A QGIS plugin for tree monitoring using AI.
MegaDetector-Overhead — The Microsoft open-source AI for overhead wildlife detection. Point-based detection model for aerial and drone imagery, identifying wildlife from above. Maintained by Microsoft AI for Good Lab. Part of the Pytorch-Wildlife ecosystem.
GreenShield Mobile App
This repository provides a tutorial and code for reproducing the data and results presented in the following publication: Automated Mapping of Post-Storm Roof Damage Using Deep Learning and Aerial Imagery: A Case Study in the Caribbean (Kucharczyk, Nesbit, & Hugenholtz, 2025, Remote Sensing).
Semantic segmentation of drone imagery using U-Net deep learning architecture | TensorFlow/Keras implementation with automated preprocessing and multi-class pixel classification | Dron görüntülerinin U-Net ile semantik segmentasyonu
Final Year Project developed for my BSc (Hons) in Computing.
Tiered edge AI land cover classification across ESP32, STM32, and Jetson Nano — the same task, scoped and quantized differently for each board's memory budget.
Drone GeoTIFF üzerinde genç mısır segmentasyonu, sıra analizi ve aday ekim boşluğu tespiti
DNN-derived synthetic vegetation index for agronomic trait prediction from multispectral drone imagery
Genomic and phenomic prediction of agronomic traits and malt quality in NY Winter Malting Barley
AI-powered traffic analysis system for detecting and tracking road users from aerial drone footage.
Deep learning pipeline (YOLOv5 + Detectron2) for detecting maize tassels in UAV imagery — CSE499 senior design project.
A modern desktop app for calculating areas from UAV-captured GeoTIFFs and shapefiles. Features support for alpha masking, automatic UTM projection, clean map overlays, and precise dimension reporting.
Technical and architecture documentation of a precision-agriculture object detection pipeline (YOLO + SAHI, geospatial export, COCO evaluation). Sanitized public release — documentation only, no source code or client data.
End-to-end drone remote sensing platform: schema-agnostic data pipeline, GeoLibre-based GIS mapping with IDW heat-surface interpolation, OpenCV computer vision for land-cover classification, and AI-assisted automated reporting — built with Streamlit.
Field-based spatial data science with GPS trajectories, temperature interpolation, and multispectral drone imagery from the Cass field trip.
Drone-based livestock detection system using YOLOv8 for identifying and counting sheep in aerial imagery. Includes dataset details, training pipeline, model weights, and Colab notebook.
UNet-based density estimation framework for automated elephant counting using UAV imagery.
DroneSeg is a full-stack semantic segmentation platform for drone/aerial imagery. Upload drone photos, run SegFormer-B2 deep learning inference to generate land-cover classification masks with bounding boxes and visualize results on an interactive map and GeoJSON export.
End-to-end MLOps pipeline for 5-class semantic segmentation of drone imagery using nnU-Net (PyTorch). Features DVC, Docker, BentoML serving & CI/CD.
To associate your repository with the drone-imagery topic, visit your repo's landing page and select "manage topics."