Automated detection of wildlife using drones: Synthesis, opportunities and constraints

TLDR

Accurate detection of individual wildlife is essential for conservation but is difficult and costly, especially for species in wide or inaccessible areas, and while drones are increasingly used to cover large areas, the constraints of automated detection remain poorly understood. The study reviewed the last five years of research on automatic wildlife detection from drone imagery to assess how technology, environment, and species traits affect detection success. The authors surveyed studies that employed machine‑learning algorithms to automatically detect wildlife in drone imagery, comparing fixed‑wing and multirotor platforms and RGB versus infrared sensors. The review showed that automated detection works for a broader range of species and conditions than previously reported, with high success using fixed‑wing RGB platforms for large species in open habitats, and requiring infrared sensors and multirotor platforms for small, elusive species in complex environments, thereby enabling more accurate and efficient abundance surveys for vulnerable populations.

Abstract

Abstract Accurate detection of individual animals is integral to the management of vulnerable wildlife species, but often difficult and costly to achieve for species that occur over wide or inaccessible areas or engage in cryptic behaviours. There is a growing acceptance of the use of drones (also known as unmanned aerial vehicles, UAVs and remotely piloted aircraft systems, RPAS) to detect wildlife, largely because of the capacity for drones to rapidly cover large areas compared to ground survey methods. While drones can aid the capture of large amounts of imagery, detection requires either manual evaluation of the imagery or automated detection using machine learning algorithms. While manual evaluation of drone‐acquired imagery is possible and sometimes necessary, the powerful combination of drones with automated detection of wildlife in this imagery is much faster and, in some cases, more accurate than using human observers. Despite the great potential of this emerging approach, most attention to date has been paid to the development of algorithms, and little is known about the constraints around successful detection (P. W. J. Baxter, and G. Hamilton, 2018, Ecosphere , 9 , e02194). We reviewed studies that were conducted over the last 5 years in which wildlife species were detected automatically in drone‐acquired imagery to understand how technological constraints, environmental conditions and ecological traits of target species impact detection with automated methods. From this review, we found that automated detection could be achieved for a wider range of species and under a greater variety of environmental conditions than reported in previous reviews of automated and manual detection in drone‐acquired imagery. A high probability of automated detection could be achieved efficiently using fixed‐wing platforms and RGB sensors for species that were large and occurred in open and homogeneous environments with little vegetation or variation in topography while infrared sensors and multirotor platforms were necessary to successfully detect small, elusive species in complex habitats. The insight gained in this review could allow conservation managers to use drones and machine learning algorithms more accurately and efficiently to conduct abundance data on vulnerable populations that is critical to their conservation.