When you can't see the koalas for the trees: Using drones and machine learning in complex environments

Hamilton, Grant; Corcoran, Evangeline; Denman, Simon; Hennekam, Molly Ellis; Koh, Lian Pin

doi:10.1016/j.biocon.2020.108598

Cited by 11 publications

(24 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These rely on evidence of occupancy and activity such as scratch marks, scats, citizen sightings, and bellows [3,20,22,24,25]. In contrast, the application of direct techniques, such as diurnal strip-width [10,26,27] and line-transects [10], nocturnal line-transects [3], and emerging remotely piloted aircraft system thermal imaging (RPAS, also known as drones) technologies [8,[28][29][30], require surveyors to physically sight koalas and this is preferable for density and population estimates [3].…”

Section: Introductionmentioning

confidence: 99%

“…For example, RPAS can be coupled with sensors and infrared detectors that capture high-resolution thermal images [41]. RPAS are particularly promising for surveying wildlife [42,43] and have been accurate and cost-effective in determining abundance [43] and for detecting a range of species including arboreal mammals such as monkeys [44] and koalas [8,[28][29][30].…”

Section: Introductionmentioning

confidence: 99%

“…RPAS thermal imaging technology has been used to initiate the development of automated machine learning algorithms that are designed to detect koalas from thermal imagery data [8,28]. These algorithms were trained by surveying radio-tracked koalas in Petrie, Queensland and detections were validated by ground survey data collected on the same day [8].…”

Section: Introductionmentioning

confidence: 99%

“…These algorithms were trained by surveying radio-tracked koalas in Petrie, Queensland and detections were validated by ground survey data collected on the same day [8]. Additionally, the method was employed to detect koalas during several one hectare plot surveys of a uniform moderately dense Eucalytpus globulus plantation on Kangaroo Island, South Australia [28]. In both cases thermal signatures were not validated in field, but rather during ex situ automated and manual frame by frame examination of footage post-hoc [8,28].…”

Section: Introductionmentioning

confidence: 99%

“…RPAS thermal imaging technology has achieved koala detection in all seasons of the year in parkland and plantations, but has only achieved detection of wild koalas in natural bushland in winter [29], and this work was completed alongside the present study. RPAS thermal imaging technology for both the manual and automated detection of koalas is still in development, seasonal differences in precision and koala detection at variable speed and altitude have not been investigated [8,[28][29][30], and machine learning algorithms require further training [8,28]. Despite this, and a claim of 'higher precision achieved' against traditional ground survey methods [8,28], RPAS-derived methods have not been formally compared to other more widely used techniques.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Real-time drone derived thermal imagery outperforms traditional survey methods for an arboreal forest mammal

et al. 2020

View full text Add to dashboard Cite

Koalas (Phascolarctos cinereus) are cryptic and currently face regional extinction. The direct detection (physical sighting) of individuals is required to improve conservation management strategies. We provide a comparative assessment of three survey methods for the direct detection of koalas: systematic spotlighting (Spotlight), remotely piloted aircraft system thermal imaging (RPAS), and the refined diurnal radial search component of the spot assessment technique (SAT). Each survey method was repeated on the same morning with independent observers (03:00–12:00 hrs) for a total of 10 survey occasions at sites with fixed boundaries (28–76 ha) in Port Stephens (n = 6) and Gilead (n = 1) in New South Wales between May and July 2019. Koalas were directly detected on 22 occasions during 7 of 10 comparative surveys (Spotlight: n = 7; RPAS: n = 14; and SAT: n = 1), for a total of 12 unique individuals (Spotlight: n = 4; RPAS: n = 11; SAT: n = 1). In 3 of 10 comparative surveys no koalas were detected. Detection probability was 38.9 ± 20.03% for Spotlight, 83.3 ± 11.39% for RPAS and 4.2 ± 4.17% for SAT. Effective detectability per site was 1 ± 0.44 koalas per 6.75 ± 1.03 hrs for Spotlight (1 koala per 6.75 hrs), 2 ± 0.38 koalas per 4.35 ± 0.28 hrs for RPAS (1 koala per 2.18 hrs) and 0.14 ± 0.14 per 6.20 ± 0.93 hrs for SAT (1 koala per 43.39 hrs). RPAS thermal imaging technology appears to offer an efficient method to directly survey koalas comparative to Spotlight and SAT and has potential as a valuable conservation tool to inform on-ground management of declining koala populations.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real-time drone derived thermal imagery outperforms traditional survey methods for an arboreal forest mammal

et al. 2020

View full text Add to dashboard Cite

show abstract

Evaluating new technology for biodiversity monitoring: Are drone surveys biased?

Corcoran

Denman

Hamilton

2021

Ecology and Evolution

Self Cite

View full text Add to dashboard Cite

Drones and machine learning‐based automated detection methods are being used by ecologists to conduct wildlife surveys with increasing frequency. When traditional survey methods have been evaluated, a range of factors have been found to influence detection probabilities, including individual differences among conspecific animals, which can thus introduce biases into survey counts. There has been no such evaluation of drone‐based surveys using automated detection in a natural setting. This is important to establish since any biases in counts made using these methods will need to be accounted for, to provide accurate data and improve decision‐making for threatened species. In this study, a rare opportunity to survey a ground‐truthed, individually marked population of 48 koalas in their natural habitat allowed for direct comparison of the factors impacting detection probability in both ground observation and drone surveys with manual and automated detection. We found that sex and host tree preferences impacted detection in ground surveys and in manual analysis of drone imagery with female koalas likely to be under‐represented, and koalas higher in taller trees detected less frequently when present. Tree species composition of a forest stand also impacted on detections. In contrast, none of these factors impacted on automated detection. This suggests that the combination of drone‐captured imagery and machine learning does not suffer from the same biases that affect conventional ground surveys. This provides further evidence that drones and machine learning are promising tools for gathering reliable detection data to better inform the management of threatened populations.

show abstract

Counting animals in aerial images with a density map estimation model

Qian

Humphries²,

Trathan

et al. 2023

Ecology and Evolution

View full text Add to dashboard Cite

Animal abundance estimation is increasingly based on drone or aerial survey photography. Manual postprocessing has been used extensively; however, volumes of such data are increasing, necessitating some level of automation, either for complete counting, or as a labour-saving tool. Any automated processing can be challenging when using such tools on species that nest in close formation such as Pygoscelis penguins. We present here a customized CNN-based density map estimation method for counting of penguins from low-resolution aerial photography. Our model, an indirect regression algorithm, performed significantly better in terms of counting accuracy than standard detection algorithm (Faster-RCNN) when counting small objects from low-resolution images and gave an error rate of only 0.8 percent. Density map estimation methods as demonstrated here can vastly improve our ability to count animals in tight aggregations and demonstrably improve monitoring efforts from aerial imagery.

show abstract

When you can't see the koalas for the trees: Using drones and machine learning in complex environments

Cited by 11 publications

References 31 publications

Real-time drone derived thermal imagery outperforms traditional survey methods for an arboreal forest mammal

Real-time drone derived thermal imagery outperforms traditional survey methods for an arboreal forest mammal

Evaluating new technology for biodiversity monitoring: Are drone surveys biased?

Counting animals in aerial images with a density map estimation model

Contact Info

Product

Resources

About