Detecting animals in African Savanna with UAVs and the crowds

TL;DR

This paper presents a semi-automatic machine learning system for detecting large mammals in semi-arid Savanna using UAV imagery, enabling efficient wildlife monitoring and conservation efforts.

Contribution

It introduces a novel crowd-sourced annotated training approach and demonstrates effective detection of large mammals with affordable UAVs in semi-arid environments.

Findings

High recall rate in mammal detection

Effective false detection elimination by human operators

Feasibility of using standard RGB UAV imagery for wildlife monitoring

Abstract

Unmanned aerial vehicles (UAVs) offer new opportunities for wildlife monitoring, with several advantages over traditional field-based methods. They have readily been used to count birds, marine mammals and large herbivores in different environments, tasks which are routinely performed through manual counting in large collections of images. In this paper, we propose a semi-automatic system able to detect large mammals in semi-arid Savanna. It relies on an animal-detection system based on machine learning, trained with crowd-sourced annotations provided by volunteers who manually interpreted sub-decimeter resolution color images. The system achieves a high recall rate and a human operator can then eliminate false detections with limited effort. Our system provides good perspectives for the development of data-driven management practices in wildlife conservation. It shows that the detection of large mammals in semi-arid Savanna can be approached by processing data provided by standard RGB cameras mounted on affordable fixed wings UAVs.