MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641017446 A) filed by Vallurupalli Nageswara Rao Vignana Jyothi Institute Of Engineering And Technology, Hyderabad, Telangana, on Feb. 17, for 'edge-deployed yolov7 crop and weed detection system using raspberry pi for offline agricultural image inference.'
Inventor(s) include Dr. Narra Dhanalakshmi.
The application for the patent was published on Feb. 27, under issue no. 09/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses an edge-based weed detection and crop classification system for agricultural field images using a YOLOv7 object detection model deployed on a Raspberry Pi (102a). The system includes an image acquisition module (101), a pre-processing module (104) for generating YOLO-compatible tensors, and a detection and classification module (105) configured to identify crop and weed instances with bounding boxes and confidence scores. A post-processing module (106) applies non-maximum suppression to refine detections and generate annotated output images. A storage and export module (107) stores results locally and transfers outputs to removable storage devices for offline field usability. The trained object detection model (103) is trained using annotated images and deployed to a CPU-only edge environment to enable inference without GPU acceleration or internet connectivity. The invention provides a low-power, standalone and cost-effective precision agriculture tool supporting localized decision-making and improved weed management."
Disclaimer: Curated by HT Syndication.
