Description:Field of the Invention
The proposed invention utilizes drone technology to analyze crop water levels, fertilizer needs, pests and weeds. This provides farmers with sufficient information to monitor crops, so problems can be solved easily and crop growth will increase. It also suggests some precautions to enhance crop growth and productivity.
Objective of this Invention
The purpose of introducing this Innovation is to estimate the health of crops and givefarmers accurate information about crop conditions, water levels, fertilizer issues and weed identification . It also helps farmers by providing information on crops and suggesting necessary measures ,precautions to improve crop growth, health, and productivity. Our system has 90% accuracy in its output. Integrated data is used to create Geographic Information System (GIS) maps by providing visual images of crop conditions and the Normalized Difference Vegetation Index (NDVI) using specific multispectral images to estimate vegetation health, and using image analysis algorithms to identify specific areas with the images.
Background of the Invention
The drone-based crop scanning system lies in the recognition of the challenges,there is a need for complete agriculture reform that integrates advanced technologies, sustainable farming practices, to assure the prosperity of traditional farming. The system is designed to modify agriculture providing accurate analysis of required parameters such as water levels, fertilizer issues, and weeds identification. It also provides sustainable and efficient agricultural practices that improve crop health and productivity.For instance, WO2021198731A1 is a method proposed for gathering data on plant characteristics through imaging, specifically tailored for agriculture and horticulture. Machine vision and various deep learning algorithms to assess the physical state of plants. The pixel matrix library with pictures of agricultural and horticultural problems, the method addresses various visual inspection. Relevant image extraction employs deep learning and machine vision, with pixel models generated from multiple images captured by cameras within the agricultural and horticultural environment.
The US20190050948A1 describes the crop prediction system using crop prediction models trained on various machine learning operations based on geographic and agronomic information. Responsive to receiving a request from a grower, the crop prediction system can access information representation of a portion of land corresponding to the request, such as the location of the land and corresponding weather conditions and soil composition.US11440659B2 is a method for precision agriculture using UAV systems and AI image processing includes an unmanned aerial vehicle (UAV), wireless communication device, central control unit, and a spray device with a multispectral camera attached to the UAV. The farming area is divided into blocks, and the central control unit guides the UAV over blocks, capturing leaf Area index (NDVI) for each block. Based on PLAI and NDVI, the spray control mode for the corresponding block is determined, guiding the spray device to apply water, salt, fertilizer, and/ or pesticide farming operations through precise and efficient resource application.KR102049938B1 an agricultural drone system is revealed, enabling real-time adjustment of pesticide application through sensor-based big data analysis of crop condition. This pesticide-spraying drone system is equipped with multiple spray nozzles, a camera capturing crop moisture, and a multispectral sensor for crop analysis. The collected data is temporarily stored in a memory unit, and a flight controller manages flight parameters. The system includes a big data-based pesticide spreading unit with a database, analyzing and learning to provide optimized pesticide amounts based on image information and crop state changes. A portable terminal displays GIS-linked spraying areas and allows user control. The drone, incorporating big data analysis, ensures real-time, optimized pesticide application, minimizing ecological impact by preventing the need for redistributive efforts.US20170127606A1 This method and system leverage agricultural drones to enhance field monitoring and mapping for the creation of contour maps, specifically aiding in field operations such as directing tillage and managing matter spreading (e.g., fertilizer, manure, or sewage treatment sludge). The focus is on preventing excessive erosion and runoff through precise control measures. The utilization of one or more drones ensures efficient field management, optimizing agricultural processes while minimizing environmental impact.
Summary of the Invention
The system represents a significant announcement in agriculture through the integration of drone based crop scanning. It enables the use of all resources such as fertilizer, water, seeds and pesticides. The system allows the farmers to keep track of their crops with the information that the system provides and the integrated data that is used to create Geographical Information System (GIS) maps. It provides a visual image of crop condition and helps the farmers view the crop and use the images and information provided by the system to understand their crop situation.It helps farmers take measures to make the crop grow faster at a high production rate, and it can also help farmers develop farming techniques.They can adapt to weather conditions and allocate resources without any waste.
Brief Description of Drawings
The invention will be described in detail with reference to the exemplary embodiments shown in the figures wherein:
Figure-1: Flowgorithm representing the workflow of the AGROVISION - AERIAL ANALYSIS FOR CROP USING DRONE TECHNOLOGY
Figure-2: Architecture representation of aerial analysis of crop using Drone
Figure-3: Diagrammatic representation of aerial analysis using drone
Detailed Description of the Invention
Our Proposed invention mostly relies on these core components and they are:
In this proposed inventionDrone is an important component for Aerial Analysis and here we can operate drones in two ways: first one is operated without a human pilot and second with a remote control device. The Drone helps in monitoring support of sizes ranging from 100mm to 300mm .Drones are rechargeable with the help of lithium-ion batteries ranging from 500 to 1000mAh and consist of a microprocessor which acts as the brain and sends the collected data.The flight times for consumer drones range from 15 to 30 minutes .And onboard cameras and gimbals help to capture HD to 4K resolution for the data. Drones incorporate AI for object recognition,navigation and obstacle avoidance but the sensor suits of drones encompass various types of sensors that play a crucial role in their functionality. Here some components help in the easy collection of data such as accelerometers, which measure acceleration forces,enabling detection of change in speed and direction ,and gyroscope which measures the rate of rotation around different axes contributing to the drone’s orientation. Vision sensors, including cameras,provide visual information and spatial awareness.Before a Drone takes flight it first scans the area of the plane and moves to the flight path.In cameras we use Calibration onboard sensor which helps to capture accurate images of the crop field. The Onboard cameras capture high-resolution images of crops, and Multispectral sensor capture data across different wavelengths of electromagnetic spectrum , revels specific information about crop conditions.For more accurate information we use two sensors and they are thermal sensors and LiDAR sensors .Thermal sensor measure infrared radiation emitted by crops ,highlight variations in temperature, And LiDAR sensors use laser light to measure distances of high precisions ,creating detailed 3D Models of the terrain and crop structure.The overall collected data from various sensors ,including images,multispectral data and LiDAR scans is integrated and processed .The Integrated data used for Geographical Information System(GIS)maps,provides a visual representation of crop conditions.The process of capturing images using onboard cameras during drone flights over the agriculture fields takes Initial steps to enhance image quality,including correction of distortion,removal of noise and normalization of lighting conditions.Combining multiple images into a single,seamlessmosaic.The Computing indices such as NDVI(Normalized Difference Vegetation Index)using specific bands of multispectral images to quantify vegetation health,utilizing image analysis algorithms to identify visual cause indicative of pests infestations on crops.
The core of the system depends on data collected by most number sensors.The user profiling creates individual profiles ,incorporating preferences and behaviours for predicting user preference,Item representation structurally portrays content,enhancing the system ability to align with users preferences and Collaborative filtering recommends item based on similar user profiles,leveraging collective wisdom for Content-based filtering suggests items akin to past user interactions.The content-based filtering ,addressing limitations for robust recommendations, Matrix factorization decomposes the user-item matrix,empowering precise prediction based on latent features . The recommendation systems are driven by a diverse array of algorithms and tools designed to craft personalised user experiences.Collaborativefiltering,content-based filtering,matrixfactorization,hybridmodels,and deep learning methods all play integral roles in the intricate of this system.Additionally, context-aware recommendation algorithms being an added layer of sophistication by incorporating contextual into the recommendation process.
It is an important content component which measure the volumetric water content in soil.The relation between the measured property and soil moisture must depending on environmental factors such as soil type, temperature, or electric conductivity.Soil moisture sensor that estimate volumetric water content .Another class of sensors measures another property of moisture in soil called water potential;these sensors are usually referred to as soil water potential sensors and include densitometers and gypsum blocks.Measuring soil moisture is important for agriculture applications to help farmers manage their irrigation systems more efficiently.Knowing the exact soil moisture condition on their fields,not only are farmers able to generally use less water to grow a crop,they are also able to increase yields and the quality of the crop by improved management of soil moisture during critical plant stages.Microprocessor is nothing but a controlling unit of a micro-computer, fabricated in small chip capable of performing operations and helps in communicating with the other devices connected to it.The data stored in the memory in a sequential order.The operation of microprocessor fetches. Those instructions from the memory, then decodes it and executes those instructions till STOP instruction is reached.We use many sensors in aerial analysis for crops and some of them are RGB,multispectral(MS),hyperspectral or thermal cameras or Lidar etc.The standard visual sensor collect red,green and blue wavelength of light and the multispectral sensor operation is which is able to collect these visible wavelength as well as wavelengths that fall outside the visible spectrum,these include near-infrared radiation(NIR),short-wave infrared radiation(SWIR) .These multispectral image composed by several bands,with the wavelength of the bands between 450 and 1250 nm.Multispectral sensing can be used for everything from assessing crop yield and quality to helping clinicians assess the wounds of burn victims.And here RBG is a standard camera attached to drone,combined with AI deep learning,can provide crop health colour maps.The standard RGB camera may also be called a natural-colour or true-colour camera and will produce images similar to a digital point-and-shoot camera.The hyperspectral imaging sensors,have large number of contiguous bands .
In this proposed invention we use advanced algorithm such as machine learning and deep learning algorithm, for automated image recognition and analysis and it also measures a specific attributes within the images,such as plant height,canopy coverage or the extent of crop damage.Using image data to develop predictive models for estimating crop yield based on various parameter for presenting analysed in a visual format, such as charts,graph, or heat integrating image deprived data into geographic information system for spatial analysis and mapping developing systems that use analysed image data to provide accurate results for the farmers And by image analysis algorithm which parts are damaged by pest infestations on crop.

Advantages of the proposed model,
➢ User-friendly Interface: An intuitive and friendly interface which can make the farmers easily accessible to it. The provides insight, fertilizer spraying amounts based on the data collected.
➢ Precise Agricultural Data collection: Sensors in drones allow for precise and comprehensive field scanning, enabling detailed analysis of crop conditions.
➢ Autonomous: Drones are operated autonomously which rescues human intervention and enhances productivity.
➢ Real-time Inspection: System allows data transmission from drones to a ground control station, enabling timely crop condition monitoring and adjustments to agriculture operations by farmers.
➢ Sensor capabilities: Drone developed as part of the system includes cameras, multispectral sensors , thermal sensors , Lidar sensors and GPS which gives a comprehensive integrated view of crop and field state.
➢ Monitoring and Control: System enables to transmit data from drones to ground control station, which allows to check the timely state of the crop and modify the adjustments of agriculture related
➢ Escalate Crop Health and fruitfulness: The System help in the enhancement of the overall crop health and its productivity by using artificial intelligence, drone, internet of things technologies. The involvement of these technologies minimize ecological impact and makes space for maintainable agricultural practice.
6 claims and 3 figures. , Claims:The scope of the invention is defined by the following claims:

Claims:
1. Agrovision: Aerial analysis for crop using drone technology comprising,
a) Using high resolution camera the crop study can be conducted and can take images in high resolution for better processing
b) The mapping can be done by area coordinate check points which can help navigation
c) LiDAR are used to accumulate the surrounding data for easy navigation.
2. According to claim 1, The drones operate autonomously which results in reduced human intervention and increased productivity.
3. As per claim 1, Theutilizes a versatile sensor suite which includes cameras, multispectral sensors, thermal sensors, LiDAR sensors and GPS for comprehensive agricultural data capture.
4. According to claim 1, It provides data transmission for farmers to monitor crop state and adjust the operations accordingly.
5. As per claim 1, An embedded with collected data into Geographic information System maps which gives visual representations of recognized patterns and areas that need improvement.
6. As per claim 1, The aim for a fruitful crop health which minimize ecological impact and promote legitimately agricultural practice