Conser-vision Practice Area: Image Classification

Looking for a great way to start working with computer vision? This competition features a small dataset of wildlife captured by camera traps used in conservation research. #climate

advanced practice
1 year left
863 joined

About the data


We rely on Earth’s natural ecosystems every day. Healthy forests store carbon that would otherwise be emitted into the atmosphere. Animals and insects pollinate crops that yield food. Natural tourist destinations provide income for many low-resource communities. Protecting wild habitats helps prevent the spread of infectious diseases from animals to humans.

The health of these ecosystems depends on a varied and complex web of flora and fauna, called biodiversity. Today, we are facing a biodiversity crisis as more and more species become endangered or extinct.

Conservation efforts to monitor and protect biodiversity often involve tracking species in the wild. One of the best tools we have to study wildlife populations is camera traps. Camera traps can be triggered by movement or heat, providing enormous amounts of data observing the natural world without human interference.

An image of a chimpanzees captured by a camera trap

An image of two adult chimpanzees and a baby chimpanzee captured by a camera trap in Moyen-Bafing National Park, Republic of Guinea

Starting in 2017, DrivenData has been partnering with the Wild Chimpanzee Foundation and Max Planck Institute of Evolutionary Anthropology on Project Zamba (meaning "forest" in Lingala), a multi-year effort to build machine learning tools for camera trap videos and drastically accelerate the speed at which these videos can be processed and used. This team of conservation researchers has also made a set of their camera trap data available for the community to use to learn and practice. We're excited to see what you build!

Additional references:

From the DrivenData team:

More information on wildlife conservation and camera traps:

Getting started with image classification: