MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202541122413 A) filed by New Prince Shri Bhavani College Of Engineering And Technology; Julie A; Rajasree K; Malarkodi S; and V. Mangaiyarkarasi, Chennai, Tamil Nadu, on Dec. 5, 2025, for 'autonomous weed detection and removal system using cnn and python-controlled embedded platform.'
Inventor(s) include Julie A; Rajasree K; Malarkodi S; and V. Mangaiyarkarasi.
The application for the patent was published on Feb. 6, under issue no. 06/2026.
According to the abstract released by the Intellectual Property India: "This project presents the development of an Autonomous 'vVeed Detection and Removal System using CNN and Python-controlled embedded Platform aimed at addressing one ofthe most persistent challenges in agriculture uncontrolled weed growth. The system integrates Convolutional Neural Networks (CNNs) with an embedded platform programmed in Python to enable real-time, intelligent weed management. The crop field is contiJ1uously photographed by a high-resolution camera module, and the pre-trained CNN model analyzes the photos to reliably identify weeds and crops. The inbuilt controller determines the weed's location when detection is finished and starts a mechanical removal process that precisely removes the weed without upsetting the crop. GPS guidance, obstacle detection, sensor-based-navigation, and wireless connection are additional features added to the system to guarantee full field coverage. These features provide smooth field movement and remote monitoring. This approach was designed in response to the shortcomings of conventional weed control methods. Chemical herbicides lower soil fertility, increase environmental pollution, and present health hazards, whereas manual weeding is time-consuming, labor-intensive, and impractical for large-scale tarming. Farmers have further difliculties during the busiest funning seasons due to the scarcity and high cost of human labor. The suggested system reduces operational expenses, dependence on hazardous chemicals, and human labor by combining embedded control and artificial intelligence. By preserving soil health, minimizing environmental harm, and facilitating steady crop development, the system also supports sustainable agriculture practices. Improved agricultura I output, lower tarm ing costs, and scalability across various crop varieties and field circumstances are among the anticipated results. Beyond its current agricultural benefits, this study shows how embedded technology and deep learning can be used to solve practical food security issues and how such intelligent systems can help realize the goal ofto1thcoming smart farming environments."
Disclaimer: Curated by HT Syndication.
