Skip to main content

Advertisement

Log in

Reducing identification errors of African carnivores from photographs through computer-assisted workflow

  • Short Communication
  • Published:
Mammal Research Aims and scope Submit manuscript

Abstract

Precise and accurate estimates of population size are fundamental to the study and conservation of wildlife. Identification of individual animals is often required to obtain such estimates, yet manual classifications by human observers induce bias, which can propagate across long-term datasets or large spatial scales. Pattern recognition algorithms have been developed to aid identification efforts and here, we demonstrate the efficacy of this technology to reduce misidentifications of African large carnivores in historic data. We used a 7-year camera-trapping dataset from north-central Namibia and revised cheetah and leopard individuals identified by human observers through a pattern recognition algorithm, HotSpotter, implemented in a web-based and open-source application, the African Carnivore Wildbook (ACW). Verification of individuals with ACW resulted in a reduction from 43 to 40 cheetah individuals and from 59 to 46 leopard individuals. This is equivalent to a difference of 7% and 22% of individuals identified for cheetahs and leopards, respectively. Additionally, this revision increased the proportion of individuals that were detected over multiple years and at multiple locations. Our findings may have implications for population and trend estimates of these and other species, given that current estimates often rely on manual identification that could overestimate population size.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1

Data availability

The data that support the findings of this study are available from the corresponding author upon reasonable request.

References

  • Agha M, Batter T, Bolas EC, Collins AC, Gomes da Rocha D, Monteza-Moreno CM, Preckler-Quisquater S, Sollmann R (2018) A review of wildlife camera trapping trends across Africa. Afr J Ecol 56:694–701. https://doi.org/10.1111/AJE.12565

    Article  Google Scholar 

  • Ahumada JA, Fegraus E, Birch T, Flores N, Kays R, O’Brien TG, Palmer J, Schuttler S, Zhao JY, Jetz W, Kinnaird M, Kulkarni S, Lyet A, Thau D, Duong M, Oliver R, Dancer A (2020) Wildlife Insights: a platform to maximize the potential of camera trap and other passive sensor wildlife data for the planet. Environ Conserv 47:1–6. https://doi.org/10.1017/S0376892919000298

    Article  Google Scholar 

  • Balme G, Rogan M, Thomas L, Pitman R, Mann G, Whittington-Jones G, Midlane N, Broodryk M, Broodryk K, Campbell M, Alkema M, Wright D, Hunter L (2019) Big cats at large: density, structure, and spatio-temporal patterns of a leopard population free of anthropogenic mortality. Popul Ecol 61:256–267. https://doi.org/10.1002/1438-390X.1023

    Article  Google Scholar 

  • Berger-Wolf TY, Rubenstein DI, Stewart C V., Holmberg JA, Parham J, Menon S, Crall J, Van Oast J, Kiciman E, Joppa L (2017) Wildbook: crowdsourcing, computer vision, and data science for conservation. arXiv 1710.08880

  • Blount D, Gero S, Van Oast J, Parham J, Kingen C, Scheiner B, Stere T, Fisher M, Minton G, Khan C, Dulau V, Thompson J, Moskvyak O, Berger-Wolf T, Stewart CV, Holmberg J, Levenson JJ (2022) Flukebook: an opensource AI platform for cetacean photo identification. Mamm Biol 2022. https://doi.org/10.1007/S42991-021-00221-3

  • Bolger DT, Morrison TA, Vance B, Lee D, Farid H (2012) A computer-assisted system for photographic mark–recapture analysis. Methods Ecol Evol 3:813–822. https://doi.org/10.1111/J.2041-210X.2012.00212.X

    Article  Google Scholar 

  • Burton AC, Neilson E, Moreira D, Ladle A, Steenweg R, Fisher JT, Bayne E, Boutin S (2015) Wildlife camera trapping: a review and recommendations for linking surveys to ecological processes. J Appl Ecol 52:675–685. https://doi.org/10.1111/1365-2664.12432

    Article  Google Scholar 

  • Carbone C, Gittleman JL (2002) A common rule for the scaling of carnivore density. Science 295:2273–2276. https://doi.org/10.1126/science.1067994

    Article  CAS  Google Scholar 

  • Crall J, Parham J, Mulich M, Chan K, Zrutfield, Weideman HJ, Weinstock A, Jablons Z, Blount D, Eylor, Lowe D, Southerland K, Batbouta A, Audrey, Scheiner B, Wrona J, Charles (2021) WildMeOrg/wildbook-ia: Version 4.0.0 (v4.0.0). Zenodo. https://zenodo.org/record/5765701

  • Crall JP, Stewart C V, Berger-Wolf TY, Rubenstein DI, Sundaresan SR (2013) HotSpotter - Patterned species instance recognition, in: IEEE Workshop on Applications of Computer Vision (WACV). Institute of Electrical and Electronics Engineers, Tampa, Florida, USA, pp. 230–237

  • Fabiano EC, Sutherland C, Fuller AK, Nghikembua M, Eizirik E, Marker L (2020) Trends in cheetah Acinonyx jubatus density in north-central Namibia. Popul Ecol 62:233–243. https://doi.org/10.1002/1438-390X.12045

  • Foster RJ, Harmsen BJ (2012) A critique of density estimation from camera-trap data. J Wildl Manage 76:224–236. https://doi.org/10.1002/jwmg.275

    Article  Google Scholar 

  • Gilbert NA, Clare JDJ, Stenglein JL, Zuckerberg B (2021) Abundance estimation of unmarked animals based on camera-trap data. Conserv Biol 35:88–100. https://doi.org/10.1111/COBI.13517

    Article  Google Scholar 

  • Green AM, Chynoweth MW, Şekercioğlu ÇH (2020) Spatially explicit capture-recapture through camera trapping: a review of benchmark analyses for wildlife density estimation. Front Ecol Evol 8:473. https://doi.org/10.3389/FEVO.2020.563477/BIBTEX

    Article  Google Scholar 

  • Hughes B, Burghardt T (2017) Automated visual fin identification of individual great white sharks. Int J Comput vis 122:542–557. https://doi.org/10.1007/S11263-016-0961-Y/FIGURES/16

    Article  Google Scholar 

  • IUCN (2012) IUCN red list categories and criteria. Gland, Switzerland

    Google Scholar 

  • Johansson Ö, Samelius G, Wikberg E, Chapron G, Mishra C (2020) Low M (2020) Identification errors in camera-trap studies result in systematic population overestimation. Sci Reports 101(10):1–10. https://doi.org/10.1038/s41598-020-63367-z

    Article  CAS  Google Scholar 

  • Kelly MJ, Betsch J, Wultsch C, Mesa B, Mills LS (2012) Noninvasive sampling for carnivores. In: Boitani L, Power RA (eds) Carnivore ecology and conservation: a handbook of techniques. Oxford University Press, UK, pp 47–69

    Chapter  Google Scholar 

  • Marker L, Dickman AJ (2005) Factors affecting leopard (Panthera pardus) spatial ecology, with particular reference to Namibian farmlands. South African J Wildl Res 35:105–115

    Google Scholar 

  • Matthé M, Sannolo M, Winiarski K, van der SpitzenSluijs A, Goedbloed D, Steinfartz S, Stachow U (2017) Comparison of photo-matching algorithms commonly used for photographic capture–recapture studies. Ecol Evol 7:5861–5872. https://doi.org/10.1002/ECE3.3140

    Article  Google Scholar 

  • Morrison TA, Yoshizaki J, Nichols JD, Bolger DT (2011) Estimating survival in photographic capture–recapture studies: overcoming misidentification error. Methods Ecol Evol 2:454–463. https://doi.org/10.1111/J.2041-210X.2011.00106.X

    Article  Google Scholar 

  • Nipko RB, Holcombe BE, Kelly MJ (2020) Identifying individual jaguars and ocelots via pattern-recognition software: comparing HotSpotter and Wild-ID. Wildl Soc Bull 44:424–433. https://doi.org/10.1002/WSB.1086

    Article  Google Scholar 

  • Obbard ME, Howe EJ, Kyle CJ (2010) Empirical comparison of density estimators for large carnivores. J Appl Ecol 47:76–84. https://doi.org/10.1111/J.1365-2664.2009.01758.X

    Article  Google Scholar 

  • Rakhimberdiev E, Karagicheva J, Saveliev A, Loonstra AHJ, Verhoeven MA, Hooijmeijer JCEW, Schaub M, Piersma T (2022) Misidentification errors in reencounters result in biased estimates of survival probability from CJS models: evidence and a solution using the robust design. Methods Ecol Evol. https://doi.org/10.1111/2041-210X.13825

    Article  Google Scholar 

  • Ripple WJ, Estes JA, Beschta RL, Wilmers CC, Ritchie EG, Hebblewhite M, Berger J, Elmhagen B, Letnic M, Nelson MP, Schmitz OJ, Smith DW, Wallach AD, Wirsing AJ (2014) Status and ecological effects of the world’s largest carnivores. Science 343:1241484. https://doi.org/10.1126/science.1241484

    Article  CAS  Google Scholar 

  • Schneider S, Taylor GW, Linquist S, Kremer SC (2019) Past, present and future approaches using computer vision for animal re-identification from camera trap data. Methods Ecol Evol 10:461–470. https://doi.org/10.1111/2041-210X.13133

    Article  Google Scholar 

  • Sherley R, Burghardt T, Barham P, Campbell N, Cuthill I (2010) Spotting the difference: towards fully-automated population monitoring of African penguins Spheniscus demersus. Endanger Species Res 11:101–111. https://doi.org/10.3354/esr00267

    Article  Google Scholar 

  • Shorrocks B, Croft DP (2009) Necks and networks: a preliminary study of population structure in the reticulated giraffe (Giraffa camelopardalis reticulata de Winston). Afr J Ecol 47:374–381. https://doi.org/10.1111/J.1365-2028.2008.00984.X

    Article  Google Scholar 

  • Stevick PT, Palsbøll PJ, Smith TD, Bravington MV, Hammond PS (2001) Errors in identification using natural markings: rates, sources, and effects on capture-recapture estimates of abundance. Can J Fish Aquat Sci 58:1861–1870. https://doi.org/10.1139/F01-131

    Article  Google Scholar 

  • Tucker AM, McGowan CP, Robinson RA, Clark JA, Lyons JE, Derose-Wilson A, Du Feu R, Austin GE, Atkinson PW, Clark NA (2019) Effects of individual misidentification on estimates of survival in long-term mark–resight studies. Condor 121:1–13. https://doi.org/10.1093/CONDOR/DUY017

    Article  Google Scholar 

  • Van Horn RC, Zug B, Lacombe C, Velez-Liendo X, Paisley S (2014) Human visual identification of individual Andean bears Tremarctos ornatus. Wildlife Biol 20:291–299. https://doi.org/10.2981/WLB.00023

    Article  Google Scholar 

  • Van Oast J, Holmberg J, June R, Kingen CW, Blount D, Mark, Me W, gpoautomation, Winstanley G, schibel21, Becker A, Donovan J, Wainner C, marcial21, Overbeck C, Southerland K, mbrecunier, Huayhuaca L, Matt, Shay E (2022) WildMeOrg/Wildbook: 2022-01-31 Release (2022-01-31_release_notes). Zenodo. 10.5281/ZENODO.5999339

  • Verschueren S, Briers-Louw WD, Cristescu B, Fabiano E, Nghikembua M, Torres-Uribe C, Walker EH, Marker L (2021) Spatiotemporal sharing and partitioning of scent-marking sites by cheetahs and leopards in north-central Namibia. Afr J Ecol 59:605–613. https://doi.org/10.1111/aje.12878

    Article  Google Scholar 

  • Yoshizaki J, Pollock KH, Brownie C, Webster RA (2009) Modeling misidentification errors in capture–recapture studies using photographic identification of evolving marks. Ecology 90:3–9. https://doi.org/10.1890/08-0304.1

    Article  Google Scholar 

Download references

Acknowledgements

We thank Cheetah Conservation Fund staff and volunteers who contributed to the data collection. We thank Tech 4 Conservation (https://www.t4c.org), Botswana Predator Conservation (https://www.bpctrust.org), and Wild Me (https://www.wildme.org) for the development of the ACW.

Funding

Fieldwork was supported by Cheetah Conservation Fund donors. ACW was funded by Microsoft for Startups grant provided to Wild Me.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Stijn Verschueren.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Communicated by Dries Kuijper

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Verschueren, S., Fabiano, E.C., Kakove, M. et al. Reducing identification errors of African carnivores from photographs through computer-assisted workflow. Mamm Res 68, 121–125 (2023). https://doi.org/10.1007/s13364-022-00657-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13364-022-00657-z

Keywords

Navigation