Drone-based thermal remote sensing provides an effective new tool for monitoring the abundance of roosting fruit bats

被引:32
作者
McCarthy, Eliane D. [1 ]
Martin, John M. [2 ]
Boer, Matthias M. [1 ]
Welbergen, Justin A. [1 ]
机构
[1] Western Sydney Univ, Hawkesbury Inst Environm, Richmond, NSW 2753, Australia
[2] Taronga Conservat Soc Australia, Inst Sci & Learning, Bradleys Head Rd, Mosman, NSW 2088, Australia
关键词
Computer vision; flying-fox; infrared; machine learning; orthomosaic; remotely piloted aircraft; FLYING-FOXES; AUTOMATED DETECTION; PTEROPODIDAE; CHIROPTERA; LANDSCAPE; COUNTS; BURROWS; SYSTEMS; IMAGERY; ISLAND;
D O I
10.1002/rse2.202
中图分类号
Q14 [生态学(生物生态学)];
学科分类号
071012 ; 0713 ;
摘要
Accurate and precise monitoring of species abundance is essential for determining population trends and responses to environmental change. However, traditional population survey methods can be unreliable and labour-intensive, which complicates the effective conservation and management of many threatened species. We developed a method of using drone-acquired thermal orthomosaics to monitor the abundance of grey-headed flying-foxes (Pteropus poliocephalus) within tree roosts, an IUCN Red Listed species of bat. We assessed the accuracy and precision of this new method and evaluated the performance of four semi-automated methods for counting flying-foxes in thermal orthomosaics, including machine learning and Computer Vision (CV) methods. We found a high concordance between the number of flying-foxes manually counted in drone-acquired thermal imagery and the true abundance of flying-foxes in single roost trees, as obtained from direct on-ground observation. This indicated that the number of flying-foxes observed in thermal imagery accurately reflected the true abundance of flying-foxes. In addition, for thermal orthomosaics of whole roost sites, the number of flying-foxes manually counted was highly repeatable between the same-day drone surveys and human counters, indicating that this method produced highly precise abundance estimates independent of the identity/experience of human counters. Finally, the number of flying-foxes manually counted in drone-acquired thermal orthomosaics was highly concordant with the counts derived from CV and machine learning-enabled classification techniques. This indicated that accurate and precise measures of colony abundance can be obtained semi-automatically, thus greatly reducing the amount of human effort involved for obtaining abundance estimates. Our method is thus valuable for reliably monitoring the abundance of individuals in flying-fox roosts and will aid in the conservation and management of this globally threatened group of flying-mammals, as well as other homeothermic arboreal-roosting species.
引用
收藏
页码:461 / 474
页数:14
相关论文
共 76 条
[51]   Control of pest mammals for biodiversity protection in Australia. I. Patterns of control and monitoring [J].
Reddiex, Ben ;
Forsyth, David M. ;
McDonald-Madden, Eve ;
Einoder, Luke D. ;
Griffioen, Peter A. ;
Chick, Ryan R. ;
Robley, Alan J. .
WILDLIFE RESEARCH, 2006, 33 (08) :691-709
[52]   Geographical sampling bias and its implications for conservation priorities in Africa [J].
Reddy, S ;
Dávalos, LM .
JOURNAL OF BIOGEOGRAPHY, 2003, 30 (11) :1719-1727
[53]  
Schindelin J, 2012, NAT METHODS, V9, P676, DOI [10.1038/NMETH.2019, 10.1038/nmeth.2019]
[54]   A REVIEW OF ESTIMATING ANIMAL ABUNDANCE [J].
SEBER, GAF .
BIOMETRICS, 1986, 42 (02) :267-292
[55]   Automated detection and enumeration of marine wildlife using unmanned aircraft systems (UAS) and thermal imagery [J].
Seymour, A. C. ;
Dale, J. ;
Hammill, M. ;
Halpin, P. N. ;
Johnston, D. W. .
SCIENTIFIC REPORTS, 2017, 7
[56]   Landscape-scale redistribution of a highly mobile threatened species, Pteropus conspicillatus (Chiroptera, Pteropodidae), in response to Tropical Cyclone Larry [J].
Shilton, Louise A. ;
Latch, Peter J. ;
McKeown, Adam ;
Pert, Petina ;
Westcott, David A. .
AUSTRAL ECOLOGY, 2008, 33 (04) :549-561
[57]  
Signorell A., 2021, DESCTOOLS TOOLS DESC
[58]   Thermal Infrared Imaging from Drones Offers a Major Advance for Spider Monkey Surveys [J].
Spaan, Denise ;
Burke, Claire ;
McAree, Owen ;
Aureli, Filippo ;
Rangel-Rivera, Coral E. ;
Hutschenreiter, Anja ;
Longmore, Steve N. ;
McWhirter, Paul R. ;
Wich, Serge A. .
DRONES, 2019, 3 (02) :1-19
[59]   Polar Bears from Space: Assessing Satellite Imagery as a Tool to Track Arctic Wildlife [J].
Stapleton, Seth ;
LaRue, Michelle ;
Lecomte, Nicolas ;
Atkinson, Stephen ;
Garshelis, David ;
Porter, Claire ;
Atwood, Todd .
PLOS ONE, 2014, 9 (07)
[60]   Machine learning to classify animal species in camera trap images: Applications in ecology [J].
Tabak, Michael A. ;
Norouzzadeh, Mohammad S. ;
Wolfson, David W. ;
Sweeney, Steven J. ;
Vercauteren, Kurt C. ;
Snow, Nathan P. ;
Halseth, Joseph M. ;
Di Salvo, Paul A. ;
Lewis, Jesse S. ;
White, Michael D. ;
Teton, Ben ;
Beasley, James C. ;
Schlichting, Peter E. ;
Boughton, Raoul K. ;
Wight, Bethany ;
Newkirk, Eric S. ;
Ivan, Jacob S. ;
Odell, Eric A. ;
Brook, Ryan K. ;
Lukacs, Paul M. ;
Moeller, Anna K. ;
Mandeville, Elizabeth G. ;
Clune, Jeff ;
Miller, Ryan S. .
METHODS IN ECOLOGY AND EVOLUTION, 2019, 10 (04) :585-590