ORIGINAL ARTICLE
Hoofed animal detection in UAV thermal images using Balanced Random Forest and CNN features
,
 
Grzegorz Jóźków 1, A-B,D-F
 
 
 
More details
Hide details
1
Institute of Geodesy and Geoinformatics, Wrocław University of Environmental and Life Sciences, Grunwaldzka 53, 50-357, Wrocław, Poland
 
 
A - Research concept and design; B - Collection and/or assembly of data; C - Data analysis and interpretation; D - Writing the article; E - Critical revision of the article; F - Final approval of article
 
 
Submission date: 2025-02-26
 
 
Final revision date: 2025-04-24
 
 
Acceptance date: 2025-05-21
 
 
Publication date: 2025-06-18
 
 
Corresponding author
Dorota Włodarczyk   

Institute of Geodesy and Geoinformatics, Wrocław University of Environmental and Life Sciences, Grunwaldzka 53, 50-357, Wrocław, Poland
 
 
Reports on Geodesy and Geoinformatics 2025;120:1-13
 
KEYWORDS
TOPICS
ABSTRACT
Wildlife monitoring is vital to conservation efforts and the prevention of animal-related negative impacts on human activities and ecosystems. The use of Unmanned Aerial Vehicles (UAVs) enables data collection with no harm to wildlife and in difficult field conditions. This study proposes a method of detecting hoofed animals in UAV-acquired thermal images, addressing the challenges of low-resolution thermal imaging and the presence of other heated objects hindering simple temperature analysis and image segmentation. The proposed method uses machine learning algorithms and is designed to work with a limited size of training dataset. The method consists of an initial segmentation step that detects potential animals based on thermal and geometrical signatures, followed by classification using a Balanced Random Forest (BRF) algorithm. One of the key aspects of the proposed method is the use of geometric and thermal features along with multi-scale Convolutional Neural Network (CNN) extracted feature representations in BRF. The benefit of the BRF is its speed, little requirement regarding the amount of training data, and its capacity to work with an imbalanced number of objects in different classes. The dataset was collected during two UAV flights over a fenced enclosure with wild hoofed animals. The proposed approach showed high efficiency, achieving an overall accuracy of 90%. These results confirm the feasibility of UAV-based animal detection based solely on thermal images collected during the day and showing many other heated objects. The method provides a solution for wildlife monitoring, with potential adaptability to different species and further applications.
FUNDING
The APC/BPC is financed/co-financed by Wrocław University of Environmental and Life Sciences.
REFERENCES (33)
1.
Afshari H.H., Gadsden S.A., Habibi S. (2017). Gaussian filters for parameter and state estimation: A general review of theory and recent trends. Signal Processing. 135: 218-238. doi:10.1016/j.sigpro.2017.01.001.
 
2.
Baskin Leonid, Danell Kjell. (2003). Ecology of ungulates: A handbook of species in Eastern Europe and Northern and Central Asia. Springer Science and Business Media.
 
3.
Browne Michael W. (2000). Cross-Validation Methods. Journal of Mathematical Psychology. 44 (1): 108-132. doi:10.1006/jmps.1999.1279.
 
4.
Burton A. Cole, Neilson Eric, Moreira Dario, Ladle Andrew, Steenweg Robin, Fisher Jason T., Bayne Erin, Boutin Stan. (2015). REVIEW: Wildlife camera trapping: a review and recommendations for linking surveys to ecological processes. Journal of Applied Ecology. 52 (3): 675-685. doi:10.1111/1365-2664.12432.
 
5.
Chicco Davide, Warrens Matthijs J., Jurman Giuseppe. (2021). The Matthews Correlation Coefficient (MCC) is More Informative Than Cohen’s Kappa and Brier Score in Binary Classification Assessment. IEEE Access. 9: 78368-78381. doi:10.1109/access.2021.3084050.
 
6.
Christiansen Peter, Steen Kim, Jørgensen Rasmus, Karstoft Henrik. (2014). Automated Detection and Recognition of Wildlife Using Thermal Cameras. Sensors. 14 (8): 13778-13793. doi:10.3390/s140813778.
 
7.
Crow L., Watts S. J. (2024). Limits to classification performance by relating Kullback-Leibler divergence to Cohen's Kappa. doi:10.48550/ARXIV.2403.01571.
 
8.
De Oliveira Diulhio C, ido, Wehrmeister Marco Aurelio. (2018). Using Deep Learning and Low-Cost RGB and Thermal Cameras to Detect Pedestrians in Aerial Images Captured by Multirotor UAV. Sensors. 18 (7): 2244-2244. doi:10.3390/s18072244.
 
9.
Deng G., Cahill L.W. (1993). An adaptive Gaussian filter for noise reduction and edge detection. 1993 IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference. doi:10.1109/nssmic.1993.373563.
 
10.
Foley Conrad J., Sillero-Zubiri Claudio. (2020). Open-source, low-cost modular GPS collars for monitoring and tracking wildlife. Methods in Ecology and Evolution. 11 (4): 553-558. doi:10.1111/2041-210x.13369.
 
11.
Ford Adam T., Clevenger Anthony P., Bennett Andrew. (2009). Comparison of Methods of Monitoring Wildlife Crossing-Structures on Highways. The Journal of Wildlife Management. 73 (7): 1213-1222. doi:10.2193/2008-387.
 
12.
Hodgson Jarrod C., Baylis Shane M., Mott Rowan, Herrod Ashley, Clarke Rohan H. (2016). Precision wildlife monitoring using unmanned aerial vehicles. Scientific Reports. 6 (1). doi:10.1038/srep22574.
 
13.
Jeni Laszlo, Cohn Jeffrey, De La, o. (2013). Facing Imbalanced Data-Recommendations for the Use of Performance Metrics. 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction. 245-251. doi:10.1109/acii.2013.47.
 
14.
Jewell Zoe. (2013). Effect of Monitoring Technique on Quality of Conservation Science. Conservation Biology. 27 (3): 501-508. doi:10.1111/cobi.12066.
 
15.
Kalinowski Paweł, Szczepaniak Paweł, Ułanowicz Leszek, Sibilski Krzysztof. (2023). Zastosowanie aerofotogrametrii w podczerwieni do śledzenia dzików w ich naturalnym środowisku oraz identyfikacji osobników zarażonych afrykańskim pomorem świń. cz. I - Architektura systemu i metodyka identyfikacji (Application of aerophotogrammetry in infrared to track wild boars in their natural environment and identify individuals infected with African swine fever. Part I - System architecture and identification methodology). Mechanika w Lotnictwie. : 165-183. doi:10.15632/ml2022/165-183.
 
16.
Lee Eun Ju, Shin Sang Young, Ko Byoung Chul, Chang Chunho. (2016). Early sinkhole detection using a drone-based thermal camera and image processing. Infrared Physics and Technology. 78: 223-232. doi:10.1016/j.infrared.2016.08.009.
 
17.
Lee Seunghyeon, Song Youngkeun, Kil Sung-Ho. (2021). Feasibility Analyses of Real-Time Detection of Wildlife Using UAV-Derived Thermal and RGB Images. Remote Sensing. 13 (11): 2169-2169. doi:10.3390/rs13112169.
 
18.
Lyu Haitao, Qiu Fang, An Li, Stow Douglas, Lewison Rebecca, Bohnett Eve. (2024). Deer survey from drone thermal imagery using enhanced faster R-CNN based on ResNets and FPN. Ecological Informatics. 79: 102383-102383. doi:10.1016/j.ecoinf.2023.102383.
 
19.
More A. S., Rana Dipti P. (2017). Review of random forest classification techniques to resolve data imbalance. 2017 1st International Conference on Intelligent Systems and Information Management (ICISIM). 72-78. doi:10.1109/icisim.2017.8122151.
 
20.
Nyhus Philip. (2016). Human-Wildlife Conflict and Coexistence. Annual Review of Environment and Resources. 41 (1): 143-171. doi:10.1146/annurev-environ-110615-085634.
 
21.
O'Shea Keiron, Nash Ryan. (2015). An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458. doi:10.48550/arXiv.1511.08458.
 
22.
Pollock Kenneth H., Nichols James D., Simons Theodore R., Farnsworth George L., Bailey Larissa L., Sauer John R. (2002). Large scale wildlife monitoring studies: statistical methods for design and analysis. Environmetrics. 13 (2): 105-119. doi:10.1002/env.514.
 
23.
Ramadhan Adam Lutfi. (2024). Understanding Human-Wildlife Interactions in Urban Environments: Implications for Conflicts, Disease Transmission, and Conservation. Law and Economics. 18 (2): 99-109.
 
24.
Rančić Kristina, Blagojević Boško, Bezdan Atila, Ivošević Bojana, Tubić Bojan, Vranešević Milica, Pejak Branislav, Crnojević Vladimir, Marko Oskar. (2023). Animal Detection and Counting from UAV Images Using Convolutional Neural Networks. Drones. 7 (3): 179-179. doi:10.3390/drones7030179.
 
25.
Ridwan Qamer, Wani Zishan, Anjum Nahila, Bhat Jahangeer, Hanief Mohd, Pant Shreekar. (2023). Human-wildlife conflict: A bibliometric analysis during 1991-2023. Regional Sustainability. 4 (3): 309-321. doi:10.1016/j.regsus.2023.08.008.
 
26.
Tuia Devis, Kellenberger Benjamin, Beery Sara, Costelloe Blair R., Zuffi Silvia, Risse Benjamin, Mathis Alex, er, Mathis Mackenzie W., van Langevelde Frank, Burghardt Tilo, Kays Rol, Klinck Holger, Wikelski Martin, Couzin Iain D., van Horn Grant, Crofoot Margaret C., Stewart Charles V., Berger-Wolf Tanya. (2022). Perspectives in machine learning for wildlife conservation. Nature Communications. 13 (1). doi:10.1038/s41467-022-27980-y.
 
27.
Verma Audrey, van der Wal René, Fischer Anke. (2016). Imagining wildlife: New technologies and animal censuses, maps and museums. Geoforum. 75: 75-86. doi:10.1016/j.geoforum.2016.07.002.
 
28.
Vujovic Z D. (2021). Classification Model Evaluation Metrics. International Journal of Advanced Computer Science and Applications. 12 (6). doi:10.14569/ijacsa.2021.0120670.
 
29.
Watanabe Shuhei. (2023). Tree-structured parzen estimator: Understanding its algorithm components and their roles for better empirical performance. arXiv preprint arXiv:2304.11127. doi:10.48550/arXiv.2304.11127.
 
30.
Witczuk Julia, Pagacz Stanisław, Zmarz Anna, Cypel Maciej. (2017). Exploring the feasibility of unmanned aerial vehicles and thermal imaging for ungulate surveys in forests - preliminary results. International Journal of Remote Sensing. 39 (15--16): 5504-5521.
 
31.
Witmer Gary W. (2005). Wildlife population monitoring: some practical considerations. Wildlife Research. 32 (3): 259-259.
 
32.
Woźniakowski Grzegorz, Pejsak Zygmunt, Jabłoński Artur. (2021). Emergence of African Swine Fever in Poland (2014--2021). Successes and Failures in Disease Eradication. Agriculture. 11 (8): 738-738.
 
33.
Yang Shuting, Gu Lingjia, Li Xiaofeng, Jiang Tao, Ren Ruizhi. (2020). Crop Classification Method Based on Optimal Feature Selection and Hybrid CNN-RF Networks for Multi-Temporal Remote Sensing Imagery. Remote Sensing. 12 (19): 3119-3119.
 
eISSN:2391-8152
ISSN:2391-8365
Journals System - logo
Scroll to top