Machine Learning for Conservation
Machine learning has gone from a relatively niche field of academic research in the 80s and 90s to powering everyday services, self-driving cars, and data analyses. Since 2012, the explosion of machine learning has largely been facilitated by advances in the graphics processing units (GPUs) and the availability of massive labeled datasets.
The CBC is committed to advancing and promoting the use of machine learning for the understanding and conservation of biodiversity by:
We recently launched the collaborative Animal Detection Network with the aim to advance the use of machine learning and developing opensource tools and workflows for the automated identification and counting of animal species in images, video, and audio. Annotating images from camera traps, the team completed a simple proof-of-concept for near real-time detection and counting of birds visiting a feeder as part of the network's flagship project Species Identification and Localization in Camera Trap Images.
