The Effect of Pre- and Post-Processing Techniques on Tree Detection in Young Forest Stands from Images of Snow Cover Using YOLO Neural Networks

Year 2024, Volume: 10 Issue: 2, 149 - 159, 13.12.2024

Aleksey Portnov , Andrey Shubin Gulfina Frolova

https://doi.org/10.33904/ejfe.1462335

Abstract

A neural network model for individual tree detection was developed based on the YOLOv4 architecture, which underwent additional preprocessing and postprocessing steps. The preprocessing step involved expanding the dataset by randomly cutting fragments from images, calculating anchor box sizes using the K-means clustering algorithm, and discarding anchor boxes that were too small a priori. The existing post-processing block of the YOLO architecture was modified by giving more weight to false positives in the error function and using the non-maximum suppression algorithm. Baseline neural networks from the YOLOv4 and YOLOv5 architectures, each in two versions (pre-trained and not pre-trained on the MS COCO dataset), were used for comparison without any additional modifications. In the overgrown experimental field, multi-season aerial copter surveys and ground counts were conducted on several sample plots to gather data. Comparison of multi-season aerial photographs with ground-count data showed that the best images in terms of the percentage of visually identifiable trees were those taken during the snowy season and when there was no foliage. Using these images and some additional images, we manually created a dataset on which we trained and tested neural network models. The model we developed showed significantly better results (2 to 10 times better) on the mAP 0.5 metric compared to the alternatives we considered.

Keywords

Individual tree detection, Convolutional neural networks, YOLO, Pre- and post-processing of data, Aerial photography, Young forest stands

Supporting Institution

This work was conducted within the framework of the state assignment of the Federal Research Centre for Scientific Biology of the Russian Academy of Sciences, registration number 122111000095-8

Thanks

The authors would like to thank Elena Babenko, Lukyan Mirny, Aleksey Nikonov and Svetlana Urabova for their assistance in preparing the data set. We would also like to extend our gratitude to Anastasia Iovcheva, who provided valuable advice on soil classification, and Vladimir Shanin, Candidate of Science, for his expertise on the structure and design of this article.

References

• Al-Wassai, F.A., Kalyankar, N.V. 2013. Major limitations of satellite images. Journal of Global Research in Computer Science, 4(5):51–59.
• Aleksanin, A.I., Kim, V., Morozov, M.A., Fomin, E.V. 2019. Obnaruzhenie rubok otdel'nyh derev'ev po tenyam na osnove snimkov pribora "Geoton" sputnika "Resurs-P" [Detection of individual tree felling by shadows on the basis of images of Geoton instrument of Resurs-P satellite]. Sovremennye problemy distancionnogo zondirovaniya Zemli iz kosmosa, 16(5):174–182. [In Russian]. DOI:10.21046/2070-7401-2019-16-5-174-182.
• Alifanov, V.M. 1995. Klyuchevoj uchastok "Pushchino". In: Paleokriogenez i sovremennoe pochvoobrazovanie [Pushchino key site. In: Paleocryogenesis and modern soil formation]. Izdatel'stvo ONTI Pushchinskogo nauchnogo centra Rossijskoj akademii nauk, Pushchino. pp. 95–156. [In Russian].
• Ayrey, E., Fraver, S., Kershaw, Jr. J.A., Kenefic, L.S., Hayes, D., Weiskittel, A.R., Roth, B.E. 2017. Layer stacking: A novel algorithm for individual forest tree segmentation from LiDAR point clouds. Canadian Journal of Remote Sensing, 43(1):16–27. DOI:10.1080/07038992. 2017.1252907.
• Bartalev, S., Egorov, V., Zharko, V., Loupian, E., Plotnikov, D., Khvostikov, S., Shabanov, N. 2016. Sputnikovoe kartografirovanie rastitel'nogo pokrova Rossii [Land cover mapping over Russia using Earth observation data]. IKI RAN, Moscow. 208 p. [in Russian].
• Baumann, M., Ozdogan, M., Kuemmerle, T., Wendland, K.J., Esipova, E., Radeloff, V.C. 2012. Using the Landsat record to detect forest-cover changes during and after the collapse of the Soviet Union in the temperate zone of European Russia. Remote Sensing of Environment, 124:174–184. DOI:10.1016/j.rse. 2012.05.001.
• Bennett, G., Hardy, A., Bunting, P., Morgan, P., Fricker, A. 2020. A transferable and effective method for monitoring continuous cover forestry at the individual tree level using UAVs. Remote sensing, 12(13):2115. DOI:10.3390/rs12132115.
• Berland, A., Shiflett, S.A., Shuster, W.D., Garmestani, A.S., Goddard, H.C., Herrmann, D.L., Hopton, M.E. 2017. The role of trees in urban stormwater management. Landscape and Urban Planning, 162:167–177. DOI:10.1016/j.landurbplan.2017.02.0 17.
• Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M. 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. DOI:10.48550/arXiv.2004.10934.
• Bohlin, J., Wallerman, J., Fransson, J.E.S. 2012. Forest variable estimation using photogrammetric matching of digital aerial images in combination with a high-resolution DEM. Scandinavian Journal of Forest Research, 27(7):692–699. DOI:10.1080/02827581. 2012.686625.
• Brandtberg, T., Walter, F. 1998. Automated delineation of individual tree crowns in high spatial resolution aerial images by multiple-scale analysis. Machine Vision and Applications, 11:64–73. DOI:10.1007/s001380050091.
• Brūmelis, G., Dauškane, I., Elferts, D., Strode, L., Krama, T., Krams, I. 2020. Estimates of tree canopy closure and basal area as proxies for tree crown volume at a stand scale. Forests, 11(11):1180. DOI:10.3390/f11111180.
• Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., Kalinin, A.A. 2020. Albumentations: fast and flexible image augmentations. Information, 11(2):125. DOI: 10.3390/info11020125.
• Cheang, E.K., Cheang, T.K., Tay, Y.H. 2017. Using convolutional neural networks to count palm trees in satellite images. arXiv preprint arXiv:1701.06462. DOI:10.48550/arXiv.1701.06462.
• Chemura, A., van Duren, I., van Leeuwen, L.M. 2015. Determination of the age of oil palm from crown projection area detected from WorldView-2 multispectral remote sensing data: The case of Ejisu-Juaben district, Ghana. ISPRS Journal of Photogrammetry and Remote Sensing, 100:118–127. DOI:10.1016/j.isprsjprs.2014.07.013.
• Condit, R. 1998. Total Cost for a Large Plot. In: Tropical Forest Census Plots: Methods and Results from Barro Colorado Island, Panama and a Comparison with Other Plots. Springer, Berlin. pp. 97–99.
• Ershov, D.V., Gavrilyuk, E.A., Tikhonova, E.V., Braslavskaya, T.Y., Koroleva, N.V., Bavshin, I.M., Grummo, D.G., Sudnik, A.V., Titovets, A.V. 2020. Veroyatnostnaya ocenka raspredeleniya klyuchevyh biotopov v lesah nacional'nogo parka “Smolenskoe Poozer'e” na osnove sputnikovyh i topograficheskih dannyh [Stochastic Evaluation of Key Biotopes Allocation in the Forests of “Smolenskoe Poozer’ye” National Park Based on Satellite and Topographic Data]. Lesovedenie 1:17–34. [In Russian]. DOI:10.31857/S0024114820010052.
• Fang, L., Zhao, J., Pan, Z., Li, Y. 2023. TPP: Deep learning based threshold post-processing multi-focus image fusion method. Computers and Electrical Engineering, 110:108736. DOI:10.1016/j.compe leceng.2023.108736
• Fujimoto, A., Haga, C., Matsui, T., Machimura, T., Hayashi, K., Sugita, S., Takagi, H. 2019. An end to end process development for UAV-SfM based forest monitoring: individual tree detection, species classification and carbon dynamics simulation. Forests, 10(8):680. DOI:10.3390/ f10080680.
• Gardner, T.A., Barlow, J., Araujo, I.S., Ávila-Pires, T.C., Bonaldo, A.B., Costa, J.E., Esposito, M.C., Ferreira, L.V., Hawes, J., Hernandez, M.I.M, Hoogmoed, M.S., Leite, R.N., Lo-Man-Hung, N.F., Malcolm, J.R., Martins, M.B., Mestre, L.A.M., Miranda-Santos, R., Overal, W.L., Parry, L., Peters, S.L., Ribeiro-Junior, M.A., Da Silva, M.N.F., Motta, C.D.S., Peres, C.A. 2008. The cost-effectiveness of biodiversity surveys in tropical forests. Ecology Letters, 11(2):139–150. DOI:10.1111/j.1461-0248.2007.01133.x
• Heinrich, V.H.A., Dalagnol, R., Cassol, H.L., Rosan, T.M., de Almeida, C.T., Silva Jr., C.H., Campanharo, W.A., House, J.I., Sitch, S., Hales, T.C., Adami, M., Anderson, L.O., Aragão, L.E. 2021. Large carbon sink potential of secondary forests in the Brazilian Amazon to mitigate climate change. Nature Communications, 12(1):1785. DOI:10.1038/s41467-021-22050-1.
• Holopainen, M., Vastaranta, M., Karjalainen, M., Karila, K., Kaasalainen, S., Honkavaara, E., Hyyppä, J. 2015. Forest inventory attribute estimation using airborne laser scanning, aerial stereo imagery, radargrammetry and interferometry-finnish experiences of the 3d techniques. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2:63–69.DOI:10.5194/isprsannals-II-3-W4-63-2015.
• Ivanova, N.V., Shashkov, M.P., Shanin, V.N. 2021a. Obtaining tree stand attributes from unmanned aerial vehicle (UAV) data: the case of mixed forests. Vestnik Tomskogo gosudarstvennogo universiteta. Biologiya = Tomsk State University Journal of Biology, 54:158–175. [In Russian, English Summary]. DOI:10.17223/19988591/54/8.
• Ivanova, N.V., Shashkov, M.P., Shanin, V.N. 2021b. Study of pine forest stand structure in the Priosko-Terrasny State Nature Biosphere Reserve (Russia) based on aerial photography by quadrocopter. Nature Conservation Research, 6(4):1–14. [In Russian, English Summary]. DOI:10.24189/ncr.2021.042.
• Jhang, K. 2020. Voting and ensemble schemes based on CNN models for photo-based gender prediction. Journal of Information Processing Systems, 16(4):809–819. DOI:10.3745/ JIPS.02.0137.
• Joshi, N., Mitchard, E.T., Brolly, M., Schumacher, J., Fernández-Landa, A., Johannsen, V.K., Marchamalo, M., Fensholt, R. 2017. Understanding 'saturation' of radar signals over forests. Scientific Reports, 7(1):3505. DOI:10.1038/s41598-017-03469-3.
• Khanina, L.G., Smirnov, V.E., Romanov, M.S., Bobrovsky, M.V. 2018. Effect of spring grass fires on vegetation patterns and soil quality in abandoned agricultural lands at local and landscape scales in Central European Russia. Ecological Processes, 7(1):1–19. DOI:10.1186/s13717-018-0150-8.
• Khati, U., Singh, G. 2022. Combining L-band Synthetic Aperture Radar backscatter and TanDEM-X canopy height for forest aboveground biomass estimation. Frontiers in Forests and Global Change 5:918408. DOI:10.3389/ffgc.2022.918408.
• Koch, B., Heyder, U., Weinacker, H. 2006. Detection of individual tree crowns in airborne lidar data. Photogrammetric Engineering & Remote Sensing, 72(4):357–363. DOI:10.14358/PERS.72.4.357.
• Kondratyev, K.Y., Kozoderov, V.V., Smokty, O.I. 2013. Remote sensing of the Earth from space: atmospheric correction. Springer Science & Business Media.
• Kutyrev, A.I., Smirnov, I.G., Andriyanov, N.A. 2023. Sravnitel'nyj analiz modelej nejronnyh setej dlya raspoznavaniya plodov yabloni na krone dereva [Neural network models of apple fruit identification in tree crowns: comparative analysis]. Sadovodstvo i vinogradarstvo, 5:56–63. [In Russian]. DOI:10.31676/0235-2591-2023-5-56-63.
• Kuzmin, A., Korhonen, L., Manninen, T., Maltamo, M. 2016. Automatic segment-level tree species recognition using high resolution aerial winter imagery. European Journal of Remote Sensing, 49(1):239–259. DOI:10.5721/EuJRS20164914.
• Larson, A.J., Lutz, J.A., Donato, D.C., Freund, J.A., Swanson, M.E., HilleRisLambers, J., Sprugel, D.G., Franklin, J.F. 2015. Spatial aspects of tree mortality differ strongly between young and old-growth forests. Ecology, 96(11):2855–2861. DOI:10.1890/15-0628.1.
• Li, C.T., Chung, P.C., Tsai, H.W., Chow, N.H., Cheng, K.S. 2019. Inflammatory cells detection in H&E staining histology images using deep convolutional neural network with distance transformation. In: New Trends in Computer Technologies and Applications: 23rd International Computer Symposium, ICS 2018, Yunlin, Taiwan, December 20-22, 2018, Revised Selected Papers 23. Springer, Singapore. pp. 665–672. DOI:10.1007/978-981-13-9190-3_73.
• Li, H., Chen, L., Yao, Z., Li, N., Long, L., Zhang, X. 2023. Intelligent Identification of Pine Wilt Disease Infected Individual Trees Using UAV-Based Hyperspectral Imagery. Remote Sensing, 15(13):3295. DOI:10.3390/rs15133295.
• Li, L., Dong, J., Tenku, S.N., Xiao, X. 2015. Mapping oil palm plantations in Cameroon using PALSAR 50-m orthorectified mosaic images. Remote Sensing, 7(2):1206–1224. DOI:10.3390/rs70201206.
• Li, W., Dong, R., Fu, H., Yu, L. 2018. Large-scale oil palm tree detection from high-resolution satellite images using two-stage convolutional neural networks. Remote Sensing, 11(1):11. DOI:10.3390/rs11010011.
• Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., Dollár, P. 2015. Microsoft COCO: Common Objects in Context. arXiv preprint arXiv:1405.0312v3.DOI:10.48550/arXiv.1405.0312.
• Livesley, S.J., McPherson, E.G., Calfapietra, C. 2016. The urban forest and ecosystem services: Impacts on urban water, heat, and pollution cycles at the tree, street, and city scale. Journal of Environmental Quality, 45(1):119-124. DOI:10.2134/jeq2015.11.05 67.
• Luoma, V., Saarinen, N., Wulder, M.A., White, J.C., Vastaranta, M., Holopainen, M., Hyyppä, J. 2017. Assessing precision in conventional field measurements of individual tree attributes. Forests, 8(2):38. DOI:10.3390/f8020038.
• Malek, S., Bazi, Y., Alajlan, N., AlHichri, H., Melgani, F. 2014. Efficient framework for palm tree detection in UAV images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(12):4692–4703. DOI:10.1109/JSTARS.2014.2331 425.
• Maschler, J., Atzberger, C., Immitzer, M. 2018. Individual tree crown segmentation and classification of 13 tree species using airborne hyperspectral data. Remote Sensing, 10(8):1218. DOI:10.3390/ rs10081218.
• Maslov, A., Gulbe, A., Gulbe, Y., Medvedeva, N., Sirin, A. 2016. Otsenka situatsii s zarastaniem selskohozyaystvennyh zemel lesnoy rastitelnostyu na primere Uglichskogo rayona Yaroslavskoy oblasti [Assessment of the overgrowing of agricultural land by forest vegetation on the example of the Uglich district of the Yaroslavl region]. Ustoychivoe losepolzovanie 48:6–14 [in Russian].
• Mumuni, A. and Mumuni, F. 2022. Data augmentation: A comprehensive survey of modern approaches. Array,16:100258. DOI:10.1016/j.array.2022.100258.
• Nelson, J. and Solawetz, J. 2024. YOLOv5 is Here: State-of-the-Art Object Detection in 140 FPS. https://blog.roboflow.com/yolov5-is-here/(Accessed: 26 March 2024).
• Neuville, R., Bates, J.S., Jonard, F. 2021. Estimating forest structure from UAV-mounted LiDAR point cloud using machine learning. Remote Sensing, 13(3):352. DOI:10.3390/rs13030352.
• Padilla, R., Passos, W.L., Dias, T.L.B., Netto, S.L., da Silva, E.A.B. 2021. A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit. Electronics, 10(3):279. DOI:10.3390/electronics10030279.
• Pix4D. Pix4Dcapture. URL: https://www.pix4d.com /product/pix4dcapture (Accessed: 26 March 2024).
• Pix4D. Ctrl+DJI. URL: https://ctrl-dji.en. aptoide.com/ app (Accessed: 26 March 2024).
• Pollock, R. 1996a. The Recognition Task. In: The automatic recognition of individual trees in aerial images of forests based on a synthetic tree crown image model. Diss. University of British Columbia. pp. 17–29. DOI:10.14288/1.0051597.
• Pollock, R. 1996b. Background. In: The automatic recognition of individual trees in aerial images of forests based on a synthetic tree crown image model. pp. 5-17. Diss. University of British Columbia. DOI:10.14288/1.0051597.
• Pouliot, D.A., King, D.J., Bell, F.W., Pitt, D.G. 2002. Automated tree crown detection and delineation in high-resolution digital camera imagery of coniferous forest regeneration. Remote Sensing of Environment, 82(2-3):322–334. DOI:10.1016/S0034-4257(02)000 50-0.
• Pugh, T.A., Lindeskog, M., Smith, B., Poulter, B., Arneth, A., Haverd, V., Calle, L. 2019. Role of forest regrowth in global carbon sink dynamics. Proceedings of the National Academy of Sciences 116(10):4382–4387. DOI:10.1073/pnas.1810512116.
• Puliti, S., Gobakken, T., Ørka, H.O., Næsset, E. 2017. Assessing 3D point clouds from aerial photographs for species-specific forest inventories. Scandinavian Journal of Forest Research, 32(1):68–79. DOI:10.1080/02827581.2016.1186727.
• Rahlf, J., Breidenbach, J., Solberg, S., Næsset, E., Astrup, R. 2014. Comparison of four types of 3D data for timber volume estimation. Remote Sensing of Environment, 155:325–333. DOI:10.1016/j.rse.2014. 08.036.
• Rebane, S., Jõgiste, K., Kiviste, A., Stanturf, J.A., Metslaid, M. 2020. Patterns of carbon sequestration in a young forest ecosystem after clear-cutting. Forests, 11(2):126. DOI:10.3390/f11020126.
• Redmon, J., Divvala, S., Girshick, R., Farhadi, A. 2016. You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp. 779–788. DOI:10.1109/CVPR.2016.91.
• Redmon J. and Farhadi A. 2017. YOLO9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp. 7263–7271. DOI:10.1109/ CVPR.2017.690.
• Rizeei, H.M., Shafri, H.Z., Mohamoud, M.A., Pradhan, B., Kalantar, B. 2018. Oil palm counting and age estimation from WorldView-3 imagery and LiDAR data using an integrated OBIA height model and regression analysis. Journal of Sensors, 2018:1–13. DOI:10.1155/2018/2536327.
• Saarinen, N., Vastaranta, M., Näsi, R., Rosnell, T., Hakala, T., Honkavaara, E., Wulder, M.A., Luoma, V., Tommaselli, A.M.G, Imai, N.N., Ribeiro, E.A.W., Guimarães, R.B., Holopainen, M., Hyyppä, J. 2018. Assessing biodiversity in boreal forests with UAV-based photogrammetric point clouds and hyperspectral imaging. Remote Sensing, 10(2):338. DOI:10.3390/rs10020338.
• Salvi, M., Acharya, U.R., Molinari, F., Meiburger, K.M. 2021. The impact of pre-and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis. Computers in Biology and Medicine, 128:104129. DOI:10.1016/j.compbiomed.2020.1041 29.
• Schepaschenko, D., Moltchanova, E., Fedorov, S., Karminov, V., Ontikov, P., Santoro, M., See, L., Kositsyn, V., Shvidenko, A., Romanovskaya, A., Korotkov, V., Lesiv, M., Bartalev, S., Fritz, S., Shchepashchenko, M., Kraxner, F. 2021. Russian forest sequesters substantially more carbon than previously reported. Scientific Reports 11(1):12825. DOI:10.1038/s41598-021-92152-9.
• Secord, J., Zakhor, A. 2007. Tree detection in urban regions using aerial lidar and image data. IEEE Geoscience and Remote Sensing Letters, 4(2):196–200. DOI:10.1109/LGRS.2006.888107.
• Shen, X., Weng, L., Xia, M., Lin, H. 2022. Multi-scale feature aggregation network for semantic segmentation of land cover. Remote Sensing 14(23):6156. DOI:10.3390/rs14236156.
• Shendryk, I., Broich, M., Tulbure, M.G., McGrath, A., Keith, D., Alexandrov, S.V. 2016. Mapping individual tree health using full-waveform airborne laser scans and imaging spectroscopy: A case study for a floodplain eucalypt forest. Remote Sensing of Environment, 187:202–217. DOI:10.1016/j.rse.2016. 10.014.
• Soloviev, S.V., Miller, G.F., Bezborodova, A.N., Filimonova, D.A. 2018. Sukcessiya na molodyh i srednevozrastnyh zalezhah lesostepnoj zony Zapadnoj Sibiri v predelah Novosibirskoj oblasti [Succession on young and medium age fallows of the forest-steppe zone of Western Siberia in the Novosibirsk region]. Mezhdunarodnyj zhurnal prikladnyh i fundamental'nyh issledovanij, 10:116120. [In Russian]. DOI:10.17513/mjpfi.12427.
• Song, Y., Pan, Q.K., Gao, L., Zhang, B. 2019. Improved non-maximum suppression for object detection using harmony search algorithm. Applied Soft Computing, 81:105478. DOI:10.1016/j.asoc.2019.05.005.
• Sparks, A.M., Corrao, M.V., Smith, A.M.S. 2022. Cross-Comparison of Individual Tree Detection Methods Using Low and High Pulse Density Airborne Laser Scanning Data. Remote Sensing, 14(14):3480. DOI:10.3390/rs14143480.
• Sun, C., Huang, C., Zhang, H., Chen, B., An, F., Wang, L., Yun, T. 2022. Individual tree crown segmentation and crown width extraction from a heightmap derived from aerial laser scanning data using a deep learning framework. Frontiers in Plant Science, 13:914974. DOI:10.3389/fpls.2022.914974.
• Suslova, E.G. 2019. Lesa Moskovskoj oblasti [Forests of the Moscow region]. Ekosistemy: ekologiya i dinamika 3(1):119-190. [In Russian] https://ecosystemsdynamic.ru/lesa-moskovskoj-obla sti/ (Accessed 26 March 2024). Tanase, M.A., Villard, L., Pitar, D., Apostol, B., Petrila, M., Chivulescu, S., Leca, S., Borlaf-Mena, I., Pascu, I.-S., Dobre, A.-C., Pitar, D., Guiman, G., Lorent, A., Anghelus, C., Ciceu, A., Nedea, G., Stanculeanu, R., Popescu, F., Aponte, C., Badea, O. 2019. Synthetic aperture radar sensitivity to forest changes: A simulations-based study for the Romanian forests. Science of the Total Environment, 689:1104–1114. DOI:10.1016/j.scitotenv.2019.06.494.
• United Nations. 1992. UN Framework Convention on Climate Change. https://unfccc.int/resource/docs/ convkp/conveng.pdf (Accessed: 26 March 2024).
• United Nations. 1998. Kyoto Protocol to the United Nations Framework Convention on Climate Change. https://unfccc.int/resource/docs/convkp/kpeng.pdf (Accessed: 26 March 2024).
• Vastaranta, M., Wulder, M.A., White, J.C., Pekkarinen, A., Tuominen, S., Ginzler, C., Kankare, V., Holopainen, M., Hyyppä, J., Hyyppä, H. 2013. Airborne laser scanning and digital stereo imagery measures of forest structure: Comparative results and implications for forest mapping and inventory update. Canadian Journal of Remote Sensing, 39(5):382–395. DOI:10.5589/m13-046.
• Wallace, L., Lucieer, A., Malenovský, Z., Turner, D., Vopěnka, P. 2016. Assessment of forest structure using two UAV techniques: A comparison of airborne laser scanning and structure from motion (SfM) point clouds. Forests, 7(3):62. DOI:10.3390/f7030062.
• Wang, T., Skidmore, A.K., Toxopeus, A.G., Liu, X. 2009. Understory bamboo discrimination using a winter image. Photogrammetric Engineering & Remote Sensing, 75(1):37–47. DOI: 10.14358/PERS.75.1.37.
• Wu, B., Yu, B., Wu, Q., Huang, Y., Chen, Z., Wu, J. 2016. Individual tree crown delineation using localized contour tree method and airborne LiDAR data in coniferous forests. International Journal of Applied Earth Observation and Geoinformation, 52:82–94. DOI:10.1016/j.jag.2016.06.003.
• Zamolodchikov, D. 2011. Sistemy ocenki i prognoza zapasov ugleroda v lesnyh ekosistemah [Systems of assessment and forecasting of carbon stocks in forest ecosystems]. Ustojchivoe lesopolzovanie, 29:15–22. [In Russian]. https://www.elibrary.ru/download/ elibrary_ 22517667_72914254.pdf (Accessed: 26 March 2024).
• Zhang, X., Tan, X., Chen, G., Zhu, K., Liao, P., Wang, T. 2021. Object-based classification framework of remote sensing images with graph convolutional networks. IEEE Geoscience and Remote Sensing Letters 19:1–5. DOI:10.1109/LGRS.2021.3072627.
• Zhang, Y., Dian, Y., Zhou, J., Peng, S., Hu, Y., Hu, L., Han, Z., Fang, X., Cui, H. 2021. Characterizing spatial patterns of pine wood nematode outbreaks in subtropical zone in China. Remote Sensing, 13(22):4682. DOI:10.3390/rs13224682.
• Zoph, B., Ghiasi, G., Lin, T. Y., Cui, Y., Liu, H., Cubuk, E. D., Le, Q. 2020. Rethinking pre-training and self-training. Advances in Neural Information Processing Systems, 33:3833–3845. https://proceedings.neurips. cc/paper/2020/hash/27e9661e033a73a6ad8cefcde965c54dAbstract. html (Accessed: 25 June 2024).