Pri-matrix Factorization

Data scientists from more than 90 countries around the world drew on 300,000 video clips in a competition to build the best machine learning models for identifying wildlife from camera trap footage. The results are powerful and – equally important … #climate

€20,000 in prizes
dec 2017
320 joined

alt-text

Pri-matrix Factorization: Computer Vision for Wildlife Research and Conservation

Welcome to the African jungle! For centuries researchers have argued that a thorough understanding of the wildlife ecology in this majestic part of the world could reveal critical insights into our origins as humans. But understanding requires observation, and observation is often no easy –or safe– task. Human interference can disrupt the natural dynamics in these habitats, altering routes and behavior, making research that much harder. In recent years, automated surveillance systems called camera traps have helped tackle this problem. Camera traps are triggered by motion or heat, and passively record the behavior of species in the area without significantly disturbing their natural tendencies.

Still, camera traps can't yet automatically label the species they observe: it takes the valuable time of experts, or thousands of citizen scientists, to label this data. Can you help automate the species-tagging process, freeing up time and resources to focus on higher-level research and conservation efforts?

In this project, data tagging by a global community through the Chimp&See Zooniverse project feeds into algorithm development by a global community now reading this description. You'll find here one of the largest labeled camera trap datasets for you to test your skills and help researchers unlock the secrets of life on Earth!


Competition End Date:

Dec. 22, 2017, 11:59 p.m. UTC

Place Prize Amount
1st €12,000
2nd €6,000
3rd €2,000

Note: Prizes delivered by DrivenData in USD, based on the exchange rate on the challenge launch date.