Quantifying the movement, behaviour and environmental context of group-living animals using drones and computer vision

被引:40
作者
Koger, Benjamin [1 ,2 ,3 ]
Deshpande, Adwait [1 ,2 ,3 ]
Kerby, Jeffrey T. T. [4 ,5 ,6 ]
Graving, Jacob M. M. [1 ,2 ,3 ,7 ]
Costelloe, Blair R. R. [1 ,2 ,3 ]
Couzin, Iain D. D. [1 ,2 ,3 ]
机构
[1] Max Planck Inst Anim Behav, Dept Collect Behav, Constance, Germany
[2] Univ Konstanz, Ctr Adv Study Collect Behav, Constance, Germany
[3] Univ Konstanz, Dept Biol, Constance, Germany
[4] Aarhus Univ, Aarhus Inst Adv Studies, Aarhus, Denmark
[5] Dartmouth Coll, Neukom Inst Computat Sci, Hanover, NH USA
[6] Aarhus Univ, Dept Biol, Sect Ecoinformat & Biodivers, Aarhus, Denmark
[7] Max Planck Inst Anim Behav, Adv Res Technol Unit, Constance, Germany
基金
欧盟地平线“2020”; 瑞士国家科学基金会;
关键词
behavioural tracking; computer vision; drones; environmental reconstruction; gelada monkey; pose; posture; video analysis; wildlife; zebra; ORGANIZATION; VIGILANCE; ECOLOGY; CLIMATE; SHOW;
D O I
10.1111/1365-2656.13904
中图分类号
Q14 [生态学(生物生态学)];
学科分类号
071012 ; 0713 ;
摘要
Methods for collecting animal behaviour data in natural environments, such as direct observation and biologging, are typically limited in spatiotemporal resolution, the number of animals that can be observed and information about animals' social and physical environments. Video imagery can capture rich information about animals and their environments, but image-based approaches are often impractical due to the challenges of processing large and complex multi-image datasets and transforming resulting data, such as animals' locations, into geographical coordinates. We demonstrate a new system for studying behaviour in the wild that uses drone-recorded videos and computer vision approaches to automatically track the location and body posture of free-roaming animals in georeferenced coordinates with high spatiotemporal resolution embedded in contemporaneous 3D landscape models of the surrounding area. We provide two worked examples in which we apply this approach to videos of gelada monkeys and multiple species of group-living African ungulates. We demonstrate how to track multiple animals simultaneously, classify individuals by species and age-sex class, estimate individuals' body postures (poses) and extract environmental features, including topography of the landscape and animal trails. By quantifying animal movement and posture while reconstructing a detailed 3D model of the landscape, our approach opens the door to studying the sensory ecology and decision-making of animals within their natural physical and social environments.
引用
收藏
页码:1357 / 1371
页数:15
相关论文
共 86 条
[1]   A call for viewshed ecology: Advancing our understanding of the ecology of information through viewshed analysis [J].
Aben, Job ;
Pellikka, Petri ;
Travis, Justin M. J. .
METHODS IN ECOLOGY AND EVOLUTION, 2018, 9 (03) :624-633
[2]   Cascading impacts of large-carnivore extirpation in an African ecosystem [J].
Atkins, Justine L. ;
Long, Ryan A. ;
Pansu, Johan ;
Daskin, Joshua H. ;
Potter, Arjun B. ;
Stalmans, Marc E. ;
Tarnita, Corina E. ;
Pringle, Robert M. .
SCIENCE, 2019, 364 (6436) :173-+
[3]   Visual obstruction and vigilance: a natural experiment [J].
Beauchamp, Guy .
JOURNAL OF AVIAN BIOLOGY, 2015, 46 (05) :476-481
[4]   Emergent Sensing of Complex Environments by Mobile Animal Groups [J].
Berdahl, Andrew ;
Torney, Colin J. ;
Ioannou, Christos C. ;
Faria, Jolyon J. ;
Couzin, Iain D. .
SCIENCE, 2013, 339 (6119) :574-576
[5]   Conservation translocations: a review of common difficulties and promising directions [J].
Berger-Tal, O. ;
Blumstein, D. T. ;
Swaisgood, R. R. .
ANIMAL CONSERVATION, 2020, 23 (02) :121-131
[6]   Mapping the stereotyped behaviour of freely moving fruit flies [J].
Berman, Gordon J. ;
Choi, Daniel M. ;
Bialek, William ;
Shaevitz, Joshua W. .
JOURNAL OF THE ROYAL SOCIETY INTERFACE, 2014, 11 (99)
[7]   Measuring behavioral responses of sea turtles, saltwater crocodiles, and crested terns to drone disturbance to define ethical operating thresholds [J].
Bevan, Elizabeth ;
Whiting, Scott ;
Tucker, Tony ;
Guinea, Michael ;
Raith, Andrew ;
Douglas, Ryan .
PLOS ONE, 2018, 13 (03)
[8]   DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels [J].
Bohnslav, James P. ;
Wimalasena, Nivanthika K. ;
Clausing, Kelsey J. ;
Dai, Yu Y. ;
Yarmolinsky, David A. ;
Cruz, Tomas ;
Kashlan, Adam D. ;
Chiappe, M. Eugenia ;
Orefice, Lauren L. ;
Woolf, Clifford J. ;
Harvey, Christopher D. .
ELIFE, 2021, 10
[9]   Linking behaviour to dynamics of populations and communities: application of novel approaches in behavioural ecology to conservation [J].
Bro-Jorgensen, Jakob ;
Franks, Daniel W. ;
Meise, Kristine .
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES, 2019, 374 (1781)
[10]  
Brown DD, 2013, ANIM BIOTELEM, V1, P20, DOI [DOI 10.1186/2050-3385-1-20, DOI 10.1186/2050-3385-1-1]