Agriculture 4.0 : Smart Farming

Antimo Musone

Antimo Musone

Rome, Lazio

"Internet of Farming” : Artificial Intelligence, Big data, IoT Sensors , Computer Vision, Drones and Analytics tools are some of the technologies shaping agriculture 4.0. Following the model of industry 4.0, the agricultural and farming sector is experimenting new business models and innovations: precision agriculture, vertical farming, self-driven tractors...etc. Based on the previous listed technologies, the target of project is provide a Intelligent Farm Dashboard Application composed by reports and analysis about the health of crop which could be include plant disease or detecting pest infestations. The Dashboard will be based on Machine Learning Models ( optimized through OpenVino Toolkit ) for analysis, prediction, forecasting and computer vision of datasets composed by Infrared & Color Images captured from drone ( Intel Aereo / DJI Spark ) and IoT data sensors from field ( Air Humidity, Soil Moisture, CO2 Monitor , Light & Temperature ). In particular, images will be captured through drone equipped with IR camera, TETRACAM ADC Snap Multispectral, this camera produces 1.3 Megapixel images (1280x1024 pixels) that are stored together with metadata, such as GPS coordinates and/or aircraft trim information (pitch, roll, and yaw). Metadata also allows you to establish the position on the ground of each image. We will analyze all possible soil and crop data in order to identify actions to improve the harvest or predict possible threats. ...learn more

Project status: Concept

Internet of Things, Artificial Intelligence

Intel Technologies
OpenVINO

Overview / Usage

The goal of the project is to monitor crop health through different analysis & KPIs:

  1. Identification of insects, larvae and parasites that can threaten the harvest ( plant disease and detecting pest infestations )

  2. Vegetation identification & classification and monitoring of health status based on biophysical parameters and vegetation indices;

  3. Land use identification, identification of soil types, vegetation and crops with their state of health;

  4. Analysis of thermal anomalies in water ,thermal behavior of surface waters, mapping of algal types and their diffusion, torpidity and water color, identification of paleoalve

Methodology / Approach

The approach is based on four phases:

  1. Sensor installation and data collection;

  2. Analysis and report of the collected data;

  3. Development of prediction models and Dashbord;

  4. Go Live Dashboard & Optimization of Farm production .

Technologies Used

Intel OpenVino Toolkit
Microsoft Desktop Application
Intel NUC
UP Squared* Grove* IoT Development Kit
Machine Learning
IoT Sensors
Intel Aereo / DJI Drone

Collaborators

There are no people to show.

Comments (0)