Automated detection of koalas using low-level aerial surveillance and machine learning

Corcoran, Evangeline; Denman, Simon; Hanger, Jon; Wilson, B. D.; Hamilton, Grant

doi:10.1038/s41598-019-39917-5

Cited by 72 publications

(135 citation statements)

References 38 publications

Supporting

Mentioning

133

Contrasting

Order By: Relevance

“…Furthermore, the methods we present can be expanded to other wildlife species or places where little to no data are available, particularly where thermal imaging via RPAS is an appropriate solution to any detection obstacles such as site inaccessibility and habitat complexity (e.g. [61]). Such efforts will help to close data gaps and provide the scientific information needed for enhanced conservation of vulnerable and protected species.…”

Section: Discussionmentioning

confidence: 99%

Using virtual reality and thermal imagery to improve statistical modelling of vulnerable and protected species

Leigh

Heron

Wilson

et al. 2019

Preprint

View full text Add to dashboard Cite

22Biodiversity loss and sparse observational data mean that critical conservation 23 decisions may be based on little to no information. Emerging technologies, such as airborne 24 thermal imaging and virtual reality, may facilitate species monitoring and improve 25 predictions of species distribution. Here we combined these two technologies to predict the 26 distribution of koalas, specialized arboreal foliovores facing population declines in many 27 parts of eastern Australia. For a study area in southeast Australia, we complemented ground-28 survey records with presence and absence observations from thermal-imagery obtained using 29 Remotely-Piloted Aircraft Systems. These field observations were further complemented 30 with information elicited from koala experts, who were immersed in 360-degree images of 31 the study area. The experts were asked to state the probability of observing a koala at sites 32 they viewed and to assign each probability a confidence rating. We fit logistic regression 33 models to the ground survey data and the ground plus thermal-imagery survey data and a beta 34 regression model to the expert elicitation data. We then combined parameter estimates from 35 the expert-elicitation model with those from each of the survey models to predict koala 36 presence and absence in the study area. The model that combined the ground, thermal-37 imagery and expert-elicitation data substantially reduced the uncertainty around parameter 38 estimates and increased the accuracy of classifications (koala presence vs absence), relative 39 to the model based on ground-survey data alone. Our findings suggest that data elicited from 40 experts using virtual reality technology can be combined with data from other emerging 41 technologies, such as airborne thermal-imagery, using traditional statistical models, to 42 increase the information available for species distribution modelling and the conservation of 43 vulnerable and protected species. Introduction 45In the face of unprecedented biodiversity loss, critical decisions are needed on the 46 conservation of vulnerable and protected species [1,2]. Unfortunately, information is seldom 47 available or dense enough in space and time to effectively inform those decisions [3].48 Monitoring programs often rely on observational records of species collected during ground 49 surveys. However, ground-based detection of vulnerable and protected species is difficult, 50 particularly when species are rare or elusive, and information may be biased towards single 51 or few individuals (e.g. radio-collared animals) or sites with high abundance [4,5].52 Furthermore, monitoring large areas using traditional ground-survey methods is logistically 53 and financially infeasible, and while professional monitoring may be time consuming and 54 expensive, volunteer data may be biased and of questionable quality [6,7]. These issues all 55 contribute towards the sparse data problem. 56Emerging technologies provide an opportunity to increase the spatial and temporal 57 coverage of data,...

show abstract

Section: Discussionmentioning

confidence: 99%

Using virtual reality and thermal imagery to improve statistical modelling of vulnerable and protected species

Leigh

Heron

Wilson

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The survey design and automated detection method used in this study are outlined in detail in Corcoran et al (2019). In brief, two sites north and south of Petrie Mill, Queensland were selected to carry out RPAS surveys of the koala population.…”

Section: Study Area and Survey Designmentioning

confidence: 99%

“…A FLIR Tau 2 640 thermal camera (FLIR, Wilsonville, Oregon, United States of America) was mounted to the underside for image collection. The drone flew at a height of 60 metres above the ground, 30 metres above the tree canopy, at a speed of 8 metres per second in transects 20 metres apart encompassing the entirety of each site (Corcoran et al 2019).…”

Section: Study Area and Survey Designmentioning

confidence: 99%

“…The same is true of the biases uniquely affecting automated detection methods, despite many studies demonstrating that computer vision is not impacted by the same constraints as the human eye (Conn et al 2014) The aim of this paper is to investigate the feasibility of integrating automated detections of koalas in RPASderived thermal imaging into an existing method of abundance estimation for wildlife developed by Terletzky and Koons (2016). Their approach was determined to come the closest of any existing modelling technique to addressing the errors inherent in the method used to survey koalas in a study by Corcoran et al (2019), as the number of missed animals and duplicate detections in surveys were calculated using telemetry to determine the presence and location of radio-collared animals within the survey area in a similar method to Terletzky & Koons (2016). These biases were then factored into a final estimate of abundance for each survey.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modelling wildlife species abundance using automated detections from drone surveillance

2019

El Sawah, S. (Ed.) MODSIM2019, 23rd International Congress on Modelling and Simulation.

View full text Add to dashboard Cite

Reliable estimates of abundance are critical to the conservation of threatened species. Aerial surveying is a sampling method that has been used to estimate wildlife abundance over large or inaccessible areas. An increasing trend in aerial surveying methodology is to use remotely piloted aircraft systems (RPAS), also known as drones, in lieu of traditional manned aircraft systems such as planes and helicopters. Studies which used RPAS instead of manned aircraft have recently attempted to analyse imagery using automated detection methods. While there are a number of advantages to this approach, there are also potential issues in abundance estimation using this data since the errors associated with using these approaches are largely unaccounted for in established models of abundance estimation. In this paper we applied a model developed by Terletzky and Koons (2016) for fixed wing survey, to data derived from RPAS surveys that has been processed by an automated detection method for koalas. The data collected enabled ground-truthing of detections which allowed both the probability of detection and the probability of duplicate detection to be accounted for in abundance estimates, as well as a comparison between the estimates and the true number of koalas present on site. Overall, it was found that the Terletzky & Koons (2016) method resulted in artificial inflation of abundance estimates when using data collected from RPAS surveys with automated detection. This is likely to have resulted from false positive detections, which can have a considerable impact on the accuracy of automated wildlife counts. Incorporating more sources of error than the probability of detection and duplicate detection appears to be essential to improving abundance estimation for these novel survey methods. An exploration of additional covariates that could affect detection in RPAS-derived thermal imaging due the unique constraints of these technologies should be considered in future model development.

show abstract

“…Nowadays, aerial accounting often requires the use of drone planes and copters equipped with various sensors and cameras [20][21][22][23][24][25][26][27][28][29][30][31]. Unmanned aerial vehicles (UAV) equipped with radio receivers can track the routes of animals with GPS collars, i.e.…”

Section: Introductionmentioning

confidence: 99%

Drone-Assisted Aerial Surveys of Large Animals in Siberian Winter Forests

Atuchin

Prosekov²,

Vesnina³

et al. 2020

Preprint

View full text Add to dashboard Cite

There are two main reasons for monitoring the population of forest animals. First of all, regular surveys reveal the real state of biodiversity. Second, they guarantee a prompt response to any negative environmental factor that affects the animal population and make it possible to eliminate the threat before any permanent damage has been done. The research objective was to study the potential of drone planes equipped with thermal infrared imaging cameras. Drone planes proved effective in covering large areas, while thermal infrared cameras provided accurate statistics in the harsh winter conditions of Siberia. The research featured the population of the European elk (Alces alces), which is gradually deteriorating due to poaching and deforestation. The surveyed territory included the Salair State Nature Reserve in the Kemerovo Region, or Kuzbass (Russia). The authors developed an effective methodology for processing the data obtained from drone-mounted thermal infrared cameras. The research provided reliable results concerning the changes in the elk population on the territory in question. The use of drone planes proved an effective means of ungulate animal survey on large areas of Siberian winter forests.

show abstract

Automated detection of koalas using low-level aerial surveillance and machine learning

Cited by 72 publications

References 38 publications

Using virtual reality and thermal imagery to improve statistical modelling of vulnerable and protected species

Using virtual reality and thermal imagery to improve statistical modelling of vulnerable and protected species

Modelling wildlife species abundance using automated detections from drone surveillance

Drone-Assisted Aerial Surveys of Large Animals in Siberian Winter Forests

Contact Info

Product

Resources

About