{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T19:42:19Z","timestamp":1778442139788,"version":"3.51.4"},"reference-count":58,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T00:00:00Z","timestamp":1658188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Using machine learning (ML) to automate camera trap (CT) image processing is advantageous for time-sensitive applications. However, little is currently known about the factors influencing such processing. Here, we evaluate the influence of occlusion, distance, vegetation type, size class, height, subject orientation towards the CT, species, time-of-day, colour, and analyst performance on wildlife\/human detection and classification in CT images from western Tanzania. Additionally, we compared the detection and classification performance of analyst and ML approaches. We obtained wildlife data through pre-existing CT images and human data using voluntary participants for CT experiments. We evaluated the analyst and ML approaches at the detection and classification level. Factors such as distance and occlusion, coupled with increased vegetation density, present the most significant effect on DP and CC. Overall, the results indicate a significantly higher detection probability (DP), 81.1%, and correct classification (CC) of 76.6% for the analyst approach when compared to ML which detected 41.1% and classified 47.5% of wildlife within CT images. However, both methods presented similar probabilities for daylight CT images, 69.4% (ML) and 71.8% (analysts), and dusk CT images, 17.6% (ML) and 16.2% (analysts), when detecting humans. Given that users carefully follow provided recommendations, we expect DP and CC to increase. In turn, the ML approach to CT image processing would be an excellent provision to support time-sensitive threat monitoring for biodiversity conservation.<\/jats:p>","DOI":"10.3390\/s22145386","type":"journal-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T23:10:22Z","timestamp":1658272222000},"page":"5386","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Understanding External Influences on Target Detection and Classification Using Camera Trap Images and Machine Learning"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1711-6590","authenticated-orcid":false,"given":"Sally O. A.","family":"Westworth","sequence":"first","affiliation":[{"name":"School of Biological and Environmental Sciences, Liverpool John Moores University, Byrom Street, Liverpool L3 3AF, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0822-1150","authenticated-orcid":false,"given":"Carl","family":"Chalmers","sequence":"additional","affiliation":[{"name":"School of Computer Science and Mathematics, Liverpool John Moores University, Byrom Street, Liverpool L3 3AF, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7070-4447","authenticated-orcid":false,"given":"Paul","family":"Fergus","sequence":"additional","affiliation":[{"name":"School of Computer Science and Mathematics, Liverpool John Moores University, Byrom Street, Liverpool L3 3AF, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6353-0170","authenticated-orcid":false,"given":"Steven N.","family":"Longmore","sequence":"additional","affiliation":[{"name":"Astrophysics Research Institute, Liverpool John Moores University, Liverpool L3 3AF, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4674-537X","authenticated-orcid":false,"given":"Alex K.","family":"Piel","sequence":"additional","affiliation":[{"name":"Department of Anthropology, University College London, Taviton Street, London WC1H OBW, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3954-5174","authenticated-orcid":false,"given":"Serge A.","family":"Wich","sequence":"additional","affiliation":[{"name":"School of Biological and Environmental Sciences, Liverpool John Moores University, Byrom Street, Liverpool L3 3AF, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.ecolind.2012.09.014","article-title":"Remote Sensing for Conservation Monitoring: Assessing Protected Areas, Habitat Extent, Habitat Condition, Species Diversity, and Threats","volume":"33","author":"Nagendra","year":"2013","journal-title":"Ecol. Indic."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.biocon.2019.02.017","article-title":"Detecting \u2018Poachers\u2019 with Drones: Factors Influencing the Probability of Detection with TIR and RGB Imaging in Miombo Woodlands, Tanzania","volume":"233","author":"Hambrecht","year":"2019","journal-title":"Biol. Conserv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"311","DOI":"10.13157\/arla.66.2.2019.ra4","article-title":"Cost-Effectiveness Assessment of Five Audio Recording Systems for Wildlife Monitoring: Differences between Recording Distances and Singing Direction","volume":"66","author":"Bota","year":"2019","journal-title":"Ardeola"},{"key":"ref_4","first-page":"1","article-title":"Drones as a Support Tool for Seismic Acquisition","volume":"1","author":"Stephenson","year":"2019","journal-title":"ASEG Ext. Abstr."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wich, S.A., and Koh, L.P. (2018). Conservation Drones, Oxford University Press.","DOI":"10.1093\/oso\/9780198787617.001.0001"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kamminga, J., Ayele, E., Meratnia, N., and Havinga, P. (2018). Poaching Detection Technologies\u2014A Survey. Sensors, 18.","DOI":"10.3390\/s18051474"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"O\u2019Connell, A.F., Nichols, J.D., and Karanth, K.U. (2011). Camera Traps in Animal Ecology: Methods and Analyses, Springer.","DOI":"10.1007\/978-4-431-99495-4"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.jort.2016.09.007","article-title":"Coupling Visitor and Wildlife Monitoring in Protected Areas Using Camera Traps","volume":"17","author":"Miller","year":"2017","journal-title":"J. Outdoor Recreat. Tour."},{"key":"ref_9","first-page":"181","article-title":"Camera-Trapping for Conservation: A Guide to Best-Practices","volume":"1","author":"Wearn","year":"2017","journal-title":"WWF Conserv. Technol. Ser."},{"key":"ref_10","unstructured":"Van Berkel, T. (2014). Camera Trapping for Wildlife Conservation: Expedition Field Techniques, Geography Outdoors."},{"key":"ref_11","unstructured":"(2022, July 09). Technical Challenges in Building Solar-Powered Drones and How Companies Are Tackling Them Using the Recent Advancements. Available online: https:\/\/circuitdigest.com\/article\/technical-challenges-in-building-solar-powered-drones-and-how-companies-are-tackling-with-recent-advancements."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1146\/annurev-ecolsys-102209-144636","article-title":"Citizen Science as an Ecological Research Tool: Challenges and Benefits","volume":"41","author":"Dickinson","year":"2010","journal-title":"Annu. Rev. Ecol. Evol. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.biocon.2013.05.025","article-title":"Realising the Full Potential of Citizen Science Monitoring Programs","volume":"165","author":"Tulloch","year":"2013","journal-title":"Biol. Conserv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1111\/j.1472-4642.2009.00615.x","article-title":"Beyond Scarcity: Citizen Science Programmes as Useful Tools for Conservation Biogeography: Citizen Science and Conservation Biogeography","volume":"16","author":"Devictor","year":"2010","journal-title":"Divers. Distrib."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1016\/j.tree.2009.03.017","article-title":"A New Dawn for Citizen Science","volume":"24","author":"Silvertown","year":"2009","journal-title":"Trends Ecol. Evol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.ecoinf.2017.07.004","article-title":"Towards Automatic Wild Animal Monitoring: Identification of Animal Species in Camera-Trap Images Using Very Deep Convolutional Neural Networks","volume":"41","author":"Salazar","year":"2017","journal-title":"Ecol. Inform."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1111\/2041-210X.13099","article-title":"Identifying Animal Species in Camera Trap Images Using Deep Learning and Citizen Science","volume":"10","author":"Willi","year":"2019","journal-title":"Methods Ecol. Evol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"100109","DOI":"10.1016\/j.patter.2020.100109","article-title":"Artificial Intelligence Meets Citizen Science to Supercharge Ecological Monitoring","volume":"1","author":"McClure","year":"2020","journal-title":"Patterns"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"E5716","DOI":"10.1073\/pnas.1719367115","article-title":"Automatically Identifying, Counting, and Describing Wild Animals in Camera-Trap Images with Deep Learning","volume":"115","author":"Norouzzadeh","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1578","DOI":"10.1002\/ece3.4747","article-title":"Animal Scanner: Software for Classifying Humans, Animals, and Empty Frames in Camera Trap Images","volume":"9","author":"Yousif","year":"2019","journal-title":"Ecol. Evol."},{"key":"ref_21","first-page":"1","article-title":"Automated Identification of Animal Species in Camera Trap Images","volume":"52","author":"Yu","year":"2013","journal-title":"J. Image Video Proc."},{"key":"ref_22","first-page":"150","article-title":"A deep active learning system for species identification and counting in camera trap images","volume":"12","author":"Norouzzadeh","year":"2021","journal-title":"Br. Ecol. Soc."},{"key":"ref_23","first-page":"2","article-title":"Recognition of Animal Species on Camera Trap Images Using Machine Learning and Deep Learning Models","volume":"10","author":"Thangarasu","year":"2019","journal-title":"Int. J. Sci. Technol. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1111\/j.2041-210X.2011.00094.x","article-title":"Quantifying the Sensitivity of Camera Traps: An Adapted Distance Sampling Approach: Quantifying Camera Trap Sensitivity","volume":"2","author":"Carbone","year":"2011","journal-title":"Methods Ecol. Evol."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Buckland, S.T., Anderson, D.R., Burnham, K.P., Laake, J.L., Borchers, D.L., and Thomas, L. (2001). Introduction to Distance Sampling: Estimating Abundance of Biological Populations, Oxford University Press.","DOI":"10.1093\/oso\/9780198506492.001.0001"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1111\/aje.12255","article-title":"Do Animal Size, Seasons and Vegetation Type Influence Detection Probability and Density Estimates of Serengeti Ungulates?","volume":"54","author":"Bukombe","year":"2016","journal-title":"Afr. J. Ecol."},{"key":"ref_27","first-page":"188","article-title":"Deterring Poaching in Western Tanzania: The Presence of Wildlife Researchers","volume":"3","author":"Piel","year":"2015","journal-title":"Glob. Ecol. Conserv."},{"key":"ref_28","unstructured":"Kingdon, J. (2015). The Kingdon Field Guide to African Mammals, Princeton University Press. [2nd ed.]."},{"key":"ref_29","unstructured":"(2020, May 01). Hyena Mammal Facts. Available online: https:\/\/www.britannica.com\/animal\/hyena."},{"key":"ref_30","unstructured":"(2020, February 01). Chimpanzee Animal Facts. Pan troglodytes. Available online: https:\/\/a-z-animals.com\/animals\/chimpanzee\/."},{"key":"ref_31","unstructured":"(2020, February 15). Leopard Animal Facts. Panthera pardus. Available online: https:\/\/a-z-animals.com\/animals\/leopard\/."},{"key":"ref_32","unstructured":"Davis, S. (2020, January 07). Cercopithecus ascanius. Available online: https:\/\/animaldiversity.org\/accounts\/Cercopithecus_ascanius\/."},{"key":"ref_33","unstructured":"(2020, January 08). Blue Duiker. SANBI. Available online: https:\/\/www.sanbi.org\/animal-of-the-week\/blue-duiker\/."},{"key":"ref_34","unstructured":"(2020, January 21). Learn More about the Bushbuck. Available online: https:\/\/www.awf.org\/wildlife-conservation\/bushbuck."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/BF03194198","article-title":"Diet of the South African Large-Spotted Genet Genetta Tigrina (Carnivora, Viverridae) in a Coastal Dune Forest","volume":"52","author":"Roberts","year":"2007","journal-title":"Acta Theriol."},{"key":"ref_36","first-page":"318","article-title":"Foraging and Habitat Use of Common Duikers, Sylvicapra Grimmia, in a Heterogeneous Environment within the Soutpansberg, South Africa","volume":"52","author":"Brown","year":"2013","journal-title":"Afr. J. Ecol."},{"key":"ref_37","first-page":"174","article-title":"A World List of Mammalian Species","volume":"25","author":"Corbet","year":"1991","journal-title":"Oryx"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Winter, B. (2019). Statistics for Linguists: An Introduction Using R, Routledge. [1st ed.].","DOI":"10.4324\/9781315165547"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1111\/j.1420-9101.2010.02210.x","article-title":"Multimodel Inference in Ecology and Evolution: Challenges and Solutions: Multimodel Inference","volume":"24","author":"Grueber","year":"2011","journal-title":"J. Evol. Biol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"3139","DOI":"10.21105\/joss.03139","article-title":"Performance: An R Package for Assessment, Comparison and Testing of Statistical Models","volume":"6","author":"Patil","year":"2021","journal-title":"J. Open Source Softw."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"558","DOI":"10.4097\/kja.19087","article-title":"Multicollinearity and Misleading Statistical Results","volume":"72","author":"Kim","year":"2019","journal-title":"Korean J. Anesthesiol."},{"key":"ref_42","unstructured":"Mohajon, J. (2021, July 24). Confusion Matrix for Your Multi-Class Machine Learning Model. Medium. Available online: https:\/\/towardsdatascience.com\/confusion-matrix-for-your-multi-class-machine-learning-model-ff9aa3bf7826."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/s13364-020-00478-y","article-title":"Component Processes of Detection Probability in Camera-Trap Studies: Understanding the Occurrence of False-Negatives","volume":"65","author":"Findlay","year":"2020","journal-title":"Mammal Res."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1109\/TCYB.2013.2255271","article-title":"Occlusion Handling via Random Subspace Classifiers for Human Detection","volume":"44","author":"Marin","year":"2014","journal-title":"IEEE Trans. Cybern."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"8","DOI":"10.5334\/cstp.219","article-title":"Just-in-Time Training Improves Accuracy of Citizen Scientist Wildlife Identifications from Camera Trap Photos","volume":"5","author":"Blickley","year":"2020","journal-title":"Citiz. Sci. Theory Pract."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1002\/rse2.25","article-title":"A Simple Method for Estimating the Effective Detection Distance of Camera Traps","volume":"3","author":"Hofmeester","year":"2017","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"ref_47","unstructured":"Panthera (2022, July 10). PoacherCams. Available online: https:\/\/panthera.org\/conservation-technology\/poachercam."},{"key":"ref_48","unstructured":"Global Conservation (2022, July 10). Trailguard-AI. Available online: https:\/\/globalconservation.org\/news\/trailguard-ai\/."},{"key":"ref_49","first-page":"148","article-title":"\u201cWhich Camera Trap Type and How Many Do I Need?\u201d A Review of Camera Features and Study Designs for a Range of Wildlife Research Applications","volume":"24","author":"Rovero","year":"2013","journal-title":"Hystrix Ital. J. Mammal."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1111\/jzo.12945","article-title":"Towards a Best-practices Guide for Camera Trapping: Assessing Differences among Camera Trap Models and Settings under Field Conditions","volume":"316","author":"Palencia","year":"2022","journal-title":"J. Zool."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1002\/fee.1448","article-title":"Scaling-up Camera Traps: Monitoring the Planet\u2019s Biodiversity with Networks of Remote Sensors","volume":"15","author":"Steenweg","year":"2017","journal-title":"Front. Ecol. Environ."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"181748","DOI":"10.1098\/rsos.181748","article-title":"Snap happy: Camera traps are an effective sampling tool when compared with alternative methods","volume":"6","author":"Wearn","year":"2019","journal-title":"R. Soc. Open Sci."},{"key":"ref_53","first-page":"1","article-title":"Real-Time Alerts from AI-Enabled Camera Traps Using the Iridium Satellite Network: A Case-Study in Gabon, Central Africa","volume":"13","author":"Whytock","year":"2021","journal-title":"bioRxiv"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1071\/PC20076","article-title":"Animal Detections Increase by Using a Wide-Angle Camera Trap Model but Not by Periodically Repositioning Camera Traps within Study Sites","volume":"28","author":"Seidlitz","year":"2021","journal-title":"Pac. Conserv. Biol."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"O\u2019Connor, K.M., Nathan, L.R., Liberati, M.R., Tingley, M.W., Vokoun, J.C., and Rittenhouse, T.A.G. (2017). Camera Trap Arrays Improve Detection Probability of Wildlife: Investigating Study Design Considerations Using an Empirical Dataset. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0175684"},{"key":"ref_56","unstructured":"Global Conservation (2022, July 11). Chapter 16: SMART: Spatial Monitoring and Reporting Tool. Available online: https:\/\/globalconservation.org\/methodology\/global-park-defense\/smart-spatial-monitoring-and-reporting-tool\/."},{"key":"ref_57","unstructured":"Hui, J. (2020, February 02). Object Detection: Speed and Accuracy Comparison (Faster R-CNN, R-FCN, SSD, FPN, RetinaNet and YOLOv3). Medium. Available online: https:\/\/jonathan-hui.medium.com\/object-detection-speed-and-accuracy-comparison-faster-r-cnn-r-fcn-ssd-and-yolo-5425656ae359."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.protcy.2016.08.115","article-title":"A Novel Approach to Detect Pedestrian from Still Images Using Random Subspace Method","volume":"25","author":"Priya","year":"2016","journal-title":"Procedia Technol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5386\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:54:10Z","timestamp":1760140450000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5386"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,19]]},"references-count":58,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["s22145386"],"URL":"https:\/\/doi.org\/10.3390\/s22145386","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,19]]}}}