Recognition of Amazonian forest species using transverse surface images

• Artur Jefferson F. da Silva UTFPR http://orcid.org/0009-0002-1280-2417
• Jandrei Sartori Spancerski UTFPR http://orcid.org/0000-0002-4077-281X
• Kelyn Schenatto UTFPR http://orcid.org/0000-0002-1810-679X
• Silvana Nisgoski UFPR http://orcid.org/0000-0001-9595-9131
• Pedro Luiz de Paula Filho UTFPR http://orcid.org/0000-0002-6291-9237

DOI: https://doi.org/10.5753/latinoware.2024.245540

Abstract

Environmental monitoring research has spurred the development of various technologies for ecosystem conservation. This paper explores the application of the YOLOv8 architecture for identifying Amazonian tree species using computer vision techniques. The study focuses on analyzing transverse wood section images, with a publicly available dataset comprising 2,160 images across 18 distinct species. The model was trained and validated, achieving high accuracy in species recognition, with test results showing accuracy levels up to 99%. The goal is to develop a solution that accurately recognizes species, aiding forest protection and improving enforcement against illegal logging.

Keywords: environmental monitoring, YOLOv8, species identification, computer vision, Amazon biome, illegal logging

References

C. A. Boulton, T. M. Lenton, and N. Boers, “Pronounced loss of amazon rainforest resilience since the early 2000s,” Nature Climate Change, vol. 12, pp. 271–278, Mar. 2022. [Online]. Available: DOI: 10.1038/s41558-022-01287-8

L. V. Gatti, L. S. Basso, J. B. Miller, M. Gloor, L. G. Domingues, H. L. G. Cassol, G. Tejada, L. E. O. C. Aragão, C. Nobre, W. Peters, L. Marani, E. Arai, A. H. Sanches, S. M. Corrêa, L. Anderson, C. V. Randow, C. S. C. Correia, S. P. Crispim, and R. A. L. Neves, “Amazonia as a carbon source linked to deforestation and climate change,” Nature Climate Change, vol. 595, pp. 388–393, Mar. 2021. [Online]. Available: DOI: 10.1038/s41586-021-03629-6

R. B. Souza, R. B. B. Souza, F. R. F. Júnior, and P. P. de Almeida Neto, “Efeitos da extração de madeira sobre a biodiversidade em florestas tropicais,” Natural Resources, vol. 11, p. 3, Jul. 2021. [Online]. Available: DOI: 10.6008/CBPC2237-9290.2021.003.0005

P. L. de Paula Filho, “Reconhecimento de espécies florestais através de imagens macroscópicas,” Ph.D. dissertation, Universidade Federal do Paraná, 2012. [Online]. Available: [link]

H. A. Ghapar, U. Khairuddin, R. Yusof, A. S. M. Khairuddin, and A. Ahmad, “New Feature Extraction for Wood Species Recognition System via Statistical Properties of Line Distribution,” 2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), pp. 1–5, Feb. 2021. [Online]. Available: [link]

S. Neethu and L. B. Syla, “Wood Species Recognition Using Machine Learning,” 2021 Fourth International Conference on Microelectronics, Signals & Systems (ICMSS), pp. 1–6, Feb. 2021. [Online]. Available: [link]

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” 2016. [Online]. Available: [link]

F. Solimani, A. Cardellicchio, G. Dimauro, A. Petrozza, S. Summerer, F. Cellini, and V. Renò, “Optimizing tomato plant phenotyping detection: Boosting yolov8 architecture to tackle data complexity,” Computers and Electronics in Agriculture, vol. 218, p. 108728, 2024. [Online]. Available: [link]

J. Terven, D.-M. Córdova-Esparza, and J.-A. Romero-González, “A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas,” Machine Learning and Knowledge Extraction, vol. 5, no. 4, p. 1680–1716, Nov. 2023. [Online]. Available: DOI: 10.3390/make5040083

Ultralytics, “Enterprise software license,” 2023. [Online]. Available: [link]

F. Wu, R. Gazo, E. Haviarova, and B. Benes, “Wood identification based on longitudinal section images by using deep learning,” Wood Science and Technology, no. 55, p. 553–563, Aug. 2021. [Online]. Available: DOI: 10.1007/s00226-021-01261-1

A. R. de Geus, S. F. d. Silva, A. B. Gontijo, F. O. Silva, M. A. Batista, and J. R. Souza, “An analysis of timber sections and deep learning for wood species classification,” Multimedia Tools and Applications, vol. 79, no. 45, pp. 34 513–34 529, 2020. [Online]. Available: DOI: 10.1007/s11042-020-09212-x

J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” 2018. [Online]. Available: [link]

A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” 2020. [Online]. Available: [link]

H. Zhang, M. Cisse, Y. N. Dauphin, and D. Lopez-Paz, “mixup: Beyond empirical risk minimization,” 2018. [Online]. Available: [link]

N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, no. 56, pp. 1929–1958, 2014. [Online]. Available: [link]