Zamba: Computer vision for wildlife conservation
Authors:
- Emily DorneEDEmily Dorne
- Jay QiJQJay Qi
- Peter BullPBPeter Bull
- Mattia BessoneMBMattia Bessone
- Benjamin DebetencourtBDBenjamin Debetencourt
- Barbara FruthBFBarbara Fruth
- David MorganDMDavid Morgan
- Meredith S. PalmerMPMeredith S. Palmer
- Crickette SanzCSCrickette Sanz
- Janika WendefeuerJWJanika Wendefeuer
- Catherine CrockfordCCCatherine Crockford
Open Access
- 10 July 2025
- conference paper
- Published by NumFOCUS - Insight Software Consortium (ITK)
- p. 85-111
Abstract
We present Zamba, an open source Python package designed to streamline camera trap data processing through machine learning. Zamba supports inference and custom model training for species classification on videos and images, as well as depth estimation inference for videos.Keywords
This publication has 44 references indexed in Scilit:
- Highly precise community science annotations of video camera‐trapped fauna in challenging environmentsRemote Sensing in Ecology and Conservation, 2024
- Camera traps unveil demography, social structure, and home range of six unhabituated Western chimpanzee groups in the Moyen Bafing National Park, GuineaAmerican Journal of Primatology, 2023
- A semi‐automated camera trap distance sampling approach for population density estimationRemote Sensing in Ecology and Conservation, 2023
- Chimpanzee identification and social network construction through an online citizen science platformEcology and Evolution, 2020
- Camera trapping reveals trends in forest duiker populations in African National ParksRemote Sensing in Ecology and Conservation, 2019
- Camera traps provide a robust alternative to direct observations for constructing social networks of wild chimpanzeesAnimal Behaviour, 2019
- Recognition in Terra Incognita2018
- A review of camera trapping for conservation behaviour researchRemote Sensing in Ecology and Conservation, 2017
- Effective sociodemographic population assessment of elusive species in ecology and conservation managementEcology and Evolution, 2013
- Risky business or simple solution – Relative abundance indices from camera-trappingBiological Conservation, 2013