SDZWA Conservation Technology Lab
Developing open-source technology and machine learning tools for wildlife conservation
SDZWA Conservation Technology Lab
Developing open-source technology and machine learning tools for wildlife conservation
Explore our core open-source conservation technology projects.
A package available in Python and R for AI-assisted camera trap image processing.
The AniML package provides functions for ingesting raw image and video files and outputs predictions for species using region-specific species classifier models. We provide several species models including for the African Savanna, the Peruvian Amazon, the Andes mountains, and the Western US. AniML provides the results in a number of export formats, including TimeLapse and CamTrapDP. The package also includes AI-based re-indentification tools and custom species model training.
For more information, see:
AniML (Python Package)
AniML (R Library)
AniML-Lite
A desktop application for Windows and Linux for AI-assisted re-identification of patterned animals.
MatchyPatchy ingests either raw image/video files or a .csv list of images, calculates vector embeddings of the images, and presents the user with potential matches based on similarity of the vectors. MatchyPatchy can be used with a set of reference images of named individuals, or from scratch on a set of data where no individuals are indentified yet.
For more information, see: MatchyPatchy