We've partnered with Driven Data and the ARCUS foundation to offer a new €20,000 challenge that takes data scientists deep into the jungles of Africa. Camera traps are useful for non-invasive observation of wildlife and have the potential to free up huge amounts of research time -- but they can't yet automatically flag and label the species they observe.
In this project, a global community has annotated videos through the Chimp&See Zooniverse project, and now its time for the data scientist community to turn those labels into algorithms! You'll find here one of the largest labeled camera trap datasets for you to practice your skills and help researchers delve into the secrets of life on Earth!
Utilizing both crowdsourced labels as well as crowdsourced algorithms, this ambitious computer vision competition is in a league of its own. The winning techniques developed here will provide a starting point for production-level automated species tagging for use in camera trap systems around the world. By decreasing the time that experts spend watching empty footage, we can improve their ability to focus on the outcomes that matter most.
On Chimp&See people from around the world have been recording what they see in each video but they also carry out more complex tasks such as identifying unique chimpanzee individuals and tagging primates and other animals to the species level. With this competition we hope to use machine learning to accomplish the first task more time efficiently thereby allowing citizen scientists to focus on the more complex tasks of the project!
No comments:
Post a Comment