Camera traps are critical tools in research and conservation efforts because they allow ecologists, biologists, and other researchers to study valuable footage of wildlife without human interference. 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.
Zamba uses state-of-the-art computer vision and artificial intelligence to perform intensive camera trap video processing work, freeing up more time for humans to focus on interpreting the content and using the results.
Zamba is freely available for anyone to use! Some of the key tasks that Zamba can automate are:
Zamba is already trained to classify 32 species common to Africa and 11 species common to Europe.If you have your own labeled videos, Zamba can generate a new model adapted to your use case. You can even retrain Zamba to predict an entirely new set of species - the world is your oyster! (We'd love to see a model trained to predict oysters.)
Zamba means forest in Lingala. Lingala is one of many Bantu languages of central Africa, and is spoken throughout the Democratic Republic of the Congo and the Republic of the Congo. The first ever Homo sapiens emerged in African forests and savannas, and African zambas may hold the keys to unlocking critical mysteries of human evolution.
Zamba Cloud is a web application where you can use the zamba algorithms by just uploading videos or pointing to where they are stored. Zamba Cloud is created for conservation researchers and wildlife experts who aren’t familiar with using a programming interface. If you’d like all of the functionality of zamba without any of the code, this is for you!
Zamba is also provided as an open source package that can be run in the command line or imported as a Python library. If you’d like to interact with zamba through a programming interface, hack away! Visit the zamba package documentation for details and user tutorials.
Zamba is trained on over 27,000 camera trap videos spanning 42 common species. It can also identify blank videos and videos that contain humans. Videos were manually classified by researchers and thousands of citizen scientists, generating over 2,000 hours of labeled camera trap footage.
Data for central and West Africa was collected and annotated by partners at The Max Planck Institute for Evolutionary Anthropology and Chimp & See. The data includes camera trap videos from:
Data for Europe was collected and annotated by partners at The Max Planck Institute for Evolutionary Anthropology from Hintenteiche bei Biesenbrow, Germany. The zamba model trained for settings in Europe can recognize 11 common species, including humans. The most common species are deer and boars, and the least common are weasels, hares, and domestic cats.
As part of the Pan African Programme: The Cultured Chimpanzee, over 8,000 hours of camera trap footage has been collected across various chimpanzee habitats from camera traps in 15 African countries. Labeling the species in this footage is no small task. It takes a lot of time to determine whether or not there are any animals present in the data, and if so, which ones.
To date, thousands of citizen scientists have manually labeled video data through the Chimp&See Zooniverse project. In partnership with experts at The Max Planck Institute for Evolutionary Anthropology (MPI-EVA), this effort fed into a well-labeled dataset of nearly 2000 hours of camera trap footage from Chimp&See's database.
Using this dataset, DrivenData and MPI-EVA ran a machine learning challenge where hundreds of data scientists competed to build the best algorithms for automated species detection. The top 3 submissions that were best able to predict the presence and type of wildlife across new videos won the challenge and received €20,000 in monetary prizes. The winning techniques developed from this challenge provided a starting point for the algorithms behind Project Zamba.
The code developed for Project Zamba is openly available for anyone to learn from and use. You can find the latest version of the project codebase on GitHub.
Thanks to all the participants in the Pri-Matrix Factorization Challenge! Special thanks to Dmytro Poplovskiy (@dmytro), developer of the top-performing solution adapted for Project Zamba, the project team at the Max Planck Institute for Evolutionary Anthropology for organizing the competitions and the data, and to the ARCUS Foundation for generously funding this project.