PyTorch Wildlife: a Collaborative Deep Learning Framework for Conservation.

This repo contains code+pre-trained models for extracting information from camera-trap images. The pre-trained models have been trained on the Snapshot Serengeti dataset.

A Python package for identifying hundreds of kinds of animals, training custom models, and estimating distance from camera trap videos and images

An online toolset to manage and analyze data collected from insect camera traps for research and conservation efforts.

Distance Estimation for Estimating Animal Abundance

Bounding Box Editor and Exporter

📷🦔 CamTrapML Python Library for Detecting, Classifying, and Analysing Camera Trap Imagery.

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 Desktop: Simple Interface for Detection of Humans, Animals and Vehicles in Camera Trap Imagery

Data Carpentry for Camera Traps

Run MegaDetector to Detect Animals, Vehicles and Humans in Camera Trap Imagery on Cog / Replicate

COCO-CameraTrap Indexer. An extension to pycocotools including location and sequence indexing.

CV pipeline for bear detection in wildlife camera traps — YOLOv8 detection & segmentation, SORT multi-object tracking, MobileNetV2 classification. Fine-tuned on 1,172 images · mAP@0.5 0.96

Python Library for Camtrap Data Packages

My personal pipeline to species identification on camera trap pix using deep learning, detection/classification with MegaDetector and RetinaNet

Code and supplementary material for "SOCRATES: Introducing Depth in Visual Wildlife Monitoring using Stereo Vision" (WIP)

Classifier for horses cropped from camera trap images

Classifier for vehicles cropped from camera trap images

Workflow and validation toolkit for human review of wildlife AI outputs

Animal Classifier for camera trap images. Uses EVA02 model to identify species, extract metadata, and export results to Excel.