively, obtains the stalk position of each plant；
It is ranked up and clusters to stalk position based on ridge, obtain stalk position, the stalk position based on every adjacent two plants of plant
The distance set judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.
2. crop growth of cereal crop seedlings seedling gesture capturing analysis method according to claim 1, which is characterized in that obtain crop growing loci
Image, specifically include:
The degree of overlapping for setting unmanned plane shooting interval time and front and back image, left images, repeatedly claps target area
It takes the photograph；
The image that shooting obtains is subjected to splicing and 3D is rebuild, obtains the Aerial Images in complete coverage goal region.
3. crop growth of cereal crop seedlings seedling gesture capturing analysis method according to claim 1, which is characterized in that and described image is carried out
Ridge is specifically included to cell identification and background segment:
The Aerial Images are handled based on the automatic division method of Hough transformation, are constituted one with the plant that each ridge is upward
A ridge carries out ridge and divides to cell to cell；
Pixel segmentation is carried out to cell to the ridge based on the random forest RF disaggregated model trained, identifies and divides non-plant
Pixel and plant pixel obtain the plant image of no background.
4. crop growth of cereal crop seedlings seedling gesture capturing analysis method according to claim 1, which is characterized in that obtain the plant of no background
After image, further includes:
Ratio based on plant pixel obtains influences of plant crown coverage, and obtains each ridge into cell based on connected domain algorithm
Distance between plant number, and every adjacent two plant.
5. crop growth of cereal crop seedlings seedling gesture capturing analysis method according to claim 1, which is characterized in that and skeletonizing is carried out respectively
Processing, obtains the stalk of each plant, specifically includes:
The skeleton intersection point in skeleton is obtained, if judgement knows skeleton number of hits not less than given threshold, by each skeleton intersection point
Equalization point is as stalk position, if judgement knows that skeleton number of hits is less than given threshold, by the bounding box center of plant profile
As stalk position.
6. crop growth of cereal crop seedlings seedling gesture capturing analysis method according to claim 1, which is characterized in that based on ridge to direction to stem
Stalk position is ranked up and clusters, after obtaining stalk position, further includes:
To each ridge to the stalk position of plant carry out linear regression, the ridge being fitted is to regression straight line；By stalk position
Projected to ridge to regression straight line, calculate separately the distance between every adjacent projections point, and by between ridge upwards every adjacent projections point away from
From average spacing in the rows of the median as this journey plant.
7. crop growth of cereal crop seedlings seedling gesture capturing analysis method according to claim 6, which is characterized in that number of being short of seedling are as follows:
MNij=round (PDij/APDi+0.5)-1
In formula, MNijFor the number of being short of seedling between+1 plant of j-th of plant in the i-th ridge and jth；PDijFor j-th of plant and jth+1
Distance between plant；APDiFor the average spacing in the rows on the i-th ridge；Round is bracket function.
8. a kind of crop growth of cereal crop seedlings seedling gesture acquisition and analysis device characterized by comprising
Image collection module carries out ridge to cell identification and back for obtaining the image of target area, and to the Aerial Images
Scape segmentation, obtains the plant image of no background；
Stalk extraction module is used for the plant image rotation to ridge to horizontal direction, and is searched based on preset area threshold value
Plant profile obtains the plant profile of each plant；Each plant profile is traversed, and carries out skeletonizing processing respectively, obtains each plant
Stalk position；
Analysis module of being short of seedling obtains stalk position, based on per adjacent for being ranked up and being clustered to stalk position based on ridge
The distance of the stalk position of two plants of plant judges whether be short of seedling between adjacent two plants of plant, and number of being short of seedling is obtained if being short of seedling.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes method as described in any one of claim 1 to 7 when executing described program
The step of.
10. a kind of non-transient computer readable storage medium, is stored thereon with computer program, which is characterized in that the calculating
The step of machine program realizes method as described in any one of claim 1 to 7 when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910016222.5A CN109886094A (en) | 2019-01-08 | 2019-01-08 | A kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910016222.5A CN109886094A (en) | 2019-01-08 | 2019-01-08 | A kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109886094A true CN109886094A (en) | 2019-06-14 |
Family
ID=66925700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910016222.5A Pending CN109886094A (en) | 2019-01-08 | 2019-01-08 | A kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109886094A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080103A (en) * | 2019-12-05 | 2020-04-28 | 中国农业科学院农业资源与农业区划研究所 | Method for automatically evaluating crop yield |
| CN112034093A (en) * | 2019-12-05 | 2020-12-04 | 陈庆梅 | Planting uniformity field detection system and method |
| CN112183329A (en) * | 2020-09-27 | 2021-01-05 | 广州极飞科技有限公司 | Reseeding information identification method and device for plants, computer equipment and storage medium |
| CN112541383A (en) * | 2020-06-12 | 2021-03-23 | 广州极飞科技有限公司 | Method and device for identifying weed area |
| CN113011221A (en) * | 2019-12-19 | 2021-06-22 | 广州极飞科技股份有限公司 | Crop distribution information acquisition method and device and measurement system |
| CN113624912A (en) * | 2020-05-08 | 2021-11-09 | 鸿富锦精密电子(天津)有限公司 | Plant growth monitoring method, monitoring device and readable storage medium |
| WO2021249560A1 (en) * | 2020-06-12 | 2021-12-16 | 广州极飞科技股份有限公司 | Crop missing detection method and detection apparatus |
| CN113807128A (en) * | 2020-06-12 | 2021-12-17 | 广州极飞科技股份有限公司 | Seedling shortage marking method and device, computer equipment and storage medium |
| CN113807135A (en) * | 2020-06-12 | 2021-12-17 | 广州极飞科技股份有限公司 | Seedling shortage area identification method, equipment and storage medium based on semantic segmentation network |
| WO2022094854A1 (en) * | 2020-11-05 | 2022-05-12 | 深圳市大疆创新科技有限公司 | Growth monitoring method for crops, and devices and storage medium |
| CN115546621A (en) * | 2022-11-28 | 2022-12-30 | 浙江托普云农科技股份有限公司 | Crop growth condition analysis method, device and application |
| CN115574786A (en) * | 2022-10-09 | 2023-01-06 | 内蒙古师范大学 | Method and system for extracting crop vegetation coverage and density based on mobile phone camera |
| CN115619286A (en) * | 2022-11-11 | 2023-01-17 | 中国农业科学院农业资源与农业区划研究所 | Method and system for evaluating sample plot quality of breeding field plot |
| CN116246225A (en) * | 2023-05-12 | 2023-06-09 | 青岛农业大学 | Crop breeding monitoring method and system based on image processing |
| CN116468657A (en) * | 2023-02-17 | 2023-07-21 | 七海行(深圳)科技有限公司 | Plant growth detection method, equipment, device and computer storage medium |
| CN117635719A (en) * | 2024-01-26 | 2024-03-01 | 浙江托普云农科技股份有限公司 | Weeding robot positioning method, system and device based on multi-sensor fusion |
| CN112614147B (en) * | 2020-12-24 | 2024-03-22 | 中国农业科学院作物科学研究所 | Crop seedling stage plant density estimation method and system based on RGB image |
| CN117974439A (en) * | 2024-04-01 | 2024-05-03 | 北京市农林科学院智能装备技术研究中心 | Plant image processing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116747A (en) * | 2013-03-11 | 2013-05-22 | 山东农业大学 | Method and system for automatically recognizing images of stalks and leaves of corns |
| CN103413172A (en) * | 2013-08-22 | 2013-11-27 | 北京农业信息技术研究中心 | Method and device for measuring number of seedlings in shortage in corn seedling stage |
| CN106971167A (en) * | 2017-03-30 | 2017-07-21 | 北京兴农丰华科技有限公司 | Crop growth analysis method and its analysis system based on unmanned aerial vehicle platform |
| CN109001125A (en) * | 2018-06-13 | 2018-12-14 | 吉林大学 | A kind of growth of cereal crop seedlings detection method and system based on high score No.1 satellite image |
-
2019
- 2019-01-08 CN CN201910016222.5A patent/CN109886094A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116747A (en) * | 2013-03-11 | 2013-05-22 | 山东农业大学 | Method and system for automatically recognizing images of stalks and leaves of corns |
| CN103413172A (en) * | 2013-08-22 | 2013-11-27 | 北京农业信息技术研究中心 | Method and device for measuring number of seedlings in shortage in corn seedling stage |
| CN106971167A (en) * | 2017-03-30 | 2017-07-21 | 北京兴农丰华科技有限公司 | Crop growth analysis method and its analysis system based on unmanned aerial vehicle platform |
| CN109001125A (en) * | 2018-06-13 | 2018-12-14 | 吉林大学 | A kind of growth of cereal crop seedlings detection method and system based on high score No.1 satellite image |
Non-Patent Citations (2)
| Title |
|---|
| 李晓鹏 等: "基于四旋翼无人机快速获取大田植株图像的方法及其应用", 《中国农业大学学报》 * |
| 王传宇 等: "基于图像拼接的苗期玉米植株缺失数量自动测量方法", 《农业工程学报》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112034093A (en) * | 2019-12-05 | 2020-12-04 | 陈庆梅 | Planting uniformity field detection system and method |
| CN111080103A (en) * | 2019-12-05 | 2020-04-28 | 中国农业科学院农业资源与农业区划研究所 | Method for automatically evaluating crop yield |
| CN113011221A (en) * | 2019-12-19 | 2021-06-22 | 广州极飞科技股份有限公司 | Crop distribution information acquisition method and device and measurement system |
| CN113624912B (en) * | 2020-05-08 | 2024-04-02 | 富联精密电子(天津)有限公司 | Plant growth monitoring method, monitoring device and readable storage medium |
| CN113624912A (en) * | 2020-05-08 | 2021-11-09 | 鸿富锦精密电子(天津)有限公司 | Plant growth monitoring method, monitoring device and readable storage medium |
| CN112541383A (en) * | 2020-06-12 | 2021-03-23 | 广州极飞科技有限公司 | Method and device for identifying weed area |
| WO2021249560A1 (en) * | 2020-06-12 | 2021-12-16 | 广州极飞科技股份有限公司 | Crop missing detection method and detection apparatus |
| CN113807128A (en) * | 2020-06-12 | 2021-12-17 | 广州极飞科技股份有限公司 | Seedling shortage marking method and device, computer equipment and storage medium |
| CN113807135A (en) * | 2020-06-12 | 2021-12-17 | 广州极飞科技股份有限公司 | Seedling shortage area identification method, equipment and storage medium based on semantic segmentation network |
| CN112541383B (en) * | 2020-06-12 | 2021-12-28 | 广州极飞科技股份有限公司 | Method and device for identifying weed area |
| CN113807128B (en) * | 2020-06-12 | 2022-09-13 | 广州极飞科技股份有限公司 | Seedling shortage marking method and device, computer equipment and storage medium |
| CN112183329A (en) * | 2020-09-27 | 2021-01-05 | 广州极飞科技有限公司 | Reseeding information identification method and device for plants, computer equipment and storage medium |
| WO2022094854A1 (en) * | 2020-11-05 | 2022-05-12 | 深圳市大疆创新科技有限公司 | Growth monitoring method for crops, and devices and storage medium |
| CN112614147B (en) * | 2020-12-24 | 2024-03-22 | 中国农业科学院作物科学研究所 | Crop seedling stage plant density estimation method and system based on RGB image |
| CN115574786A (en) * | 2022-10-09 | 2023-01-06 | 内蒙古师范大学 | Method and system for extracting crop vegetation coverage and density based on mobile phone camera |
| CN115619286A (en) * | 2022-11-11 | 2023-01-17 | 中国农业科学院农业资源与农业区划研究所 | Method and system for evaluating sample plot quality of breeding field plot |
| CN115619286B (en) * | 2022-11-11 | 2023-10-03 | 中国农业科学院农业资源与农业区划研究所 | Method and system for evaluating quality of sample plot of breeding field district |
| CN115546621A (en) * | 2022-11-28 | 2022-12-30 | 浙江托普云农科技股份有限公司 | Crop growth condition analysis method, device and application |
| CN116468657A (en) * | 2023-02-17 | 2023-07-21 | 七海行(深圳)科技有限公司 | Plant growth detection method, equipment, device and computer storage medium |
| CN116246225A (en) * | 2023-05-12 | 2023-06-09 | 青岛农业大学 | Crop breeding monitoring method and system based on image processing |
| CN117635719A (en) * | 2024-01-26 | 2024-03-01 | 浙江托普云农科技股份有限公司 | Weeding robot positioning method, system and device based on multi-sensor fusion |
| CN117635719B (en) * | 2024-01-26 | 2024-04-16 | 浙江托普云农科技股份有限公司 | Weeding robot positioning method, system and device based on multi-sensor fusion |
| CN117974439A (en) * | 2024-04-01 | 2024-05-03 | 北京市农林科学院智能装备技术研究中心 | Plant image processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886094A (en) | A kind of crop growth of cereal crop seedlings seedling gesture capturing analysis method and device | |
| Tetila et al. | Automatic recognition of soybean leaf diseases using UAV images and deep convolutional neural networks | |
| US10977494B2 (en) | Recognition of weed in a natural environment | |
| Xiong et al. | Visual detection of green mangoes by an unmanned aerial vehicle in orchards based on a deep learning method | |
| Tedesco-Oliveira et al. | Convolutional neural networks in predicting cotton yield from images of commercial fields | |
| Barbosa et al. | UAV-based coffee yield prediction utilizing feature selection and deep learning | |
| Zhang et al. | EPSA-YOLO-V5s: A novel method for detecting the survival rate of rapeseed in a plant factory based on multiple guarantee mechanisms | |
| CN113011221A (en) | Crop distribution information acquisition method and device and measurement system | |
| Selvi et al. | Weed detection in agricultural fields using deep learning process | |
| Díaz et al. | Grapevine buds detection and localization in 3D space based on structure from motion and 2D image classification | |
| Tan et al. | Rapid recognition of field-grown wheat spikes based on a superpixel segmentation algorithm using digital images | |
| JP2018005467A (en) | Farmwork plan support device and farmwork plan support method | |
| CN115861686A (en) | Litchi key growth period identification and detection method and system based on edge deep learning | |
| Lyu et al. | Development of phenotyping system using low altitude UAV imagery and deep learning | |
| Gao et al. | Maize seedling information extraction from UAV images based on semi-automatic sample generation and Mask R-CNN model | |
| Lu et al. | Citrus green fruit detection via improved feature network extraction | |
| Mortensen et al. | The oil radish growth dataset for semantic segmentation and yield estimation | |
| CN109657540A (en) | Withered tree localization method and system | |
| CN113313692A (en) | Automatic banana young plant identification and counting method based on aerial visible light image | |
| Zhang et al. | YOLO-VOLO-LS: a novel method for variety identification of early lettuce seedlings | |
| CN117197595A (en) | Fruit tree growth period identification method, device and management platform based on edge calculation | |
| CN113435345A (en) | Growth stage determination method and device, agricultural system, equipment and storage medium | |
| Valente et al. | Fast classification of large germinated fields via high-resolution UAV imagery | |
| Zhang et al. | Automatic counting of lettuce using an improved YOLOv5s with multiple lightweight strategies | |
| Ban et al. | A lightweight model based on YOLOv8n in wheat spike detection |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190614 |
|
| RJ01 | Rejection of invention patent application after publication |