Unmanned Aerial Vehicles (UAVs) and Artiﬁcial Intelligence Revolutionizing Wildlife Monitoring and Conservation
Luis F. Gonzalez 1,*, Glen A. Montes 1, Eduard Puig 1, Sandra Johnson 2, Kerrie Mengersen 2 and Kevin J. Gaston 3
1 Australian Research Centre for Aerospace Automation (ARCAA), Queensland University of Technology (QUT) 2 George St, Brisbane QLD 4000, Australia; (G.A.M.); (E.P.)
2 ARC Centre of Excellence for Mathematical & Statistical Frontiers (ACEMS), Queensland University of Technology (QUT), 2 George St, Brisbane QLD 4000, Australia; (S.J.); (K.M.)
Surveying threatened and invasive species to obtain accurate population estimates is an important but challenging task that requires a considerable investment in time and resources. Estimates using existing ground-based monitoring techniques, such as camera traps and surveys performed on foot, are known to be resource intensive, potentially inaccurate and imprecise, and difﬁcult to validate. Recent developments in unmanned aerial vehicles (UAV), artiﬁcial intelligence and miniaturized thermal imaging systems represent a new opportunity for wildlife experts to inexpensively survey relatively large areas. The system presented in this paper includes thermal image acquisition as well as a video processing pipeline to perform object detection, classiﬁcation and tracking of wildlife in forest or open areas. The system is tested on thermal video data from ground based and test ﬂight footage, and is found to be able to detect all the target wildlife located in the surveyed area. The system is ﬂexible in that the user can readily deﬁne the types of objects to classify and the object characteristics that should be considered during classiﬁcation.