Deep learning based poplar tree detection and counting using multispectral UAV images
Keywords:
Poplar trees, Deep learning, Tree detection, Tree counting, YOLOv7Abstract
Poplars (Populus sp.), a member of fast-growing and short-lived tree species, have been widely planted since ancient times. Identification and mapping of poplar planted areas on global and local scales, as well as the automatic crown detection and counting of individual poplar trees in a given area provide valuable information to decision-makers in developing strategies for planting area estimation, growth monitoring and yield estimation. At this point, offering significant advantages compared to traditional methods, remote sensing technologies, especially unmanned aerial vehicle (UAV) systems, have become a prominent data source in individual tree crown detection. In this study, one of the latest You Only Look Once (YOLO) algorithms, YOLOv7, was applied to high-resolution multispectral UAV captured images to detect and count individual poplar (P. deltoides) trees. For this purpose, a UAV-derived orthomosaic image covering dense hybrid poplar tree plantations in the Akyazı district of Sakarya province was used as the primary data source. Training and validation datasets were created from the orthomosaic with a total of 260 images and 19.989 instances. Results showed that the YOLOv7 model achieved the precision, recall, mean average precision, and F-score values for the bounding boxes of poplar trees as 86.50%, 86.80%, 87.80%, and 88.20%, respectively.
References
Isebrands, J. G. & Richardson, J. (2014). Poplars and Willows: Trees for Society and the Environment CAB International and Food and Agriculture Organization of the United Nations (FAO), CABI, p. 634.
Ke, Y., & Quackenbush, L. J. (2011). A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing. International Journal of Remote Sensing, 32(17), 4725-4747.
Gan, Y., Wang, Q., & Iio, A. (2023). Tree Crown Detection and Delineation in a Temperate Deciduous Forest from UAV RGB Imagery Using Deep Learning Approaches: Effects of Spatial Resolution and Species Characteristics. Remote Sensing, 15(3), 778.
Ateşoğlu, A., Kavzoğlu, T., Çölkesen, İ., Özlüsoylu, Ş., Tonbul, H., Yılmaz, E. Ö. & Öztürk, M. Y. (2022). Türkiye'de Hızlı Büyüyen Türlere Ait Spektral Kütüphane Kurulması: Kavak Türleri Çalışması. Bartın Orman Fakültesi Dergisi, 24 (2), 324-338.
Colkesen, I., Kavzoglu, T., Atesoglu, A., Tonbul, H., & Ozturk, M. Y. (2022). Multi-seasonal evaluation of hybrid poplar (P. Deltoides) plantations using Worldview-3 imagery and state-of-the-art ensemble learning algorithms. Advances in Space Research. https://doi.org/10.1016/j.asr.2022.10.044
Diez, Y., Kentsch, S., Fukuda, M., Caceres, M. L. L., Moritake, K., & Cabezas, M. (2021). Deep learning in forestry using UAV-acquired RGB data: A practical review. Remote Sensing, 13(14), 2837.
Yu, K., Hao, Z., Post, C. J., Mikhailova, E. A., Lin, L., Zhao, G., ... & Liu, J. (2022). Comparison of classical methods and mask R-CNN for automatic tree detection and mapping using UAV imagery. Remote Sensing, 14(2), 295.
Zhu, Y., Zhou, J., Yang, Y., Liu, L., Liu, F., & Kong, W. (2022). Rapid Target Detection of Fruit Trees Using UAV Imaging and Improved Light YOLOv4 Algorithm. Remote Sensing, 14(17), 4324.
Yildirim, E., Nazar, M., Sefercik, U. G., & Kavzoglu, T. (2022). Stone Pine (Pinus Pinea L.) Detection from High-Resolution UAV Imagery Using Deep Learning Model. In IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium (pp. 441-444). IEEE.
Vimal, S., & Subbulakshmi, P. (2016). Secure data packet transmission in MANET using 18 enhanced identity-based cryptography. International Journal of New Technologies in Science and Engineering, 3(12), 35-42.
Chen, Y., Yang, T., Zhang, X., Meng, G., Xiao, X., & Sun, J. (2019). Detnas: Backbone search for object detection. Advances in Neural Information Processing Systems, 32.
Rothe, R., Guillaumin, M., & Van Gool, L. (2015). Non-maximum suppression for object detection by passing messages between windows. In Computer Vision–ACCV 2014: 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised Selected Papers, Part I 12 (pp. 290-306). Springer International Publishing.
Chen, J., Liu, H., Zhang, Y., Zhang, D., Ouyang, H., & Chen, X. (2022). A Multiscale Lightweight and Efficient Model Based on YOLOv7: Applied to Citrus Orchard. Plants, 11(23), 3260.
