Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.6.2.5

Detection of Urban Trees Using YOLOv5 from Aerial Images  

Park, Che-Won (Department of Geoinformatics, University of Seoul)
Jung, Hyung-Sup (Department of Geoinformatics, University of Seoul)
Publication Information
Korean Journal of Remote Sensing / v.38, no.6_2, 2022 , pp. 1633-1641 More about this Journal
Abstract
Urban population concentration and indiscriminate development are causing various environmental problems such as air pollution and heat island phenomena, and causing human resources to deteriorate the damage caused by natural disasters. Urban trees have been proposed as a solution to these urban problems, and actually play an important role, such as providing environmental improvement functions. Accordingly, quantitative measurement and analysis of individual trees in urban trees are required to understand the effect of trees on the urban environment. However, the complexity and diversity of urban trees have a problem of lowering the accuracy of single tree detection. Therefore, we conducted a study to effectively detect trees in Dongjak-gu using high-resolution aerial images that enable effective detection of tree objects and You Only Look Once Version 5 (YOLOv5), which showed excellent performance in object detection. Labeling guidelines for the construction of tree AI learning datasets were generated, and box annotation was performed on Dongjak-gu trees based on this. We tested various scale YOLOv5 models from the constructed dataset and adopted the optimal model to perform more efficient urban tree detection, resulting in significant results of mean Average Precision (mAP) 0.663.
Keywords
Tree detection; Object detection; YOLOv5; Aerial images;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Kim, H.M., D.G. Lee, and S. Sung, 2016. Effect of urban green spaces and flooded area type on flooding probability, Sustainability, 8(2): 134. https://doi.org/10.3390/su8020134   DOI
2 Choi, J.W., 2018. A Study on Model Development for the Density Management of Overcrowded Planting Sites and the Planting Design of New Planting Sites-A Case Study of Buffer Green Spaces in the Dongtan New Town, Hwaseong, Journal of the Korean Institute of Landscape Architecture, 46(5): 82-92 (in Korean with English abstract). https://doi.org/10.9715/KILA.2018.46.5.082   DOI
3 Kang, J.E. and M.J. Lee, 2012. Assessment of flood vulnerability to climate change using fuzzy model and GIS in Seoul, Journal of the Korean Association of Geographic Information Studies, 15(3): 119-136 (in Korean with English abstract). https://doi.org/10.11108/kagis.2012.15.3.119   DOI
4 Kaur, P., B.S. Khehra, and E.B.S. Mavi, 2021. Data augmentation for object detection: A review, Proc. of 2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), East Lansing, MI, USA, Aug. 9-11, pp. 537-543. https://doi.org/10.1109/MWSCAS47672.2021.9531849   DOI
5 Hwang, S.R., M.J. Lee, and I.P. Lee, 2012. Detection of Individual Trees and Estimation of Mean Tree Height using Airborne LIDAR Data, Spatial Information Research, 20(3): 27-38 (in Korean with English abstract). https://doi.org/10.12672/ksis.2012.20.3.027   DOI
6 Park, M., 2021. Comparison of Accuracy between Analysis Tree Detection in UAV Aerial Image Analysis and Quadrat Method for Estimating the Number of Treesto be Removed in the Environmental Impact Assessment, Journal of Environmental Impact Assessment, 30(3): 155-163 (in Korean with English abstract). https://doi.org/10.14249/eia.2021.30.3.155   DOI
7 Puliti, S. and R. Astrup, 2022. Automatic detection of snow breakage at single tree level using YOLOv5 applied to UAV imagery, International Journal of Applied Earth Observation and Geoinformation, 112: 102946. https://doi.org/10.1016/j.jag.2022.102946   DOI
8 Wang, J. and L. Perez, 2017. The effectiveness of data augmentation in image classification using deep learning, arXiv preprint arXiv:1712.04621. https://doi.org/10.48550/arXiv.1712.04621   DOI
9 Wang, T.S., S. Oh, H.S. Lee, J. Jang, and M. Kim, 2021. A Study on the AI Detection Model of Marine Deposition Waste Using YOLOv5, Proc. of Korean Institute of Information and Communication Sciences Conference, Gunsan, Korea, Oct. 28-30, vol. 25, pp. 385-387.
10 Weinstein, B.G., S. Marconi, S. Bohlman, A. Zare, and E. White, 2019. Individual tree-crown detection in RGB imagery using semi-supervised deep learning neural networks, Remote Sensing, 11(11): 1309. https://doi.org/10.3390/rs11111309   DOI
11 Xu, R., H. Lin, K. Lu, L. Cao, and Y. Liu, 2021. A forest fire detection system based on ensemble learning, Forests, 12(2): 217. https://doi.org/10.3390/f12020217   DOI
12 Zamboni, P., J.M. Junior, J.D.A. Silva, G.T. Miyoshi, E.T. Matsubara, K. Nogueira, and W.N. Goncalves, 2021. Benchmarking anchor-based and anchor-free state-of-the-art deep learning methods for individual tree detection in RGB high-resolution images, Remote Sensing, 13(13): 2482. https://doi.org/10.3390/rs13132482   DOI
13 Sim, W. K. and D. I. Lee, 2001. An analysis of Status quo on the multi-layer planting at the landscape planting area in apartments and neighborhood parks in Seoul metropolitan area, Journal of the Korean Institute of Landscape Architecture, 29(1): 140-151.