MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641100712 A) filed by Jeppiaar Institute Of Technology on August 20, 2026, for Cansat Imagery Analysis For Vegetation Density, Soil Classification, And Ai-Based Crop Selection.
Inventors include Janani M; Anushiya Jasbin A; Dharanika A; Usharani D; Dr. J. Venu Gopala Krishnan; Dr. T. Sripriya; Dr. W. Nancy; Dr. M. Benisha; M. Indumathi; Bharathi M; Karthika. T; M. Nithya; S. Revathy; and M. Sudhagar.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: This patent proposes a CanSat-based imagery analysis system for vegetation density monitoring, soil classification, and Al-based crop selection to provide an efficient approach for smart agriculture applications. Agriculture is one of the most important sectors that supports human life and the economy. Efficient monitoring of agricultural land and proper crop selection are essential for improving productivity and reducing resource waste. Traditional methods of land analysis require manual inspection and take more time and effort. The suggested method takes aerial photos of agricultural area using a CanSat fitted with a camera module. After being taken, the photos are saved on an SD card for later examination. In order to extract valuable information about the features of the soil and plant, the acquired photos are analyzed using image processing techniques. In order to evaluate vegetation density, the system focuses on examining the areas of green vegetation that are present in the taken pictures. The vegetation level is divided into high, medium, and low density groups by locating the greenish areas and figuring out the percentage of vegetation coverage. The suggested method uses a machine learning-based image classification model to classify soil in addition to analyzing flora. The machine learning model is trained using soil photos gathered from agricultural regions. The submitted soil photos are analyzed by the trained model, which then uses the attributes of the photographs to determine the type of soil. Without the need for manual soil inspection techniques, this aids in comprehending the properties of the soil. An Al-based crop selection system is created to suggest appropriate crops for the specified soil condition based on the classified soil type. In order to increase agricultural output and encourage wise farming decisions, the recommendation system assists in choosing crops that are more compatible with the determined soil type. To make interacting with the suggested system simple, a web-based interface is created. The integrated machine learning model analyzes the photos and provides recommendations for appropriate crops, vegetation density analysis, and soil classification findings once the user uploads the photos via the website. Python-based tools are used to create the machine learning model, and image processing methods are used to analyze collected photos accurately. The suggested CanSat imagery analysis system offers an affordable option for agricultural monitoring by combining web-based technology, machine learning, image processing, and remote sensing. Faster land condition assessments and improved crop selection are two ways that this approach might help farmers and agricultural researchers. The research shows how artificial intelligence and CanSat technologies can be used in precision agriculture.
Disclaimer: Curated by HT Syndication.
