megadetector

Microsoft AI for Good Lab — Biodiversity research hub. Open-source AI models, edge devices, and tools for biodiversity monitoring and conservation. Your source for MegaDetector, SPARROW, PytorchWildlife, Bioacoustics, and more.

MegaDetector is an AI model that helps conservation folks spend less time doing boring things with camera trap images.

AI-assisted camera trap analysis: detection, species recognition, verification, dashboards and exports. Free, open source, for Windows, macOS and Linux.

SPARROW — Solar-Powered Acoustic and Remote Recording Observation Watch. An AI-enabled edge device for biodiversity monitoring with camera-trap imaging and bioacoustic recording. By Microsoft AI for Good Lab.

Detect Animals, Humans and Vehicles in Camera Trap Imagery. Powered by MegaDetector v5.

MegaDetector V6 — Microsoft AI for Good Lab's open-source model that detects animals, people, and vehicles in camera-trap images, filtering blanks to speed wildlife research.

A desktop application that makes using MegaDetector's model easier

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.

MegaDetector models served over FastAPI & visualized with Streamlit

MegaDetector-Acoustic — The Microsoft open-source AI for bioacoustic biodiversity monitoring. Audio classification and species identification from sound recordings, for terrestrial bioacoustics. Maintained by Microsoft AI for Good Lab. Part of the Pytorch-Wildlife ecosystem.

The Image Level Label to Bounding Box (IL2BB) pipeline automates the generation of labeled bounding boxes by leveraging an organization’s previous labeling efforts.

MegaDetector-Classifier — The Microsoft open-source AI for camera-trap species classification. Fine-tuning and inference for wildlife identification, running downstream of MegaDetector animal detection. Maintained by Microsoft AI for Good Lab. Part of the Pytorch-Wildlife ecosystem.

Open-source wildlife detection, segmentation & tracking in video.

TeraiNet is a species classification model focussed on the Terai region in Nepal to support Bengal tiger conservation

Docker image for running the MegaDetector v4 camera-trap object detection model.

Instructions to export megadetector v5 from PyTorch to ONNX and tools to use the exported model.

Classifier for vehicles cropped from camera trap images

Guidance for image-based identification of traded animals in highly occluded contexts.

Aplicación de estrategias de deep-learning para la detección de animales en imágenes de fototrampeo

Local backyard wildlife webcam rig - motion-gated MegaDetector v6 capture with species ID, individual re-ID, behaviour clips, and a live dashboard.