Automatic counting
Bird counts using medic software have already been described by
Pérez-García (2012), who used the UHTSCSA Image Tool 3.0 software to
perform a census of starlings. This software does not work everywhere,
however: e.g. it cannot be installed in the Windows 10 operating system.
Other free software dedicated to birds has been described by Descamps et
al. (2011), who used this to count flamingos in breeding colonies. This
latter software has turned out to be quite difficult to use: one serious
difficulty is the use of French as the basic language and the inability
to change the language version. In contrast, DotCount v1.2 is easy to
use, but its disadvantage is the closed source, so that it cannot be
used to create plugins or updates to enhance its functionality;
moreover, the latest version of this stems from as long ago as 2012. In
the future, the use of neural networks and machine learning in wildlife
studies will undoubtedly increase in importance (e.g. Villa et al. 2017,
Tabak et al. 2019). Clearly, there are many different possibilities and
solutions for automatic bird counting, but at present, ImageJ / Fiji
(Grishagin 2015) seems the best
choice. It is an open-source platform, so several programmers and
biologists can work together to create new plugins. Some of them already
use neural network-based algorithms (Buchholz et al. 2020).
The automatic counting methods using the ImageJ / Fiji platform proved
to be the best in our study, as they were the fastest and maintained the
precision of the results (Tables 3 and 4, Fig. 2). For small and medium
bird concentrations, we recommend using the Analyze Particles tool in
the ImageJ / Fiji software program. This does require pre-treatment of
each image each time, but with some practice, one can do this quite
efficiently and the results will be precise.
In the case of solutions using neural network algorithms, a one-off
count takes a very short time (23 seconds on average, Table 4), but to
achieve this state requires a lot of prior preparation, and the images
require some preliminary assumptions. The computer on which the machine
learning will be conducted must have the appropriate hardware. Then the
images have to be scaled in such a way that the objects are roughly the
same size, and the learning time of the neural network can take up to
several dozen hours. This method is therefore recommended in situations
where a lot of data (images) have been acquired from long-term
monitoring programmes, in large breeding colonies and in non-breeding
concentrations.
Acknowledgments
The author would like to thank Zbigniew Kajzer, Łukasz Ławicki,
Aleksandra Marchowska and Paweł Stańczak, who helped him with his field
work, and Joran Deschamps and Deborah Schmidt for their help in data
analysis using neural networks.
Author’s contributions
D.M. is responsible for all parts of this work.
Data availability statement
The raw data on the basis of which the analyses were carried out are
attached to the article as supplementary materials.
ORCID
Dominik Marchowskihttps://orcid.org/0000-0001-7508-9466
References
Adame, K., Pardo, M.A., Salvadeo,
C., Beier, E., and Elorriaga-Verplancken, F.R. 2017. Detectability and
categorization of California sea lions using an unmanned aerial vehicle.
Mar. Mammal Sci. 33(3): 913–925. doi: 10.1111/ mms.12403.
Amano, T., Székely, T., Sandel,
B., Nagy, S., Mundkur, T., Langendoen, T., et al. 2017. Successful
conservation of global waterbird populations depends on effective
governance. Nature , 553(7687), doi: 10.1038/nature25139.
Amat, J.A. & Green, A.J. 2010.
Waterbirds as Bioindicators of Environmental Conditions. In: C. Hurford
et al. (eds.), Conservation Monitoring in Freshwater Habitats: A
Practical Guide and Case Studies, Springer. Dordrecht, Heidelberg,
London, New York. DOI 10.1007/978-1-4020-9278-7_5.
Arts K., van der Wal R., Adams W.M. 2015. Digital technology and the
conservation of nature. Ambio 44, 661 – 673.
Bablok W, Passing H (1985) Application of statistical procedures in
analytical instrument testing. Journal of Automatic Chemistry 7:74-79.
Barnas A.F., Chabot D., Hodgson
A.J., David W. Johnston D.W., Bird D.M., Ellis-Felege S.N. 2020. A
standardized protocol for reporting methods when using drones for
wildlife research. J. Unmanned Veh. Syst. 8: 89–98.
dx.doi.org/10.1139/juvs-2019-0011.
Barbedo J.G.A. 2012. Method for Counting Microorganisms and Colonies in
Microscopic Images. 12th International Conference on Computational
Science and Its Applications, 18-21 June 2012.
DOI: 10.1109/ICCSA.2012.23.
Bilić-Zulle L. 2011. Comparison of methods: Passing and Bablok
regression. Biochemia Medica 21(1):49–52.
Buchholz TO., Prakash M., Schmidt D., Krull A., Jug F. 2020. DenoiSeg:
Joint Denoising and Segmentation. In: Bartoli A., Fusiello A. (eds)
Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in
Computer Science, vol 12535. Springer, Cham.
https://doi.org/10.1007/978-3-030-66415-2_21.
Chabot, D., Craik, S.R., and Bird,
D.M. 2015. Population census of a large common tern colony with a small,
unmanned aircraft. PLoS ONE, 10(4): e0122588. doi:
10.1371/journal.pone.0122588.
Costello M.J., May R.M., Stork N.E. 2013. Can We Name Earth’s Species
Before They Go Extinct? Science, Vol. 339, Issue 6118, pp. 413-416. DOI:
10.1126/science.1230318
Descamps S., Béchet A., Descombes X., Arnaud A. and Zerubia J. 2011. An
automatic counter for aerial images of aggregations of large birds.
Birds Study 58, 302–308.
Díaz, S., Fargione, J., Chapin,
F.S. III, Tilman, D. (2006). Biodiversity Loss Threatens Human
Well-Being. PLoS Biol 4(8): e277.
https://doi.org/10.1371/journal.pbio.0040277.
Díaz-Delago R., Lucas R., Hurford C. (eds.) 2017. The Roles of Remote
Sensing in Nature Conservation. A Practical Guide and Case Studies.
Springer International Publishing, Cham, Switzerland. DOI
10.1007/978-3-319-64332-8.
Elsey, R.M., and Trosclair, P.L.,
III. 2016. The use of an unmanned aerial vehicle to locate alligator
nests. Southeast. Nat. 15(1): 76–82. doi: 10.1656/058.015.0106.
Farina A., Pieretti N., Piccioli L. 2011. The soundscape methodology for
long-term bird monitoring: A Mediterranean Europe case-study. Ecological
Informatics 6(6): 354-363, doi.org/10.1016/j.ecoinf.2011.07.004.
Gregory, R.D. & van
Strien, A. 2010. Wild bird
indicators: using composite population trends of birds as measures of
environmental health. Ornithological Science 9:3-22.
https://doi.org/10.2326/osj.9.3.
Hu, J., Wu, X., and Dai, M. 2020.
Estimating the population size of migrating Tibetan antelopesPantholops hodgsonii with unmanned aerial vehicles. Oryx, 54(1):
101–109. doi: 10.1017/S0030605317001673.
Hodgson. J.C., Mott R., Baylis
S.M., Pham T.T., Wotherspoon S., Kilpatrick A.D., Segaran R.R., Reid I.,
Terauds A., Koh L.P. 2018. Drones count wildlife more accurately and
precisely than humans. Methods Ecol Evol. 9:1160–1167. DOI:
10.1111/2041-210X.12974.
Hooper, D., Adair, E., Cardinale,
B. et al. (2012). A global synthesis reveals biodiversity loss as
a major driver of ecosystem
change. Nature 486, 105–108.
https://doi.org/10.1038/nature11118.
Jarrett D., Calladine J., Cotton A., Wilson M.W., Humphreys E. (2020):
Behavioural responses of non-breeding waterbirds to drone approach are
associated with flock size and habitat, Bird Study, DOI:
10.1080/00063657.2020.1808587.
Koski, W.R., Gamage, G., Davis,
A.R., Mathews, T., LeBlanc, B., and Ferguson, S.H. 2015. Evaluation of
UAS for photographic re-identification of bowhead whales, Balaena
mysticetus. J. Unmanned Veh. Syst. 3(1): 22–29. doi: 10.1139/
juvs-2014-0014.
Kyrkou C., Timotheou S., Kolios P., Theocharides T., Panayiotou C. 2019.
Drones: Augmenting Our Quality of Life. IEEE Potentials 38 (1): 30-36,
doi: 10.1109/MPOT.2018.2850386.
Lyons, M., Brandis, K., Callaghan, C., McCann, J., Mills, C., Ryall, S.
and Kingsford, R. (2018) ‘Bird interactions with drones, from
individuals to large colonies’, Australian Field Ornithology. BirdLife
Australia, 35, pp. 51–56.
https://search.informit.org/doi/10.3316/informit.477965736750809.
Ławicki Ł., Guentzel S., Jasiński M., Kajzer Z., Czeraszkiewicz R.,
Oleksiak A., Żmihorski M., Marchowski D. 2010. Lower Odra River Valley.
In: Wilk. T., Jujka M., Krogulec J., Chylarecki P. (eds.) Important Bird
Areas of International Importance in Poland. OTOP, Marki, Poland.
Marchowski D., Ławicki Ł., Guentzel S., Kaliciuk J., Kajzer Z. 2018.
Long-term changes in the numbers of waterbirds at an important European
wintering site. Acta Biologica 25: 111-112. DOI: 10.18276/ab.2018.25-09.
Meissner W. 2011. Methods of counting wintering waterbirds. Birds
wintering in inland waters and in the coastal zone of the Baltic Sea.
FWIE. Kraków, Poland.
Michez, A., Morelle, K., Lehaire,
F., Widar, J., Authelet, M., Vermeulen, C., and Lejeune, P. 2016. Use of
unmanned aerial system to assess wildlife (Sus scrofa) damage to crops
(Zea mays). J. Unmanned Veh. Syst. 4(4): 266–275. doi:
10.1139/juvs-2016-0014.
Niemi, Gerald J.; Howe, Robert W.; Sturtevant, Brian R.; Parker, Linda
R.; Grinde, Alexis R.; Danz, Nicholas P.; Nelson, Mark D.; Zlonis,
Edmund J.; Walton, Nicholas G.; Gnass Giese, Erin E.; Lietz, Sue M.
2016. Analysis of long-term forest bird monitoring data from national
forests of the western Great Lakes Region. Gen. Tech. Rep. NRS-159.
Newtown Square, PA: U.S. Department of Agriculture, Forest Service,
Northern Research Station. 322 p.
Pérez-García J.M. 2012. The use of digital photography in censuses of
large concentrations of passerines: the case of a winter starling
roost-site. Revista Catalana d’Ornitologia 28:28-33.
Puttock, A., Cunliffe, A.,
Anderson, K., and Brazier, R.E. 2015. Aerial photography collected with
a multirotor drone reveals impact of Eurasian beaver reintroduction on
ecosystem structure. J. Unmanned Veh. Syst. 3(3): 123–130. doi:
10.1139/juvs-2015-0005.
Ratcliffe, N., Guihen, D., Robst,
J., Crofts, S., Stanworth, A., and Enderlein, P. 2015. A protocol for
the aerial survey of penguin colonies using UAVs. J. Unmanned Veh. Syst.
3(3): 95–101. doi: 10.1139/juvs-2015-0006.
Reif J. 2013. Long-Term Trends in Bird Populations: A Review of Patterns
and Potential Drivers in North America and Europe. Acta Ornithologica,
48(1):1-16, doi.org/10.3161/000164513X669955.
Grishagin I.V. 2015. Automatic cell counting with ImageJ. Analytical
Biochemistry 473: 63-65. https://doi.org/10.1016/j.ab.2014.12.007.
LaBarbera P, Rosso R (1989) On the fractal dimension of stream
networks. Water Resources Research 25: 735-741.
Levine, N. CrimeStat: A spatial statistics program for the
analysis of crime incident locations (v 4.02) . Ned Levine &
Associates, Houston, TX, USA
(2015).
Neagu M. & Bejan A. 1999. Constructal-theory tree networks of
“constant” thermal resistance
Journal of Applied Physics 86, 1136
(1999); https://doi.org/10.1063/1.370855.
R Core Team. 2021. R: A Language
and Environment for Statistical Computing. R Foundation for Statistical
Computing. Vienna, Austria, url = {https://www.R-project.org/}.
Sandhya N. Baviskar A. 2011. Quick & Automated Method for Measuring
Cell Area Using ImageJ. The American Biology Teacher 1 November, 73 (9):
554–556. doi: https://doi.org/10.1525/abt.2011.73.9.9.
Schindelin, J., Arganda-Carreras, I. & Frise, E. et al. 2012. Fiji: an
open-source platform for biological-image analysis. Nature methods 9(7):
676-682, PMID 22743772, doi:10.1038/nmeth.2019.
Shin D-H.& Choi M.J.2015.Ecological views of big data: Perspectives and
issues. Telematics and Informatics.32(2: 311-320,
doi.org/10.1016/j.tele.2014.09.006.
Shroeder A.B., Dobson E.T.A., Rueden C.T., Tomancak P., Jug F., Eliceiri
K.W. 2020. The ImageJ ecosystem: Open‐source software for image
visualization, processing, and analysis. Protein
Science, 30: 234– 249. https://doi.org/10.1002/pro.3993.
Tabak, MA, Norouzzadeh, MS, Wolfson, DW, et al. Machine learning to
classify animal species in camera trap images: Applications in
ecology. Methods Ecol
Evol. 2019; 10: 585– 590. https://doi.org/10.1111/2041-210X.13120.
Vas, E., Lescroël, A., Duriez, O.,
Boguszewski, G. & Grémillet, D. 2015. Approaching birds with drones:
first experiments and ethical guidelines. Biological Letters 11:
20140754.
Vermeulen, C., Lejeune, P.,
Lisein, J., Sawadogo, P., and Bouché, P. 2013. Unmanned aerial survey of
elephants. PLoS ONE, 8(2): e54700. doi: 10.1371/journal.pone.0054700.
PMID: 23405088.
Villa A.G., Salazar A., Vargas F.
2017. Towards automatic wild animal monitoring: Identification of animal
species in camera-trap images using very deep convolutional neural
networks. Ecological Informatics,41: 24-32,
doi.org/10.1016/j.ecoinf.2017.07.004.