AU2021101996A4 - Nutrient deficiency stress detection and prediction in corn fields from aerial images using machine learning - Google Patents
Nutrient deficiency stress detection and prediction in corn fields from aerial images using machine learning Download PDFInfo
- Publication number
- AU2021101996A4 AU2021101996A4 AU2021101996A AU2021101996A AU2021101996A4 AU 2021101996 A4 AU2021101996 A4 AU 2021101996A4 AU 2021101996 A AU2021101996 A AU 2021101996A AU 2021101996 A AU2021101996 A AU 2021101996A AU 2021101996 A4 AU2021101996 A4 AU 2021101996A4
- Authority
- AU
- Australia
- Prior art keywords
- nutrient deficiency
- plant
- nutrient
- aerial images
- machine learning
- 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.)
- Ceased
Links
- 235000018343 nutrient deficiency Nutrition 0.000 title claims abstract description 55
- 238000010801 machine learning Methods 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 title claims abstract description 18
- 240000008042 Zea mays Species 0.000 title claims abstract description 13
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 title claims abstract description 13
- 235000002017 Zea mays subsp mays Nutrition 0.000 title claims abstract description 13
- 235000005822 corn Nutrition 0.000 title claims abstract description 13
- 241000196324 Embryophyta Species 0.000 claims abstract description 75
- 208000024891 symptom Diseases 0.000 claims abstract description 33
- 238000012706 support-vector machine Methods 0.000 claims abstract description 21
- 241001057636 Dracaena deremensis Species 0.000 claims abstract description 20
- 230000012010 growth Effects 0.000 claims abstract description 14
- 235000015097 nutrients Nutrition 0.000 claims abstract description 11
- 238000004383 yellowing Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 26
- 230000007812 deficiency Effects 0.000 claims description 23
- 238000013459 approach Methods 0.000 claims description 21
- 239000002689 soil Substances 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 5
- 244000038559 crop plants Species 0.000 claims description 5
- 235000021049 nutrient content Nutrition 0.000 claims description 5
- 238000011002 quantification Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 229910000906 Bronze Inorganic materials 0.000 claims description 3
- 239000010974 bronze Substances 0.000 claims description 3
- KUNSUQLRTQLHQQ-UHFFFAOYSA-N copper tin Chemical compound [Cu].[Sn] KUNSUQLRTQLHQQ-UHFFFAOYSA-N 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 abstract description 5
- 238000011160 research Methods 0.000 abstract description 4
- 230000011218 segmentation Effects 0.000 abstract description 4
- 230000007423 decrease Effects 0.000 abstract description 3
- 208000037824 growth disorder Diseases 0.000 abstract description 3
- 210000003462 vein Anatomy 0.000 abstract description 3
- YYXHRUSBEPGBCD-UHFFFAOYSA-N azanylidyneiron Chemical compound [N].[Fe] YYXHRUSBEPGBCD-UHFFFAOYSA-N 0.000 abstract description 2
- ZFXVRMSLJDYJCH-UHFFFAOYSA-N calcium magnesium Chemical compound [Mg].[Ca] ZFXVRMSLJDYJCH-UHFFFAOYSA-N 0.000 abstract description 2
- 230000006378 damage Effects 0.000 abstract description 2
- 238000003745 diagnosis Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 abstract description 2
- PZDFRGGOXGETNN-UHFFFAOYSA-N phosphane;potassium Chemical compound P.[K] PZDFRGGOXGETNN-UHFFFAOYSA-N 0.000 abstract description 2
- 238000005070 sampling Methods 0.000 abstract description 2
- 230000036435 stunted growth Effects 0.000 abstract description 2
- 239000000126 substance Substances 0.000 abstract 2
- 230000007613 environmental effect Effects 0.000 abstract 1
- 238000012423 maintenance Methods 0.000 abstract 1
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 10
- 230000008859 change Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 229910052757 nitrogen Inorganic materials 0.000 description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 239000003337 fertilizer Substances 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- ZOXJGFHDIHLPTG-UHFFFAOYSA-N Boron Chemical compound [B] ZOXJGFHDIHLPTG-UHFFFAOYSA-N 0.000 description 3
- 208000002720 Malnutrition Diseases 0.000 description 3
- 229910052796 boron Inorganic materials 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 2
- 206010006956 Calcium deficiency Diseases 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 description 2
- ZOKXTWBITQBERF-UHFFFAOYSA-N Molybdenum Chemical compound [Mo] ZOKXTWBITQBERF-UHFFFAOYSA-N 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 2
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 2
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 2
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 description 2
- 239000011575 calcium Substances 0.000 description 2
- 229910052791 calcium Inorganic materials 0.000 description 2
- 229930002875 chlorophyll Natural products 0.000 description 2
- 235000019804 chlorophyll Nutrition 0.000 description 2
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 2
- 229910052802 copper Inorganic materials 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 239000011777 magnesium Substances 0.000 description 2
- 229910052749 magnesium Inorganic materials 0.000 description 2
- 229910052750 molybdenum Inorganic materials 0.000 description 2
- 239000011733 molybdenum Substances 0.000 description 2
- 230000001338 necrotic effect Effects 0.000 description 2
- 235000016709 nutrition Nutrition 0.000 description 2
- 239000011574 phosphorus Substances 0.000 description 2
- 229910052698 phosphorus Inorganic materials 0.000 description 2
- 229910052700 potassium Inorganic materials 0.000 description 2
- 239000011591 potassium Substances 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000004611 spectroscopical analysis Methods 0.000 description 2
- 239000011593 sulfur Substances 0.000 description 2
- 229910052717 sulfur Inorganic materials 0.000 description 2
- 239000011701 zinc Substances 0.000 description 2
- 229910052725 zinc Inorganic materials 0.000 description 2
- 208000019025 Hypokalemia Diseases 0.000 description 1
- 206010022971 Iron Deficiencies Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 239000002551 biofuel Substances 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000012272 crop production Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- BHEPBYXIRTUNPN-UHFFFAOYSA-N hydridophosphorus(.) (triplet) Chemical compound [PH] BHEPBYXIRTUNPN-UHFFFAOYSA-N 0.000 description 1
- WPBNNNQJVZRUHP-UHFFFAOYSA-L manganese(2+);methyl n-[[2-(methoxycarbonylcarbamothioylamino)phenyl]carbamothioyl]carbamate;n-[2-(sulfidocarbothioylamino)ethyl]carbamodithioate Chemical compound [Mn+2].[S-]C(=S)NCCNC([S-])=S.COC(=O)NC(=S)NC1=CC=CC=C1NC(=S)NC(=O)OC WPBNNNQJVZRUHP-UHFFFAOYSA-L 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000029553 photosynthesis Effects 0.000 description 1
- 238000010672 photosynthesis Methods 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 208000007645 potassium deficiency Diseases 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000246 remedial effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000002786 root growth Effects 0.000 description 1
- 230000009528 severe injury Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G7/00—Botany in general
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Environmental Sciences (AREA)
- Forests & Forestry (AREA)
- Multimedia (AREA)
- Ecology (AREA)
- Quality & Reliability (AREA)
- Botany (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Biodiversity & Conservation Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
NUTRIENT DEFICIENCY STRESS DETECTION AND PREDICTION IN CORN FIELDS
FROM AERIAL IMAGES USING MACHINE LEARNING
Abstract:
Early, accurate diagnosis of nutrient deficiency stress (NDS) has important economic and
environmental implications; precision application of chemical rather than blanket application
decreases grower maintenance costs while minimizing the chemicals amount that can reach the
atmosphere unnecessarily. Furthermore, early treatment decreases crop damage and, as a result,
increases crop yield within a given season. In order to identify and predict NDS around the region,
we collect sequences of aerial imagery of high-resolution and create models for semantic
segmentation. Agriculture, deep learning, modern machine vision, and remote sensing all collide in
our research. To begin, we create a benchmark for detection of full-field nutrient deficiency stress
(NDS) and quantify the pretraining effects, architecture of backbone, representation of the input, and
strategy sampling. This research leads to recent advances in deep learning (DL) for agriculture and
remote sensing while also tackling a major social issue with sustainability and economic
ramifications. Thus, this invention is intended in detecting the nutrient deficiency in corn fields using
aerial images. Machine learning uses the aerial images in identifying and classifying the nutrient
deficiency corn plant based on the severity of stress and symptom of each specific nutrient type. This
invention of detecting NDS uses support vector machine (SVM) algorithm.
1
NUTRIENT DEFICIENCY STRESS DETECTION AND PREDICTION IN CORN
FIELDS FROM AERIAL IMAGES USING MACHINE LEARNING
NITROGEN
IRON OLD GROWTH IS YELLOW
NEW GROWTH IS YELLOW AND NEW GROWTH IS
LIGHT GREEN
CALCIUM MAGNESIUM
STUNTED GROWTH AND DARK VEINS LIGHTLEAVES
MISSHAPEN LEAVES
POTASSIUM PHOSPHORUS
YELLOWING TIPS AND LOSS OF LEAVES DARKER
EDGES HUE
C02
MPANANES LEAVES DIE STUNTED SPO T.SAN DHOLE S
GROWTH
Figure 1: Nutrient deficiency in plant.
Description
C02 MPANANES LEAVES DIE STUNTED SPO T.SAN DHOLE S GROWTH
Figure 1: Nutrient deficiency in plant.
Field of the Invention:
This invention is intended in detecting the nutrient deficiency in corn fields using aerial images. Machine learning uses the aerial images in identifying and classifying the nutrient deficiency corn plant based on the severity of stress and symptom of each specific nutrient type. This invention of detecting NDS uses support vector machine (SVM) algorithm.
Background of the Invention:
Nowadays, the key interest of machine learning approach is more to improve the agricultural production drastically. The sustainable practice in the agricultural field faces the challenges in the economic way, water scarcity, and change in climatic conditions. The requirement for the food production in large scale is due to the increased population growth. The nutrient to the plant crop increases the production rate in a large scale and hence, the management of the nutrient content in the plant crop is being diagnosis continuously with the small time interval. The deficiency and excess usage of nutrient content to the plant might affect the entire corn plant. The timely detection of the nutrient deficiency condition in the plant enables us to prevent the plant by providing the required nutritional content. The aerial photography and remote sensing methods have been widely used in agriculture. Orthodox machine vision-based studies of agriculture have relied heavily on indices from vegetative cultivation like the NDVI (Normalized Difference Vegetative Index). Another important measure, the GNDVI (Green Normalized Difference Vegetative Index), is more closely associated with concentration of chlorophyll and thus with rate of photosynthesis, rendering it a possible predictor of stress. To diagnose and identify different forms of NDS (nutrient deficiency stress), researchers used both conventional computerized and machine learning approaches. Mostly these findings concentrate on determining the deficiency type based on close-up photographs of the plant. Aerial imagery research in early phase focused on detecting imagery of hyper spectrum signatures and radiation of short-wave that were linked to the presence of nutrient deficiency stress. Indices of vegetation-based algorithms, like many conventional hand-crafted elements, suffer from changes in appearance because of variable seamlines and lighting, resulting in numerous appearances globally for the picture. If other improvements and corrections are not made, this may pose problems when depending on these indexes. We investigate the use of indices in Vegetation's machine learning mission.
Singh et al utilized machine learning approach in predicting the high-throughput stress phenotyping plants. They developed an automated technology that uses the high-resolution images and sensor data in acquiring information. The machine learning (ML) tool from the dataset extracts the certain data pattern and features in detecting the stressed phenotype. The detection of the stressed phenotypic plant breed in the agricultural land includes the four stages of decision cycle namely identification, classification, quantification, and prediction. Thus, they overviewed the stress in a large plant community using various machine learning approaches precisely.
Dadsetan et al involved in the detection and prediction of nutrient deficiency stress using longitudinal aerial imagery. The nutrient deficiency stress (NDS) economically causes the great impact in the environment. The nutrient deficiency stress has to be precisely identified so that the operational cost is minimized and the earlier detection of the plant reduces the loss with the simultaneous improvement in the crop production. The proposed systematic approach makes use of the high resolution aerial images to detect and classify NDS in the agricultural land. They involved the modem computerized technologies such as deep learning with remote sensing to yield the high production. Initially, the impact, architectural backbone, input model, and sampling strategy are notified before entering into the detection stage of stressed plant. Depending on UNet, a single timestamp model acquires the informational data. The proposed system framework includes spatiotemporal information and UNet in association with convolutional LSTM layer enable us to identify the NDS plant crop. The sustainable and economical enhancement of the agriculture is achieved using remote sensing and deep learning approach.
Barbedo et al utilized proximal images and machine learning for the detection of nutrition deficiencies in plants. The challenges in the agricultural land are solved using the digital images and machine learning techniques and thus promoting it to the digitalized farming method. The plant diseases and the damages in the plant crop are identified using the proximal images. This is even applicable to detect the current status of the nutrient content present in the plant crops and further researches can be carried out on this topic. They made a literature survey in identifying the plant using proximal images. The image sensors such as visible range, multispectral, hyperspectral, chlorophyll fluorescence, etc are the images being captured using Unmanned Aerial Vehilces (UAVs), satellite, and airplane. Thus, the proposed method of detecting the nutrient deficiency in plants is effective.
Zubler et al provided a review on the recent machine learning algorithms. Plant stresses have been monitored using the spectrometry or imaging of leaves of the plant in the near-infrared (NIR), visible (RGB), ultraviolet (UV) and infrared (IR) wavebands, with image of fluorescence or spectrometry sometimes added. Imaging at several distinct wavelengths (imaging multispectral) or through a broad spectrum of wavelengths (hyperspectral imaging) can provide invaluable insight into plant disease and stress. In recent years, thermal cameras, optical filters and digital cameras have become more affordable, while cameras have become more portable and lightweight hyperspectral. Furthermore, the accuracy of mobile cameras has greatly upgraded, making them a viable choice for on-the-spot stress monitoring. Plant pressures can now be tracked more effectively using field-deployable and handheld approaches thanks to advancements in imaging technologies. Recent developments in machine learning (ML) algorithms have made it possible to interpret and classify spectra and images in a completely automatic and repeatable way, without the use of complex spectrum or image processing techniques. This analysis would highlight recent advancements in portable (including smartphone-based) stress detection approaches, explore data processing and machine learning strategies that can yield stress recognition and classification outcomes, and propose potential avenues for effective implementation of these methods into practical use.
Objective of the Invention:
1. This invention is intended in detecting the nutrient deficiency in corn fields using aerial images. The nutrient deficiency might affect the growth of the crop plant. In the several plants, the symptoms of the deficiency in nutrient affect the soil texture or management pattern. In case of regular pattern, the nutrient deficiency symptoms show the changes in the soil condition. 2. Machine learning uses the aerial images in identifying and classifying the nutrient deficiency corn plant based on the severity of stress and symptom of each specific nutrient type. Machine learning is the most appropriate technology involved in the analysis of the aerial images. The machine learning approach transform the aerial images into a number of smaller images are involved in the training. 3. This invention of detecting NDS uses support vector machine (SVM) algorithm. SVM method uses the aerial images of the leaves of the stressed plant for the estimation process. The preprocessed images are extracted is fed as an input to the SVM model.
Summary of the Invention:
In today's world, corn crop is utilized in the various applications such as biofuels, animal feed, and for domestic consumption. Depending on the usage crop plants are classified into various types namely, food crops, feed crops, fiber crops, oil crops, ornamental crop, food crops, and ornamental crops. The most important challenge faced during the corn yield is the nutrient deficiency this might affect the growth and affect the entire production. The corn field is affected due to the nutrient deficiency such as nitrogen, phosphorus, potassium, calcium, magnesium, sulfur, molybdenum, boron, copper, iron, manganese, and zinc. The nutrient deficiency might affect the growth of the crop plant. In the several plants, the symptoms of the deficiency in nutrient affect the soil texture or management pattern. In case of regular pattern, the nutrient deficiency symptoms show the changes in the soil condition. The corn plant leaves are changed to yellow in color, interveinal yellowing in leaves, short internodes, leaves with color such as red, purple, bronze are symptoms encountered under nutrient deficiency.
Modern technologies are utilized in the agricultural field in identifying the nutrient deficiency in the crop yields. The nutrient deficiency affected plants are separately segregated from the healthy plants. The farmer lacks to identify the injured plants and therefore, the alternative source is developed to overcome the challenges faced by the farmer in yielding crops. The aerial images are the most appropriate methodologies that support in identifying nutrient deficiency stress in corn plants. The aerial vehicle collects the high resolution images over the stressed plants at a low altitude is known as the aerial images. The aerial images are collected in the RGB spectrum. The computerized method capturing RGB images analysis the plants where there is change in color and shape in corn leaves to determine the stressed nutritional deficiency plant and the deficiency plants contains the pigments in the leaves.
The aerial images are utilized for the scientific and commercial purposes. The aerial images is applicable for many contemporaneous applications as the aerial images encloses more informational data that helps in tackling the consequence aroused in a wide range. This approach promotes the sustainable development of globe with the contribution of various characteristic features. Machine learning is the most appropriate technology involved in the analysis of the aerial images. The machine learning approach transform the aerial images into a number of smaller images are involved in the training. The aerial images with the training models is effectively trained and managed to obtain the expected result. The use of machine learning approaches for applications related to agriculture has intensified. These observations can be divided into two categories: images that are standard and images obtained aerially imagery captured by satellite, drone, or aircraft. Pest and disease recognition, identification of the seed, counting crop, detection of weed, forecasting the yield, and segmentation of the parcel are only a few examples of applications.
Machine learning is the advanced technology which collects the aerial images from satellite and involved in identifying the stressed plants. The machine learning initially involved in training the acquired data further undergoes the testing of the data. The aerial images are compared with the true nutrient deficiency stressed plant image and the affected plant are segregated and removed from the healthy plant environment and also capable of classifying which type of nutrient deficiency is caused in that crop plant. The growth of the stressed plant is prevented using the fertilizer in the required amount. Thus, the corn yield is increased using the aerial images in association with the machine learning approach. Machine learning-based techniques used for the segmentation in several studies to segment the field semantically into various patterns, including nutrient deficiency stress (NDS), from aerial imagery of higher-resolution.
Detailed Description of the Invention:
The proposed machine learning approach initially involved in the data collection. The satellite involved in capturing the images of the stressed plant in the agricultural land and stored in the satellite. Across the large land areas, the aerial images provide the better opportunity to overview the field. Aerial images with the high resolution enable the farmers in identifying the stressed plant. The data from the corn plant is obtained using the captured aerial images. The aerial images are captured as a visual RGB images are captured at a resolution of 10cm/pixels using Wide Area Multi-Spectral System (WAMS).
The single images with the large pixel dimension are captured using the ground control point based on the size of the farm. RGBN image and a digital elevation model (DEM) are required to generate the true images after the performance of ortho-rectification process. Aerial images generate the information of the exact condition of the agricultural land. The aerial images are protected with the high security and therefore, hacking of data is not easily permitted. The experts are involved in segregating the plants which are stressed due to the nutritional deficiency. Detection of the stressed nutrient deficiency plants are acquired by implementing the machine learning approach using aerial images. The proposed system enables us to take some remedial action and providing the fertilizer to the stressed plants. The system framework encloses the control unit, data acquisition, and processing units. The nutrient deficiency symptoms are cross-verified using machine learning approach.
Machine learning approach includes the four stages namely identification, classification, quantification, and prediction. In the agricultural field, the nutrient deficiency stressed plants are detected with the specific stress features are included in the identification. In the identification methods, the aerial images preprocessing is difficult. The aerial images with the high resolution provide the information regarding the stressed plant automatically. Support Vector Machine (SVM) is a part of the machine learning approach is effectively in identifying the corn plant stress. Early identification of the stressed plant is quite challenging as the changes in the plant is not easily notified. SVM method uses the aerial images of the leaves of the stressed plant for the estimation process. The preprocessed images is extracted is fed as an input to the SVM model. Even two aerial image platforms can also be utilized in indentifying the nutrient deficiency and the images obtained from both the platforms undergo the classification process. SVM model detect based on the symptoms such as yellow colored leaves, interveinal yellowing in leaves, short internodes, leaves with color such as red, purple, bronze.
Classification of stressed plants is performed based on the nutritional deficiency symptoms. Preprocessing, segmentation, and feature extraction are included in the classification process. The stress is classified based on the type of the nutrient being used each and every nutrient and their corresponding symptoms are discussed below to undergo the classification process.
Nitrogen: The nitrogen deficiency causes the yellowish-green corn plant with the pale texture and spindle stalks. The reason for the nitrogen deficiency due to favored condition such as dry soil, cold soil, sandy soil, inadequate fertilizers, and heavy rainfall.
Symptoms: looks aged, v-shaped yellowing on leaves, and lower leaves.
Phosphorus: This deficiency usually occurs in the young plant crops. This type of deficiency mobilizes in the plant but still there is no change in color in a newly emerging leaves. This minimizes the growth rate of the plant and the plant will not cross three feet taller. Only several corn hybrids show the purple color change whereas the others do not change in case of inadequate phosphorous.
Symptoms: The plant remains in dark green color, leaf tips and margin are colored reddish purple, restricted root growth.
Potassium: In this deficiency, corn leaf margins and lower leaves are turned to yellow color and necrosis. It takes several weeks to show the changes in plant. The progress of the potassium deficiency increases in the plant might transfer the deficiency effect from old to young leaves and decreases the stalk strength.
Symptoms: older leaves changes to yellow along the margin.
Calcium: Calcium deficiency is rare in the corn plant. The calcium deficiency in the plant remains immobile and this occurs in the soil with low pH rate.
Symptoms: The lower leaf sticks to the upper leaf tip.
Zinc: Plant remains stable as the internodes are shortened due to this deficiency and it is relatively immobile. Severity of deficiency changes the new leaves into a white bud. These deficiencies are favored with high soil pH.
Symptoms: Causes interveinal, light striping in the leaves towards tip whereas the margin, midrib, and leaf tip remain green.
Iron: This deficiency occurs rarely in corn plant. This remains immobile and therefore, it is not transferred from the old leaves to new leaves. This type of deficiency occurs on high pH soils.
Symptoms: The upper leaves are pale green nearly white along the length of the interveinal.
Copper: This deficiency rarely occurs in corn plant and this remains relatively immobile. Similar to iron deficiency, the leaves are streaked and the stalk is soft and limp. This is favored in organic soil and high soil pH.
Symptoms: young leaves are yellow in color and the tip is died.
Boron: It is also rare in corn plant and this is not transferred to the entire plant instead the upper internodes stop growing. Corn is highly sensitive to the boron fertilizer.
Symptoms: small dead spots in leaves.
Molybdenum: This deficiency is rare in corn plant and it is favored by a very low soil pH and weathered soils.
Symptoms: At the tip, along margin, and between veins older leaves turn necrotic.
Sulfur: Similar to nitrogen deficiency, this also occurs in the small corn plants. This is favored by acid sandy soil, and cold-dry soil.
Symptoms: upper part of the younger leaves turns yellow, stunting plant, and delayed maturity.
Magnesium: This deficiency is mobile and therefore, transferred from old to new plant tissues. This is favored in the moderate to high rainfall regions. During the severity of the deficiency, the older leave turn reddish -purple whereas the edges and tips become necrotic.
Symptoms: Lower part of the leaves turn from yellow to white in the interveinal striping, presence of dead round spots.
The nutrient deficiency stressed plants are quantified using the Support Vector Machine (SVM), a part of the machine learning approach. Depending on the stress severity and symptoms, the plant is classified under the specific nutrient content in the quantification methods. The various nutrient deficiencies are mentioned above with the symptoms helps in quantifying the corn plant on a scale of -100%. Initially, quantification process consists of preprocessing stage with the symptoms detection and contrast enhancement. The hyper spectral images are utilized for the autonomous method of quantifying the severe damage in the corn plant.
The captured images generate the information regarding the stressed plant. The images enable us to identify which nutrient deficiency leads to the plant stress by notifying the symptoms of the specific nutrient are involved in the classification process are extracted. The features such as texture, color, shape, and size that distinguishing healthy plant from stressed plant that would be helpful for farmers. The timely and corrective control of stress is necessary to avoid the severe loss of production. The farmer may lack to identify the stress plant in the earlier stage and therefore, the proposed system model with the support of experts identifies the stressed plant in the earlier stage. Thus, the proposed system model enables a high precision agriculture. The SVM based approach uses the hyper spectral images in forecasting the nutrient deficiency stress plant.
Claims (3)
1. This invention is intended in detecting the nutrient deficiency in corn fields using aerial images. The nutrient deficiency might affect the growth of the crop plant. From claim 1, In the several plants, the symptoms of the deficiency in nutrient affect the soil texture or management pattern. From claim 1, In case of regular pattern, the nutrient deficiency symptoms show the changes in the soil condition.
2. Machine learning uses the aerial images in identifying and classifying the nutrient deficiency corn plant based on the severity of stress and symptom of each specific nutrient type. From claim 2, Machine learning is the most appropriate technology involved in the analysis of the aerial images. From claim 2, The machine learning approach transform the aerial images into a number of smaller images are involved in the training.
3. This invention of detecting NDS uses support vector machine (SVM) algorithm. SVM method uses the aerial images of the leaves of the stressed plant for the estimation process. From claim 3, The preprocessed images are extracted is fed as an input to the SVM model. From claim 3, SVM model detect based on the symptoms such as yellow-colored leaves, interveinal yellowing in leaves, short internodes, leaves with color such as red, purple, bronze. From claim 3, Depending on the stress severity and symptoms, the plant is classified under the specific nutrient content in the quantification methods. From claim 4, The various nutrient deficiencies are mentioned above with the symptoms helps in quantifying the corn plant on a scale of 0-100%.
NUTRIENT DEFICIENCY STRESS DETECTION AND PREDICTION IN CORN FIELDS FROM AERIAL IMAGES USING MACHINE LEARNING 2021101996
Figure 1: Nutrient deficiency in plant.
Figure 2: The proposed system model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021101996A AU2021101996A4 (en) | 2021-04-18 | 2021-04-18 | Nutrient deficiency stress detection and prediction in corn fields from aerial images using machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021101996A AU2021101996A4 (en) | 2021-04-18 | 2021-04-18 | Nutrient deficiency stress detection and prediction in corn fields from aerial images using machine learning |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2021101996A4 true AU2021101996A4 (en) | 2021-06-03 |
Family
ID=76132940
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2021101996A Ceased AU2021101996A4 (en) | 2021-04-18 | 2021-04-18 | Nutrient deficiency stress detection and prediction in corn fields from aerial images using machine learning |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2021101996A4 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022094698A1 (en) * | 2020-11-05 | 2022-05-12 | Farmers Edge Inc. | Advanced crop manager for crops stress mitigation |
-
2021
- 2021-04-18 AU AU2021101996A patent/AU2021101996A4/en not_active Ceased
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022094698A1 (en) * | 2020-11-05 | 2022-05-12 | Farmers Edge Inc. | Advanced crop manager for crops stress mitigation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Calderón et al. | Detection of downy mildew of opium poppy using high-resolution multi-spectral and thermal imagery acquired with an unmanned aerial vehicle | |
US20230292647A1 (en) | System and Method for Crop Monitoring | |
Tewari et al. | Estimation of plant nitrogen content using digital image processing | |
Zhou et al. | Rice plant-hopper infestation detection and classification algorithms based on fractal dimension values and fuzzy C-means | |
Rasti et al. | A survey of high resolution image processing techniques for cereal crop growth monitoring | |
Lang et al. | Detection of chlorophyll content in maize canopy from UAV imagery | |
Polder et al. | Automatic detection of tulip breaking virus (TBV) using a deep convolutional neural network | |
Zhao et al. | Spatial-aware SAR-optical time-series deep integration for crop phenology tracking | |
Zhang et al. | Development of an automated high-throughput phenotyping system for wheat evaluation in a controlled environment | |
Siegfried et al. | Combining a cotton ‘Boll Area Index’with in-season unmanned aerial multispectral and thermal imagery for yield estimation | |
AU2021101996A4 (en) | Nutrient deficiency stress detection and prediction in corn fields from aerial images using machine learning | |
Wang et al. | Combining vegetation, color, and texture indices with hyperspectral parameters using machine-learning methods to estimate nitrogen concentration in rice stems and leaves | |
Bleasdale et al. | Feasibility of detecting apple scab infections using low-cost sensors and interpreting radiation interactions with scab lesions | |
Liang et al. | CanopyCAM–an edge-computing sensing unit for continuous measurement of canopy cover percentage of dry edible beans | |
Luo et al. | Evergreen broadleaf greenness and its relationship with leaf flushing, aging, and water fluxes | |
Wang et al. | Research on application of smart agriculture in cotton production management | |
Barjaktarović et al. | A multispectral acquisition system for potential detection of Flavescence dorée | |
CN115035423A (en) | Hybrid rice male and female parent identification and extraction method based on unmanned aerial vehicle remote sensing image | |
Zhou et al. | Imaging technology for high-throughput plant phenotyping | |
Poblete-Echeverria et al. | Detection of the spectral signature of Phytophthora root rot (PRR) symptoms using hyperspectral imaging | |
Hosseini et al. | Nitrogen estimation in sugarcane fields from aerial digital images using artificial neural network. | |
Barjaktarovic et al. | Data acquisition for testing potential detection of Flavescence dorée with a designed, affordable multispectral camera | |
Valero et al. | Identification of agricultural crops in early stages using remote sensing images | |
Munibah et al. | Application of RGB UAV images to identify spectral patterns and estimate rice production | |
Johnson et al. | Vision-Based Cranberry Crop Ripening Assessment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |