CN103793686A - Method for early-prediction of fruit tree yield - Google Patents
Method for early-prediction of fruit tree yield Download PDFInfo
- Publication number
- CN103793686A CN103793686A CN201410020528.5A CN201410020528A CN103793686A CN 103793686 A CN103793686 A CN 103793686A CN 201410020528 A CN201410020528 A CN 201410020528A CN 103793686 A CN103793686 A CN 103793686A
- Authority
- CN
- China
- Prior art keywords
- fruit
- image
- region
- area
- leaf
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a method for early-prediction of the fruit tree yield. The method comprises the steps that S1, according to the requirement for fruit ranch management, the image obtaining time is determined and images of a fruit tree which is ready to be predicated in yield are collected by a portable image collecting device in a certain time under a certain image collecting condition; S2, fruit zone identification is conducted according to image characteristics; S3, leaf zone identification is conducted according to the image characteristics; S4, characteristics of a fruit zone and a leaf zone are extracted to serve as fruit tree crown characteristics; S5, the fruit tree crown characteristics are input into an artificial neural network yield measuring model for predicting the yield of the fruit tree. According to the method, the image processing and identification technology is effectively combined with the artificial intelligence technology, the defect that only the image processing and identification technology is used for prediction is overcome, and therefore prediction can be accurately conducted on apples in the fruit ranch in an early period.
Description
Technical field
The present invention relates to agriculture electric powder prediction, specifically, relate to a kind of method of output of the fruit tree early prediction.
Background technology
Apple is to eat in the world one of fruit the most widely, and world's apple annual production is about 3,200 ten thousand tons.China is maximum in the world apple production state and country of consumption, and cultivated area of the apple and the more than 40% of output Jun Zhan world total amount occupy critical role in world's Apple Industry.In order to estimate apple production before apple results, required various human and material resources resources when arranging various results, conventional method is that artificial extracting part is divided fruit tree at present, goes out apple quantity by a number, then roughly estimates output.This kind of manual method is time-consuming, effort and precision not high.In the research of apple production early prediction, Computerized Information Processing Tech becomes one of focus of current research as a kind of means.Because color, shape, the Texture eigenvalue of apple are different from the branches and leaves on tree, current research process is mainly to utilize these feature combining image treatment technologies to identify apple, estimation output.But the accurate identification that realizes setting apple carrys out forecast production, solves overlapping apple and the leaf problem of blocking to apple, and only relying on image processing techniques is a very large challenge.
Summary of the invention
In order to solve problems of the prior art, the object of this invention is to provide the method for output of the fruit tree early prediction in a kind of orchard, realize apple production is predicted more accurately.
In order to realize the object of the invention, the invention provides a kind of method of output of the fruit tree early prediction, comprise step:
S1: need to determine the Image Acquisition time according to orchard management, in certain image acquisition condition, adopt portable image capture equipment to gather the image of product fruit tree to be measured in definite time;
S2: carry out the identification of fruit region according to feature of image;
S3: carry out the identification of leaf region according to feature of image;
S4: extract the feature in fruit region and leaf region as top fruit sprayer feature;
S5: top fruit sprayer feature input artificial neural network is surveyed to product model the output of fruit tree is predicted.
Further, described step S1 takes fruit tree one-sided image at specific fruit growth period, and the whole tree crown of fruit tree should be contained in taken the photograph image, when image taking, after tree, places white curtain as a setting.
Further, described step S2 comprises step:
S21: the color characteristic of different objects, shape facility and textural characteristics in analysis image.
S22: according to the analysis of step 1, draw the qualifications that can identify fruit region from image;
S23: obtain fruit area image according to the qualifications in step 2.
Further, described step S3 comprises step:
S31: deduct fruit area image and obtain leaf region initial pictures from fruit tree image;
S32: remove the background in the initial pictures of leaf region, obtain leaf region without background image;
S33: remove leaf region without the limb in background image.
Further, described step S31 is specially: the R value of pixel in fruit area image is greater than to 0, in apple tree image, corresponding pixel R, G, B value is set to 0, obtain the initial pictures in leaf region; Described step S32 is specially: utilize G, B component in RGB color model, and the G-B value of each pixel in computed image, difference is less than 10 pixel and belongs to background area, removes background with this; Described step S33 is specially: by RGB color space conversion, to HSI space, the H value of leaf and the H value of limb have bigger difference, adopts OSTU automatic threshold segmentation algorithm, is partitioned into leaf region.
Further, described step S4 comprises step:
S41: the computed image total area;
S42: statistics fruit region number:
S43: calculate fruit region proportion;
S44: calculate small size fruit region proportion;
S45: calculate leaf region proportion;
S46: set fruit growth period parameter value.
Wherein, in described step S41: total pixel count of statistical picture, as its area.
Wherein, in described step S42: in fruit area image, comprise several fruit regions (the corresponding fruit in one of them fruit region or a fruit bunch), the fruit region number in image is counted, concrete steps are as follows:
Step 1: by fruit area image binaryzation;
Step 2: adopt neighborhood method mark fruit region;
Step 3: statistics obtains total number in fruit region.
Wherein, in described step S43: in the bianry image of fruit region, add up non-zero number of pixels, as the fruit region total area; Proportion=fruit region, the fruit region total area/total image area.
Wherein, in described step S44: the total area/total image area of proportion=small size fruit region, small size fruit region; Described small size fruit region is 0.2% the fruit region that fruit region area is less than total image area.
Wherein, described step S45 is specially: by leaf area image binaryzation; In bianry image, add up non-zero number of pixels, as leaf region area; Leaf region proportion=leaf region area/total image area.
Wherein, in described step S46, fruit tree growth period parameters value is surveyed the settings setting of producing growth period in model according to artificial neural network.
Further, the foundation of described step S5 using the tree crown feature of extracting from fruit tree image as estimation output of the fruit tree; Input take the number in fruit region, fruit region proportion, small size fruit region proportion, leaf region proportion and fruit growth period as Artificial Neural Network Prediction Model, the forecast production of fruit tree (kilogram/tree) be output.
Beneficial effect of the present invention is:
The invention provides apple early yield Forecasting Methodology in a kind of orchard, the method is utilized effective combination of image processing and recognition technology and artificial intelligence technology, make up and utilized merely the deficiency that image is processed and recognition technology is predicted, thereby can predict the output of apple in orchard more in early days.This method, compares Forecasting Methodology existing in current orchard, more objective, more efficient.
Accompanying drawing explanation
Fig. 1 is output of the fruit tree prediction process flow diagram described in the embodiment of the present invention;
Fig. 2 is leaf region identification process figure described in the embodiment of the present invention;
Fig. 3 is tree crown feature extraction process flow diagram described in the embodiment of the present invention;
Fig. 4 is apple early yield forecast model schematic diagram described in the embodiment of the present invention.
Embodiment
Following examples are used for illustrating the present invention, but are not used for limiting the scope of the invention.
Embodiment 1
Take loud, high-pitched sound apple tree in orchard as example, survey product process of the present invention is described.In the present embodiment, orchard is positioned at the Klein Altendorf of Univ Bonn Germany experiment orchard, and in embodiment, related fruit tree is the apple tree of label 170, and in orchard, embark on journey in apple tree north and south, and fruit tree west is subject to solar radiation abundance in the east.No. 170 apple trees, after its physiological fallen fruit phase completes approximately 1.5 months, are surveyed to product, the following step of process need:
S1: obtain product fruit tree image to be measured
Step 1: determine the Image Acquisition time, in the present embodiment, image acquisition was on August 19th, 2010.
Step 2: when Image Acquisition, avoid strong illumination, place long 2 meters after tree, high 1.5 off-white painting cloth curtains as a setting.Shooting angle is apart from 1.7 meters, fruit tree, 1.2 meters of heights off the ground, and perpendicular to planting fruit trees direction.
Step 3: use Cannon PowerShot SX110ISS digital camera, automatically taking fruit tree image in focusing situation, picture size is 2112 × 2816.
S2: fruit region identifying processing in image, concrete steps are as follows:
Step 1: read in original image, dwindle its size to 512 × 683.
Step 2: in RGB color space, adopt the wave characteristic that cuts open each color component of different objects in the image of mentioning in line-plot method analytical procedure two.
Step 3: according to the analysis of step 2, adopt color component difference analysis method, draw the condition in the fruit region of defining in image.The pixel that meets two conditions of the poor G-R<20 of the poor R-B>40 of reddish blue and red green all belongs to fruit region, and R, G, the B value of non-fruit area pixel all set to 0.
Step 4: transfer image to gray level image, adopt 3 × 3 median filter removal isolated point noise.
Step 5: image is carried out to opening operation processing, and structural element adopts disc structure, and its radius is 2, and the profile in each region in smoothed image, disconnects narrow connection.
Step 6: the apple region obtaining after step 5 is processed corresponds in original image, obtains the RGB image in apple region.
S3: leaf region identification in image, its concrete scheme as shown in Figure 2.
S31: the R value of pixel in fruit area image is greater than to 0, in apple tree image, corresponding pixel R, G, B value is set to 0, obtain the initial pictures in leaf region.
S32: the fluctuation situation of each color component of white background and tree in the initial pictures of RGB color space analysis leaf region, if the turquoise difference G-B<10 of pixel, judge that pixel belongs to white background district, the R of pixel, G, B value are set to 0 respectively, thus obtain leaf region without background image.
S33: utilize the conversion formula of RGB color space to HIS color space, obtain the HIS figure of leaf region without background image.
S34: undulatory property and the histogram of H component, I component and the S component of analysis image.
S35: according to the analysis of step 4, utilize OSTU automatic threshold method, the H component of cutting apart image, can be divided into two parts by image: trunk and branch region and leaf region, by trunk and branch in leaf region R, G, the B value without the pixel value of the part in background image put O.
S4: extract the feature of apple tree tree crown, its concrete scheme as shown in Figure 3.
S41: total number of pixels in statistical picture, as the total area of image, its size is: 512 × 683=349696.
S42: in fruit area image, comprise several apple regions, the corresponding apple in one of them apple region or an apple bunch, count the fruit region number in image, and concrete steps are as follows:
Step 1: by fruit area image binaryzation, binary-state threshold is set to 0;
Step 2: adopt the object in 8 neighborhood method mark bianry images;
Step 3: the number of statistics tagged object is 65, and it is as total number in fruit region.
S43: in the bianry image of fruit region, adding up non-zero number of pixels is 9408, and the fruit region total area is 9408.Proportion=fruit region, the fruit region total area 9408/ total image area 349696=0.0269.
S44: the summation of the area in the apple region of an only corresponding apple in computed image, concrete steps are as follows:
Step 1: total image area 349696 × 0.2% ≈ 700, are less than 700 region and are small size apple region in apple area image;
Step 2: calculate in S42 the area of each object in marking image, area is less than to 700 area and adds up, obtain the total area 7785 in small size apple region.
Step 3: the total area 7785/ total image area 349696 ≈ 0.0223 in proportion=small size fruit region, fruit region.
S45: calculate the total area in leaf region, concrete steps are as follows:
Step 1: by leaf area image binaryzation, binary-state threshold is set to 0.
Step 2: in bianry image, add up non-zero number of pixels 216673, leaf region area is 216673.
Step 3: proportion=leaf region, leaf region total area 216673/ total image area 349696 ≈ 0.6196.
S46: fruit growth period parameter value is made as 0.5.
S5: utilize BP neural network apple to survey in early days product model and survey product, as shown in Figure 4.
By fruit region number 65, fruit region proportion 0.0269, small size fruit region proportion 0.0223, leaf region proportion 0.6196 and fruit growth input model in period 0.5, obtaining being output as 22.09, is 22.09 kilograms to the forecast production of this apple tree.Wherein BP neural network apple early yield forecast model can be predicted the fruit tree output in three periods: when fruit physiology shedding finishes, fruit physiology shedding finished after 1.5 months, first 2 weeks of fruit harvest.Three parameter values corresponding to fruit tree growth phase are respectively 0,0.5,1; This model is the image in these three periods according to 150 fruit trees in orchard in 2009, take the fruit region number in every fruit tree image in each period, fruit region proportion, small size fruit region proportion, leaf region proportion and fruit growth period as input, train and obtain with the fruit tree actual output of every (kilogram/tree) target.This model is three-layer neural network structure (input layer, hidden layer, output layer), 5 neurons of input layer, 1 neuron of output layer, middle layer neuron number 11.Middle layer neural transferring function adopts tangent sigmoid function, and output layer neural transferring function adopts line shape function.
Although above the present invention is described in detail with a general description of the specific embodiments, on basis of the present invention, can make some modifications or improvements it, this will be apparent to those skilled in the art.Therefore, these modifications or improvements without departing from theon the basis of the spirit of the present invention, all belong to the scope of protection of present invention.
Claims (10)
1. a method for output of the fruit tree early prediction, is characterized in that, comprises step:
S1: need to determine the Image Acquisition time according to orchard management, in certain image acquisition condition, adopt portable image capture equipment to gather the image of product fruit tree to be measured in definite time;
S2: carry out the identification of fruit region according to feature of image;
S3: carry out the identification of leaf region according to feature of image;
S4: extract the feature in fruit region and leaf region as top fruit sprayer feature;
S5: top fruit sprayer feature input artificial neural network is surveyed to product model the output of fruit tree is predicted.
2. method according to claim 1, is characterized in that, described step S1 takes fruit tree one-sided image at specific fruit growth period, and the whole tree crown of fruit tree should be contained in taken the photograph image, when image taking, after tree, places white curtain as a setting.
3. method according to claim 1, is characterized in that, described step S3 comprises step:
S31: deduct fruit area image and obtain leaf region initial pictures from fruit tree image;
S32: remove the background in the initial pictures of leaf region, obtain leaf region without background image;
S33: remove leaf region without the limb in background image.
4. method according to claim 3, is characterized in that, described step S31 is specially: the R value of pixel in fruit area image is greater than to 0, in apple tree image, corresponding pixel R, G, B value is set to 0, obtain the initial pictures in leaf region; Described step S32 is specially: utilize G, B component in RGB color model, and the G-B value of each pixel in computed image, difference is less than 10 pixel and belongs to background area, removes background with this; Described step S33 is specially: by RGB color space conversion, to HSI space, the H value of leaf and the H value of limb have bigger difference, adopts OSTU automatic threshold segmentation algorithm, is partitioned into leaf region.
5. method according to claim 1, is characterized in that, described step S4 comprises step:
S41: the computed image total area;
S42: statistics fruit region number:
S43: calculate fruit region proportion;
S44: calculate small size fruit region proportion;
S45: calculate leaf region proportion;
S46: set fruit growth period parameter value.
6. method according to claim 5, is characterized in that, in described step S43: the total area/total image area of proportion=fruit region, fruit region.
7. method according to claim 5, is characterized in that, in described step S44: the total area/total image area of proportion=small size fruit region, small size fruit region; Described small size fruit region is 0.2% the fruit region that fruit region area is less than total image area.
8. method according to claim 5, is characterized in that, described step S45 is specially: by leaf area image binaryzation; In bianry image, add up non-zero number of pixels, as leaf region area; Leaf region proportion=leaf region area/total image area.
9. method according to claim 5, is characterized in that, in described step S46, fruit tree growth period parameters value is surveyed the settings setting of producing growth period in model according to artificial neural network.
10. method according to claim 1, is characterized in that, the foundation of described step S5 using the tree crown feature of extracting from fruit tree image as estimation output of the fruit tree; Input take the number in fruit region, fruit region proportion, small size fruit region proportion, leaf region proportion and fruit growth period as Artificial Neural Network Prediction Model, the forecast production of fruit tree is output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410020528.5A CN103793686B (en) | 2014-01-16 | 2014-01-16 | A kind of method of output of the fruit tree early prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410020528.5A CN103793686B (en) | 2014-01-16 | 2014-01-16 | A kind of method of output of the fruit tree early prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103793686A true CN103793686A (en) | 2014-05-14 |
| CN103793686B CN103793686B (en) | 2017-12-15 |
Family
ID=50669331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410020528.5A Expired - Fee Related CN103793686B (en) | 2014-01-16 | 2014-01-16 | A kind of method of output of the fruit tree early prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103793686B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881626A (en) * | 2015-01-19 | 2015-09-02 | 新疆农业大学 | Recognition method for fruit of fruit tree |
| CN106570770A (en) * | 2016-11-11 | 2017-04-19 | 山东农业大学 | Orchard water and fertilizer integration top-dressing amount accurate estimation method |
| CN107092891A (en) * | 2017-04-25 | 2017-08-25 | 无锡中科智能农业发展有限责任公司 | A kind of paddy rice yield estimation system and method based on machine vision technique |
| CN107832655A (en) * | 2017-02-21 | 2018-03-23 | 石河子大学 | A kind of take photo by plane system and output of cotton estimating and measuring method based on unmanned plane imaging near the ground |
| CN108053078A (en) * | 2017-12-28 | 2018-05-18 | 深圳春沐源控股有限公司 | A kind of production prediction method, server and computer readable storage medium |
| CN109843034A (en) * | 2016-10-19 | 2019-06-04 | 巴斯夫农化商标有限公司 | Production forecast for wheatland |
| CN109937733A (en) * | 2019-03-28 | 2019-06-28 | 北京农业智能装备技术研究中心 | A kind of orchard yield automatic measurement mechanism |
| CN111311573A (en) * | 2020-02-12 | 2020-06-19 | 贵州理工学院 | Branch determination method and device and electronic equipment |
| CN111918547A (en) * | 2018-03-23 | 2020-11-10 | 日本电气方案创新株式会社 | Crown identification device, identification method, program, and recording medium |
| CN113673279A (en) * | 2020-05-14 | 2021-11-19 | 明谷农业生技股份有限公司 | Plant growth identification method and system |
| CN114155526A (en) * | 2021-11-09 | 2022-03-08 | 中国农业大学 | Tomato fruit growth prediction method, device, equipment and product |
| US11462008B2 (en) | 2017-11-15 | 2022-10-04 | Nec Solution Innovators, Ltd. | Device for collecting breeding data in farm field, device for analyzing feature in breeding, method for collecting breeding data in farm field, program, and recording medium |
| CN115238964A (en) * | 2022-06-28 | 2022-10-25 | 安徽未来种业有限公司 | Rice harvest prediction evaluation method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102954816A (en) * | 2012-01-13 | 2013-03-06 | 北京盈胜泰科技术有限公司 | Crop growth monitoring method |
| CN103310218A (en) * | 2013-05-21 | 2013-09-18 | 常州大学 | Precise recognition method of overlapped shielded fruits |
-
2014
- 2014-01-16 CN CN201410020528.5A patent/CN103793686B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102954816A (en) * | 2012-01-13 | 2013-03-06 | 北京盈胜泰科技术有限公司 | Crop growth monitoring method |
| CN103310218A (en) * | 2013-05-21 | 2013-09-18 | 常州大学 | Precise recognition method of overlapped shielded fruits |
Non-Patent Citations (6)
| Title |
|---|
| A.B. PAYNE等: "Estimation of mango crop yield using image analysis – Segmentation", 《COMPUTERS AND ELECTRONICS IN AGRICULTURE》 * |
| D. STAJNKO等: "Modelling Apple Fruit Yield Using Image Analysis for Fruit Colour,", 《EUROPEAN JOURNAL OF HORTICULTURAL SCIENCE 》 * |
| RONG ZHOU等: "Using colour features of cv. ‘Gala’ apple fruits in an orchard in image processing to predict yield", 《PRECISION AGRICULTURE》 * |
| ROZMAN ČRTOMIR等: "Application of Neural Networks and Image Visualization for Early Forecast of Apple Yield", 《ERWERBS-OBSTBAU》 * |
| 李莹莹等: "基于matlab的苹果树枝图像分割方法研究", 《科学技术与工程》 * |
| 蔡健荣等: "自然场景下成熟水果的计算机视觉识别", 《农业机械学报》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881626B (en) * | 2015-01-19 | 2017-12-29 | 新疆农业大学 | The recognition methods of Tree Fruit |
| CN104881626A (en) * | 2015-01-19 | 2015-09-02 | 新疆农业大学 | Recognition method for fruit of fruit tree |
| CN109843034A (en) * | 2016-10-19 | 2019-06-04 | 巴斯夫农化商标有限公司 | Production forecast for wheatland |
| CN109843034B (en) * | 2016-10-19 | 2022-08-23 | 巴斯夫农化商标有限公司 | Yield prediction for grain fields |
| CN106570770B (en) * | 2016-11-11 | 2020-12-18 | 山东农业大学 | Orchard water and fertilizer integrated topdressing amount accurate estimation method |
| CN106570770A (en) * | 2016-11-11 | 2017-04-19 | 山东农业大学 | Orchard water and fertilizer integration top-dressing amount accurate estimation method |
| CN107832655A (en) * | 2017-02-21 | 2018-03-23 | 石河子大学 | A kind of take photo by plane system and output of cotton estimating and measuring method based on unmanned plane imaging near the ground |
| CN107092891A (en) * | 2017-04-25 | 2017-08-25 | 无锡中科智能农业发展有限责任公司 | A kind of paddy rice yield estimation system and method based on machine vision technique |
| US11462008B2 (en) | 2017-11-15 | 2022-10-04 | Nec Solution Innovators, Ltd. | Device for collecting breeding data in farm field, device for analyzing feature in breeding, method for collecting breeding data in farm field, program, and recording medium |
| CN108053078A (en) * | 2017-12-28 | 2018-05-18 | 深圳春沐源控股有限公司 | A kind of production prediction method, server and computer readable storage medium |
| CN111918547A (en) * | 2018-03-23 | 2020-11-10 | 日本电气方案创新株式会社 | Crown identification device, identification method, program, and recording medium |
| CN111918547B (en) * | 2018-03-23 | 2022-06-07 | 日本电气方案创新株式会社 | Crown recognition device, crown recognition method, program, and recording medium |
| US11594020B2 (en) | 2018-03-23 | 2023-02-28 | Nec Solution Innovators, Ltd. | Crown identification device, identification method, program, and recording medium |
| CN109937733A (en) * | 2019-03-28 | 2019-06-28 | 北京农业智能装备技术研究中心 | A kind of orchard yield automatic measurement mechanism |
| CN111311573A (en) * | 2020-02-12 | 2020-06-19 | 贵州理工学院 | Branch determination method and device and electronic equipment |
| CN111311573B (en) * | 2020-02-12 | 2024-01-30 | 贵州理工学院 | Branch determination method and device and electronic equipment |
| CN113673279A (en) * | 2020-05-14 | 2021-11-19 | 明谷农业生技股份有限公司 | Plant growth identification method and system |
| CN114155526A (en) * | 2021-11-09 | 2022-03-08 | 中国农业大学 | Tomato fruit growth prediction method, device, equipment and product |
| CN114155526B (en) * | 2021-11-09 | 2024-04-16 | 中国农业大学 | Tomato fruit growth prediction method, device, equipment and product |
| CN115238964A (en) * | 2022-06-28 | 2022-10-25 | 安徽未来种业有限公司 | Rice harvest prediction evaluation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103793686B (en) | 2017-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103793686B (en) | A kind of method of output of the fruit tree early prediction | |
| Stajnko et al. | Estimation of number and diameter of apple fruits in an orchard during the growing season by thermal imaging | |
| Payne et al. | Estimation of mango crop yield using image analysis–segmentation method | |
| Aquino et al. | Automated early yield prediction in vineyards from on-the-go image acquisition | |
| Skovsen et al. | The GrassClover image dataset for semantic and hierarchical species understanding in agriculture | |
| Zhou et al. | Using colour features of cv.‘Gala’apple fruits in an orchard in image processing to predict yield | |
| Bai et al. | Crop segmentation from images by morphology modeling in the CIE L* a* b* color space | |
| Zhou et al. | Strawberry maturity classification from UAV and near-ground imaging using deep learning | |
| CN105718945B (en) | Apple picking robot night image recognition method based on watershed and neural network | |
| Kamlapurkar | Detection of plant leaf disease using image processing approach | |
| Sarkate et al. | Application of computer vision and color image segmentation for yield prediction precision | |
| Malik et al. | Detection and counting of on-tree citrus fruit for crop yield estimation | |
| Wang et al. | DeepPhenology: Estimation of apple flower phenology distributions based on deep learning | |
| Zhou et al. | Early detection and continuous quantization of plant disease using template matching and support vector machine algorithms | |
| JP2018161058A (en) | Plant growth state evaluation method, plant growth state evaluation program, plant growth state evaluation device and plant monitoring system | |
| Han et al. | Real-time detection of rice phenology through convolutional neural network using handheld camera images | |
| WO2023116454A1 (en) | Method and apparatus for identifying area having potential high risk of locust plagues, and device and storage medium | |
| CN111199192A (en) | Method for detecting integral maturity of field red globe grapes by adopting parallel line sampling | |
| CN102542560A (en) | Method for automatically detecting density of rice after transplantation | |
| Gao et al. | Recognition and Detection of Greenhouse Tomatoes in Complex Environment. | |
| CN110399785B (en) | Method for detecting leaf occlusion based on deep learning and traditional algorithm | |
| Victorino et al. | Grapevine yield prediction using image analysis-improving the estimation of non-visible bunches | |
| CN116189076A (en) | Observation and identification system and method for bird observation station | |
| CN115147835A (en) | Pineapple maturity detection method in natural orchard scene based on improved RetinaNet | |
| ES2470065A1 (en) | System and procedure to automatically determine the number of flowers of an inflorescence (Machine-translation by Google Translate, not legally binding) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171215 Termination date: 20190116 |