Using YOLOv7 for crop and weed detection

A curated collection of 45 high-quality RGB image datasets for computer vision in agriculture. Features datasets for weed detection, disease identification, and crop monitoring, focusing on natural field scenes. Part of our GIL 2025 survey paper.

PyTorch-based Mask R-CNN framework for high-precision instance segmentation of agricultural imagery. Supports custom datasets, advanced training workflows, and robust evaluation for crop and plant analysis.

This repository contains the projects I completed as part of my "𝐔𝐩𝐬𝐤𝐢𝐥𝐥𝐬 𝐈𝐧𝐭𝐞𝐫𝐧𝐬𝐡𝐢𝐩". The internship focused on applying concepts of 𝐌𝐚𝐜𝐡𝐢𝐧𝐞 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠 𝐚𝐧𝐝 𝐂𝐨𝐦𝐩𝐮𝐭𝐞𝐫 𝐕𝐢𝐬𝐢𝐨𝐧 to solve real-world problems.

A Python-based machine learning application for classifying wheat species using image data.

Agrorader farm management software enables large businesses to have complete control over their farming processes across different stakeholders.

Computer Vision pipeline designed for precision agriculture applications, featuring automated dataset processing, advanced data augmentation, hyperparameter optimization, and edge-optimized model deployment for real-time crop and weed detection.