dc.contributor.author | Torney, CJ | |
dc.contributor.author | Dobson, AP | |
dc.contributor.author | Borner, F | |
dc.contributor.author | Lloyd-Jones, DJ | |
dc.contributor.author | Moyer, D | |
dc.contributor.author | Maliti, HT | |
dc.contributor.author | Mwita, M | |
dc.contributor.author | Fredrick, H | |
dc.contributor.author | Borner, M | |
dc.contributor.author | Hopcraft, JG | |
dc.date.accessioned | 2016-07-20T11:10:39Z | |
dc.date.issued | 2016-05-26 | |
dc.description.abstract | Accurate and on-demand animal population counts are the holy grail for wildlife conservation organizations throughout the world because they enable fast and responsive adaptive management policies. While the collection of image data from camera traps, satellites, and manned or unmanned aircraft has advanced significantly, the detection and identification of animals within images remains a major bottleneck since counting is primarily conducted by dedicated enumerators or citizen scientists. Recent developments in the field of computer vision suggest a potential resolution to this issue through the use of rotation-invariant object descriptors combined with machine learning algorithms. Here we implement an algorithm to detect and count wildebeest from aerial images collected in the Serengeti National Park in 2009 as part of the biennial wildebeest count. We find that the per image error rates are greater than, but comparable to, two separate human counts. For the total count, the algorithm is more accurate than both manual counts, suggesting that human counters have a tendency to systematically over or under count images. While the accuracy of the algorithm is not yet at an acceptable level for fully automatic counts, our results show this method is a promising avenue for further research and we highlight specific areas where future research should focus in order to develop fast and accurate enumeration of aerial count data. If combined with a bespoke image collection protocol, this approach may yield a fully automated wildebeest count in the near future. | en_GB |
dc.description.sponsorship | CJT is supported by a Complex Systems Scholar Award from the James S. McDonnell Foundation. JGCH is supported by a Lord Kelvin Adam Smith Fellowship, funding from the British Ecological Society and the European Union’s Horizon 2020 research and innovation programme under grant agreement No 641918 AfricanBioServices. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. | en_GB |
dc.identifier.citation | Vol. 11, No 5, Article no. e0156342 | en_GB |
dc.identifier.doi | 10.1371/journal.pone.0156342 | |
dc.identifier.other | PONE-D-16-08656 | |
dc.identifier.uri | http://hdl.handle.net/10871/22650 | |
dc.language.iso | en | en_GB |
dc.publisher | Public Library of Science | en_GB |
dc.relation.source | Source code is available at https://github.com/ctorney/wildCount. Image count data is available as Supporting Information. Images were provided by the Frankfurt Zoological Society. | en_GB |
dc.relation.url | http://www.ncbi.nlm.nih.gov/pubmed/27227888 | en_GB |
dc.rights | © 2016 Torney et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. | en_GB |
dc.subject | wildebeest | en_GB |
dc.subject | imaging techniqes | en_GB |
dc.subject | machine learning algorithms | en_GB |
dc.subject | algorithms | en_GB |
dc.subject | Fourier analysis | en_GB |
dc.subject | animal performance | en_GB |
dc.subject | cameras | en_GB |
dc.subject | conservation science | en_GB |
dc.title | Assessing rotation-invariant feature classification for automated wildebeest population counts | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2016-07-20T11:10:39Z | |
dc.identifier.issn | 1932-6203 | |
exeter.place-of-publication | United States | en_GB |
dc.identifier.journal | PLoS One | en_GB |