ارزیابی دقت تصاویر پهپاد در آشکارسازی تاج درختان در ساختارهای متفاوت یک جنگل شهری

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار گروه سنجش ازدور و GIS ، دانشکده منابع طبیعی و محیط زیست، داﻧﺸﮕﺎه آزاد اسلامی، واحد علوم و تحقیقات

2 عضو باشگاه پژوهشگران جوان، دانشگاه آزاد اسلامی،واحد سنندج، سنندج، اﯾﺮان

10.22131/sepehr.2021.246146

چکیده

آماربرداری و نقشهبرداری از درختان شهری بهمنظور برنامهریزی و کمک به طراحی استراتژیهای بهینهسازی خدمات اکوسیستم شهری و سازگاری با تغییرات اقلیمی بسیار ضروری است. پیشرفتهای اخیر در فناوری سیستمهای هوایی بدون سرنشین، فناوری انعطافپذیر مکانی و زمانی دادههای سهبعدی با وضوح بالا را تسهیل کرده است. روشهای رایج آشکارسازی پایههای درختی براساس دادههای ماهوارهای با وضوح بسیار بالا یا دادههای اسکن لیزر هوایی است. با این حال، دادههای ماهوارهای اغلب با مشکل مناسب نبودن در مقیاس تکدرخت و محدودیت ابرها مواجه است و دادههای لیزر اسکن هوایی نیز از هزینههای نسبتاً بالایی برخوردار هستند. بنابراین در مطالعه حاضر با هدف آشکارسازی تاج درختان، از دو الگوریتم رشد ناحیهای و حوضه آبخیز معکوس در یک جنگل شهری با ساختارهای متفاوت از مدل ارتفاع تاج بهدست آمده از ساختار حرکت مبنا استفاده شد. به همین منظور تصویربرداری و آماربرداری زمینی درختان درتابستان 1398 در جنگل شهری باغ فاتح واقع در شهرستان کرج انجام شد. پس از پردازش تصاویر و تولید مدل ارتفاع تاج، آشکارسازی درختان در 5 اندازه پیکسل 25، 50، 75، 100 و 125 سانتیمتر و در سه ساختار ناهمگن متراکم، ناهمگن پراکنده و همگن متراکم انجام شد. نتایج نشان داد که دو الگوریتم رشد ناحیهای و حوضه آبخیز معکوس در ساختار همگن متراکم بیشترین عملکرد را دارد. همچنین الگوریتم رشد ناحیهای با میزان صحت کلی 88 درصد در سایت3 (ساختار همگن متراکم) با اندازه پیکسل 75 سانتیمتر بهترین نتیجه را در آشکارسازی درختان ارائه داد. در کل نتایج این تحقیق نشان داد که آشکارسازی پایههای درختی با استفاده از مدل ارتفاع تاج بهدست آمده از تصاویر پهپاد در سایتهای همگن دارای دقت بالایی است، در حالیکه در سایتهای ناهمگن و متراکم از کارایی بالایی برخوردار نبود. 

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Assessing the accuracy of UAV-captured images used for individual trree crowns delineation in different structures of an urban forest

نویسندگان [English]

  • Zahra Azizi 1
  • Mojdeh Miraki 2
1 Asistant professor of Remote sensing and GIS , Science and Research Branch,Islamic Azad University, Tehran, Iran
2 Young researchers and elites club, Sanandaj Branch Islamic Azad University, Sanandaj, Iran
چکیده [English]

Extended Abstract
Introduction
Advances in computer vision and the development of remote sensing instruments have made indirect measurement of tree features possible. Individual tree crown delineation is an important step towards information collection and mapping trees in an urban area. This information is then used to help planners design strategies for optimization of urban ecosystem services and adapt to climate changes. Common methods of Individual tree crown delineation (ITCD) were based on very high-resolution satellite or Light Detection and Ranging (LiDAR) data. However, satellite data are usually covered by clouds and thus, cannot be appropriate for the measurement of individual trees. Aerial Laser scanning is also relatively expensive. Remote sensing with unmanned aerial vehicle (UAV) captures low altitude imagery and thus, is potentially capable of mapping complex urban vegetation. Automatic delineation of trees with UAV data makes collection of detailed information from trees in large geographic and urban regions possible. Therefore, a multirotor UAV equipped with a high-resolution RGB camera was used in the present study to obtain aerial images and delineate individual trees.
 
Materials & Methods
The present study has compared the performance of Inverse watershed segmentation (IWS) and region growing (RG) algorithms using point clouds derived from Structure from Motion (SfM) algorithm and UAV imagery captured with the aim of tree delineation in Fateh urban forest located in Karaj. Region growing (RG) is used to separate regions and distinguish objects in an image. It starts at the initial seed points and determines whether the neighboring pixels should be added to the growing region. If the neighboring pixels are sufficiently similar to the seed pixel, they are labeled as belonging to the seed pixel. To implement the algorithm, the window size and the growing threshold were set for all resolutions. In order to obtain the most appropriate size for the search window, we examined different window sizes with a growing threshold of 0.5 for each resolution. Individual trees delineation was performed for each CHM resolution in the three different sites using "itcSegment" package of R software. Watershed segmentation algorithm is also similar to RG algorithm. The only difference is that it sets the growing seeds at the local minima. In other words, the local maxima in this algorithm change into local minima and vice versa. Inverse Watershed Segmentation (IWS) method was implemented in ArcGIS 10.3 because of its capability in delineation of distinct tree entities. In the summer of 2018, three sites with different structures including a mixed uneven-aged dense stand (site 1), a mixed uneven-aged sparse stand (site 2), and a homogeneous even-aged dense stand (site 3) were surveyed and photographed, and a 3D point cloud was extracted from the images. Then, the performance of algorithms was tested using a series of different canopy height models (CHM) with spatial resolutions of 25, 50, 75, 100, and 120 cm. To generate these models, digital surface model (DSM) was subtracted from digital terrain model (DTM). Results of individual tree delineation were validated using data collected in field observation of the aforementioned sites.
 
Results & Discussion
Results indicated that both RG and IWS algorithms yielded their best performance in the dense homogeneous structure. Moreover, the number of segments resulting from CHMs with low resolution was often much more than the actual number of trees. This was due to the occurrence of several peaks within an individual tree crown especially in low resolution images. With an F-score of 0.88, homogeneous even-aged dense stand (site 3) showed the highest overall accuracy in RG algorithm with a pixel size of 75 cm. Generally, results indicated that RG is an appropriate approach for individual tree delineation due to its flexibility in delineation of varying crown sizes. Furthermore, this method does not assume a circular shape for tree crowns and thus, is capable of detecting and segmenting irregular crowns. Generally, delineation of trees in urban forests using CHMs obtained from UAV-captured aerial imagery was highly accurate in homogeneous sites, while such models lacked efficiency in heterogeneous sites.

کلیدواژه‌ها [English]

  • Urban forest
  • UAV
  • Inverse watershed segmentation algorithm
  • Region-growing algorithm
  • Individual Tree Crown Delineation (ITCD)
1- Asner, Gregory., Roberta Martin., Lisa Keith., Wade Heller., Marc Hughes., Nicholas Vaughn., et al.2018. “A Spectral Mapping Signature for the Rapid Ohia Death (ROD) Pathogen in Hawaiian Forests.” Remote Sensing 10 (3): 404. https://doi.org/10.3390/rs10030404.
2- Brovkina, Olga., Emil Cienciala., Peter Surový., and Přemysl Janata. 2018. “Unmanned Aerial Vehicles (UAV) for Assessment of Qualitative Classification of Norway Spruce in Temperate Forest Stands.” Geo-Spatial Information Science 21 (1): 12–20. https://doi.org/10.1080/10095020.2017.1416994.
3- Bunting, Peter., Richard Lucas. 2006. “The Delineation of Tree Crowns in Australian Mixed Species Forests Using Hyperspectral Compact Airborne Spectrographic Imager (CASI) Data.” Remote Sensing of Environment 101 (2): 230–48. https://doi.org/10.1016/j.rse.2005.12.015.
4- Cochrane, Mark. 2000. “Using Vegetation Reflectance Variability for Species Level Classification of Hyperspectral Data.” International Journal of Remote Sensing 21 (10): 2075–87. https://doi.org/10.1080/01431160050021303.
5- Dalponte, Michele. 2018. “Individual Tree Crowns Segmentation R Package Version 0.8.”
6- Dalponte, Michele., Lorenzo Frizzera., and Damiano Gianelle. 2019. “Individual Tree Crown Delineation and Tree Species Classification with Hyperspectral and LiDAR Data.” PeerJ 6 (January): e6227. https://doi.org/10.7717/peerj.6227.
7- Dalponte, Michele., Francesco Reyes., Kaja Kandare., and Damiano Gianelle. 2015. “Delineation of Individual Tree Crowns from ALS and Hyperspectral Data: A Comparison among Four Methods.” European Journal of Remote Sensing 48 (August): 365–82. https://doi.org/10.5721/EuJRS20154821.
8- Dong, Tianyang, Xinpeng Zhang, Zhanfeng Ding, and Jing Fan. 2020. “Multi-Layered Tree Crown Extraction from LiDAR Data Using Graph-Based Segmentation.” Computers and Electronics in Agriculture 170 (March): 105213. https://doi.org/10.1016/j.compag.2020.105213.
9- Duncanson, L.I.,Cook, B.D., Hurtt, G.C., andDubayah. R.O. 2014. “An Efficient, Multi-Layered Crown Delineation Algorithm for Mapping Individual Tree Structure across Multiple Ecosystems.” Remote Sensing of Environment 154 (November): 378–86. https://doi.org/10.1016/J.RSE.2013.07.044.
10- Feng, Quanlong., Jiantao Liu., Jianhua Gong., Quanlong Feng., Jiantao Liu., and Jianhua Gong. 2015. “UAV Remote Sensing for Urban Vegetation Mapping Using Random Forest and Texture Analysis.” Remote Sensing 7 (1): 1074–94. https://doi.org/10.3390/rs70101074.
11- Frey, Julian., Kyle Kovach., Simon Stemmler., and Barbara Koch. 2018. “UAV Photogrammetry of Forests as a Vulnerable Process. A Sensitivity Analysis for a Structure from Motion RGB-Image Pipeline.” Remote Sensing 10 (6). https://doi.org/10.3390/rs10060912.
12- Goldbergs, Grigorijs., Stefan Maier., Shaun Levick., Andrew Edwards., Grigorijs Goldbergs., Stefan W. Maier., Shaun R. Levick., and Andrew Edwards. 2018. “Efficiency of Individual Tree Detection Approaches Based on Light-Weight and Low-Cost UAS Imagery in Australian Savannas.” Remote Sensing 10 (2): 161. https://doi.org/10.3390/rs10020161.
13- Guerra-Hernández, Juan., Diogo N. Cosenza., Luiz Carlos Estraviz Rodriguez., Margarida Silva., Margarida Tomé., Ramón A. Díaz-Varela., and Eduardo González-Ferreiro. 2018. “Comparison of ALS- and UAV(SfM)-Derived High-Density Point Clouds for Individual Tree Detection in Eucalyptus Plantations.” International Journal of Remote Sensing 39 (15–16): 5211–35. https://doi.org/10.1080/01431161.2018.1486519.
14- Harikumar, Aravind., Francesca Bovolo., and Lorenzo Bruzzone. 2019. “A Local Projection-Based Approach to Individual Tree Detection and 3-D Crown Delineation in Multistoried Coniferous Forests Using High-Density Airborne LiDAR Data.” IEEE Transactions on Geoscience and Remote Sensing 57 (2): 1168–82. https://doi.org/10.1109/TGRS.2018.2865014.
15- Heenkenda, Muditha K., Karen E. Joyce., and Stefan W. Maier. 2015. “Mangrove Tree Crown Delineation from High-Resolution Imagery.” Photogrammetric Engineering and Remote Sensing 81 (6): 471–79. https://doi.org/10.14358/PERS.81.6.471.
16- Huang, Gang., Chen-Hua Li., and Yan Li. 2018. “Phenological Responses to Nitrogen and Water Addition Are Linked to Plant Growth Patterns in a Desert Herbaceous Community.” Ecology and Evolution 8 (10): 5139–52. https://doi.org/10.1002/ece3.4001.
17- Huang, Hongyu., Xu Li., and Chongcheng Chen. 2018. “Individual Tree Crown Detection and Delineation from Very-High-Resolution UAV Images Based on Bias Field and Marker-Controlled Watershed Segmentation Algorithms.” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 11 (7): 2253–62. https://doi.org/10.1109/JSTARS.2018.2830410.
18- Ke, Yinghai., Quackenbush, Lindi. 2011. “A Review of Methods for Automatic Individual Tree-Crown Detection and Delineation from Passive Remote Sensing.” International Journal of Remote Sensing 32 (17): 4725–47. https://doi.org/10.1080/01431161.2010.494184.
19- Klein Hentz, Ângela Maria., Michael P. Strager. 2018. “Cicada Tree Damage Detection Based on UAV Spectral and 3D Data.” Natural Science 10 (01): 31–44. https://doi.org/10.4236/ns.2018.101003.
20- Larsen, Morten., Mats Eriksson., Xavier Descombes., Guillaume Perrin., Tomas Brandtberg., and François A. Gougeon. 2011. “Comparison of Six Individual Tree Crown Detection Algorithms Evaluated under Varying Forest Conditions.” International Journal of Remote Sensing 32 (20): 5827–52. https://doi.org/10.1080/01431161.2010.507790.
21- Lisein, Jonathan., Adrien Michez., Hugues Claessens., and Philippe Lejeune. 2015. “Discrimination of Deciduous Tree Species from Time Series of Unmanned Aerial System Imagery.” Edited by Marco Cristani. PLoS ONE 10 (11): 1–20. https://doi.org/10.1371/journal.pone.0141006.
22- Mohan, Midhun., Carlos Alberto Silva., Carine Klauberg., Prahlad Jat., Glenn Catts., Adrián Cardil., Andrew Thomas Hudak., and Mahendra Dia. 2017. “Individual Tree Detection from Unmanned Aerial Vehicle ( UAV ) Derived Canopy Height Model in an Open Canopy Mixed Conifer Forest.” Forests 8 (9): 1–17. https://doi.org/10.3390/f8090340.
23- Miraki, Mojdeh, Hormoz Sohrabi, Parviz Fatehi, and Mathias Kneubuehler. 2021. “Individual Tree Crown Delineation from High-Resolution UAV Images in Broadleaf Forest.” Ecological Informatics 61 (March): 101207. https://doi.org/10.1016/j.ecoinf.2020.101207.
24- Nevalainen, A., Nilton, N., and Antonio, M G. 2017. “Individual Tree Detection and Classification with UAV-Based Photogrammetric Point Clouds and Hyperspectral Imaging.” Remote Sensing 9 (3): 185. https://doi.org/10.3390/rs9030185.
25- Nordin, Sitinor Atikah., Zulkiflee Abd Latif., and Hamdan Omar. 2019. “Individual Tree Crown Segmentation in Tropical Peat Swamp Forest Using Airborne Hyperspectral Data.” Geocarto International 34 (11): 1218–36. https://doi.org/10.1080/10106049.2018.1475511.
26- Panagiotidis, Dimitrios., Azadeh Abdollahnejad., Peter Surový., and Vasco Chiteculo. 2016. “Determining Tree Height and Crown Diameter from High-Resolution UAV Imagery.” International Journal of Remote Sensing 38 (8–10): 2392–2410. https://doi.org/10.1080/01431161.2016.1264028.
27- Salehi, A., Gomroki, M., Azizi, A., and Sadeghian, H. 2016. “Automated Tree Crown Delineation and Detection in UltraCam-D Digital Image.” Forest Research and Development, 2 (3): 241–56.
28- Surovy, Peter., Nuno Almeida Ribeiro., and Dimitrios Panagiotidis. 2018. “Estimation of Positions and Heights from UAV-Sensed Imagery in Tree Plantations in Agrosilvopastoral Systems.” International Journal of Remote Sensing 39 (14): 4786–4800. https://doi.org/10.1080/01431161.2018.1434329.
29- Tanhuanpaa, Topi., Ninni Saarinen., Ville Kankare, Kimmo Nurminen., Mikko Vastaranta., Eija Honkavaara., Mika Karjalainen., et al. 2016. “Evaluating the Performance of High-Altitude Aerial Image-Based Digital Surface Models in Detecting Individual Tree Crowns in Mature Boreal Forests.” Forests 7 (12): 143. https://doi.org/10.3390/f7070143.
30- Thiel, Christian., Christiane Schmullius. 2017. “Comparison of UAV Photograph-Based and Airborne Lidar-Based Point Clouds over Forest from a Forestry Application Perspective.” International Journal of Remote Sensing 38 (8–10): 2411–26. https://doi.org/10.1080/01431161.2016.1225181.
31- Vauhkonen, J.,Ene, L., Gupta, S., Heinzel, J., Holmgren, J., Pitkanen, J., Solberg, S et al. 2012. “Comparative Testing of Single-Tree Detection Algorithms under Different Types of Forest.” Forestry 85 (1): 27–40. https://doi.org/10.1093/forestry/cpr051.
32- Vauhkonen, Jari., Anne Seppänen., Petteri Packalén., and Timo Tokola. 2012. “Remote Sensing of Environment Improving Species-Speci Fi c Plot Volume Estimates Based on Airborne Laser Scanning and Image Data Using Alpha Shape Metrics and Balanced Fi Eld Data.” Remote Sensing of Environment 124: 534–41. https://doi.org/10.1016/j.rse.2012.06.002.
33- Yilmaz, Volkan., Oguz Gungor. 2019. “Estimating Crown Diameters in Urban Forests with Unmanned Aerial System-Based Photogrammetric Point Clouds.” International Journal of Remote Sensing 40 (2): 468–505. https://doi.org/10.1080/01431161.2018.1562255.
34- Yin, Dameng., Le Wang. 2016. “How to Assess the Accuracy of the Individual Tree-Based Forest Inventory Derived from Remotely Sensed Data: A Review.” International Journal of Remote Sensing 37 (19): 4521–53. https://doi.org/10.1080/01431161.2016.1214302.
35- Yin, Dameng., Le Wang. 2019. “Individual Mangrove Tree Measurement Using UAV-Based LiDAR Data: Possibilities and Challenges.” Remote Sensing of Environment 223 (December 2018): 34–49. https://doi.org/10.1016/j.rse.2018.12.034.
36- Zhang, Caiyun., Yuhong Zhou., Fang Qiu., Caiyun Zhang., Yuhong Zhou., and Fang Qiu. 2015. “Individual Tree Segmentation from LiDAR Point Clouds for Urban Forest Inventory.” Remote Sensing 7 (6): 7892–7913. https://doi.org/10.3390/rs70607892.
37- Zhen, Zhen., Lindi J. Quackenbush., and Lianjun Zhang. 2016. “Trends in Automatic Individual Tree Crown Detection and Delineation-Evolution of LiDAR Data.” Remote Sensing. 8(4), 333. https://doi.org/10.3390/rs8040333.