TheCacophonyProject/classifier-pipeline
Exports tracked animals through thermal vision.
This project helps wildlife researchers and conservationists automatically identify and classify animals in thermal video footage. You provide thermal video files (CPTV format) from cameras, and it outputs a classified list of detected animals and a preview video, saving countless hours of manual review. It's designed for users who work with thermal imaging for ecological monitoring.
Available on PyPI.
Use this if you need to automatically detect and classify animals from large volumes of thermal camera recordings and want a system that learns from your existing data.
Not ideal if you're working with standard visible-light video, require real-time classification directly on edge devices without prior training, or only need basic motion detection.
Stars
22
Forks
14
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 26, 2026
Monthly downloads
389
Commits (30d)
0
Dependencies
24
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/TheCacophonyProject/classifier-pipeline"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
agentmorris/MegaDetector
MegaDetector is an AI model that helps conservation folks spend less time doing boring things...
microsoft/CameraTraps
PyTorch Wildlife: a Collaborative Deep Learning Framework for Conservation.
PetervanLunteren/AddaxAI
Simplify camera trap image analysis with AI species recognition models based around the...
maxsitt/insect-detect
Detection models and Python scripts for automated insect monitoring with the Insect Detect DIY...
ahmetozlu/color_recognition
:art: Color recognition & classification & detection on webcam stream / on video / on single...