Determination of Olive Tree (Olea europaea L.) Some Dendrometric Components from Unmanned Aerial Vehicle (UAV) Data with Local Extrema and Multiresolution Segmentation Algorithms

Abstract

In this study, it was aimed to determine the dendrometric components of olive trees by using an unmanned aerial vehicle (UAV). The research was carried out in the olive groves of Akdeniz University Faculty of Agriculture. The study consists of the basic stages of acquisition, processing and analysis of UAV images. In the first stage, autonomous flight was performed with the UAV and digital images of the area were collected. In addition, at this stage, the number and height of olive trees in the area were determined by making local measurements. In the second stage, orthomosaic image, digital surface model (DSM) and digital terrain model (DTM) were produced by processing UAV images. At this stage, tree crown boundaries were determined by manual digitization over the orthomosaic image. Then, a canopy height model (CHM) was created to semi-automatically calculate the crown borders, number of trees and tree height values of olive trees. As a result of the evaluation of semi-automatic findings and ground measurements, the general accuracy in the determination of trees in the olive grove was 96.15%, the accuracy of the producer was 85.14% and the user accuracy was 81.82% in the determination of the tree crown boundaries. In addition, high correlations were obtained in the determination of tree crown area (r = 0.980) and tree height (r = 0.918). According to these results, it has been revealed that some dendrometric components of the olive tree can be determined quite successfully with the semi-automatically calculated data from the UAVs.

Keywords

• Canopy height model
• olive tree
• precision farming
• UAV

İnsansız Hava Aracı (İHA) Verilerinden Zeytin Ağacının (Olea europaea L.) Bazı Dendrometrik Bileşenlerinin Yerel Ekstrema ve Çoklu Çözünürlüklü Bölütleme Algoritmaları ile Belirlenmesi

Öz

Bu çalışmada, insansız hava aracı (İHA) kullanılarak zeytin ağaçlarının dendrometrik bileşenlerin belirlenmesi amaçlanmıştır. Araştırma Akdeniz Üniversitesi Ziraat Fakültesi zeytinliklerinde gerçekleştirilmiştir. Çalışma, İHA görüntülerinin elde edilmesi, işlenmesi ve analizi temel aşamalarından oluşmaktadır. İlk aşamada İHA ile otonom uçuş gerçekleştirilerek alanın dijital görüntüleri toplanmıştır. Ayrıca bu aşamada yersel ölçümler yapılarak alandaki zeytin ağaçlarının sayısı ve yükseklikleri belirlenmiştir. İkinci aşamada, İHA görüntüleri işlenerek ortomozaik görüntü, sayısal yüzey modeli (DSM) ve sayısal arazi modeli (DTM) üretilmiştir. Bu aşamada ortomozaik görüntü üzerinden manuel sayısallaştırma ile ağaç taç sınırları belirlenmiştir. Daha sonra zeytin ağaçlarının taç sınırlarını, ağaç sayısını ve ağaç yükseklik değerlerini yarı otomatik olarak hesaplamak için bir kanopi yükseklik modeli (KYM) oluşturulmuştur. Yarı otomatik bulgular ile yersel ölçümlerin değerlendirilmesi sonucunda zeytinlikteki ağaçların tespitinde genel doğruluk %96,15, ağaç taç sınırlarının belirlenmesinde ise üretici doğruluğu %85.14 ve kullanıcı doğruluğu %81.82 olarak bulunmuştur. Ayrıca ağaç taç alanı (r = 0.980) ve ağaç yüksekliğinin (r = 0.918) belirlenmesinde de yüksek korelasyonlar elde edilmiştir. Bu sonuçlara göre, İHA’lardan yarı otomatik olarak hesaplanan veriler ile zeytin ağacının bazı dendrometric bileşenlerinin oldukça başarılı bir şekilde belirlenebildiği ortaya konmuştur.

Anahtar Kelimeler

• Kanopi yükseklik modeli
• zeytin ağacı
• hassas tarım
• İHA
• Canopy height model
• olive tree
• precision farming
• UAV

Kaynakça

1. Carolan, M. (2017). Publicising food: big data, precision agriculture, and co-experimental techniques of addition: publicising food. Sociollogia Ruralis, 57, 135-154. https://doi.org/10.1111/soru.12120
2. Castro, A. I., Rallo, P., Suárez, M. P., Torres-Sánchez, J., Casanova, L., Jiménez-Brenes, F. M., Morales-Sillero, A., Jiménez, M. R., & López-Granados, F. (2019). High-throughput system for the early quantification of major architectural traits in olive breeding trials using UAV images and OBIA techniques. Frontiers in Plant Science, 10, 1472. https://doi.org/10.3389/fpls.2019.01472 Çubukçu, K. M. (2015). Planlamada ve coğrafyada temel istatistik ve mekânsal istatistik kitabı. Nobel Akademik Yayıncılık, Yayın No:1097, Ankara.
3. Das, U. (2018). Precision farming a promising technology in horticulture: a review. International Journal of Pure Applied Bioscience, 6, 1596-1606. https://doi.org/10.18782/2320-7051.3088
4. Demir, N., Sönmez, N. K., Akar, T., & Ünal, S. (2018). Automated measurement of plant height of wheat genotypes using a DSM derived from UAV imagery. MDPI Proceedings, 2, 350-350. https://doi.org/10.3390/ecrs-2-05163
5. Díaz-Varela, R. A., de la Rosa, R., León, L., & Zarco-Tejada, P. J. (2015). High-resolution airborne UAV imagery to assess olive tree crown parameters using 3D photo reconstruction: Application in breeding trials. Remote Sensing, 7, 4213-4232. https://doi.org/10.3390/rs70404213
6. DJI (2021). Phantom 3 advanced specs. Access address https://www.dji.com/phantom-3-adv/info
7. Dong, X., Zhang, Z., Yu, R., Tian, Q., & Zhu, X. (2020). Extraction of information about individual trees from high-spatial-resolution UAV-acquired images of an orchard. Remote Sensing, 12, 133. https://doi.org/10.3390/rs12010133
8. Drăguţ, L., Csillik, O., Eisank, C., & Tiede, D. (2014). Automated parameterisation for multi-scale image segmentation on multiple layers. ISPRS Journal of Photogrammetry and Remote Sensing, 88, 119-127. https://doi.org/10.1016/j.isprsjprs.2013.11.018

9. Fang, F., Im, J., Lee, J., & Kim, K. (2016). An improved tree crown delineation method based on live crown ratios from airborne LIDAR data, GIScience & Remote Sensing, 53, 402-419. https://doi.org/10.1080/15481603.2016.1158 774
10. Jing, L., Hu, B., Li, J., & Noland, T. (2012). Automated delineation of individual tree crowns from LIDAR data by multi-scale analysis and segmentation. Photogrammetric Engineering and Remote Sensing, 78(12), 1275-1284. https://doi.org/10.14358/PERS.78.11.1275
11. Marques, P., Pádua, L., Adão, T., Hruška, J., Peres, E., Sousa, A., & Sousa, J. J. (2019). UAV-based automatic detection and monitoring of chestnut trees. Remote Sensing, 11, 855. https://doi.org/10.3390/rs11070855
12. Matese, A., Capraro, F., Primicerio, J., Gualato, G., Di Gennaro, S. F., & Agati, G. (2013). Mapping of vine vigor by UAV and anthocyanin content by a non-destructive fluorescence technique. In Proceedings of the 9th European Conference on Precision Agriculture (ECPA), Lleida, Spain, 7–11 July.
13. Mu, Y., Fujii, Y., Takata, D., Zheng, B., Noshita, K., Honda, K., Ninomiya, S., & Guo, W. (2018). Characterization of peach tree crown by using high-resolution images from an unmanned aerial vehicle. Horticulture Research, 5, 74. https://doi.org/10.1038/s41438-018-0097-z
14. Mohan, M., Silva, C. A., Klauberg, C., Jat, P., Catts, G., Cardil, A., Hudak, A. T., & Dia, M. (2017). Individual tree detection from unmanned aerial vehicle (UAV) derived canopy height model in an open canopy mixed conifer forest. Forests, 8, 340. https://doi.org/10.3390/f8090340
15. Ozdarici-Ok A. (2015). Automatic detection and delineation of citrus trees from VHR satellite imagery. International Journal of Remote Sensing, 36, 4275–4296. https://doi.org/10.1080/01431161.2015.1079663
16. Ok, A. O. & Ozdarici-Ok, A. (2017). Detection of citrus trees from UAV DSMs. In Proceedings of the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Hannover, Germany, 4, 27-34. https://doi.org/10.5194/isprs-annals-IV-1-W1-27-2017
17. Ok, A. O. & Ozdarici-Ok, A. (2018). 2-D delineation of individual citrus trees from UAV-based dense photogrammetric surface models. International Journal of Digital Earth, 11, 583-608. https://doi.org/10.1080/17538947.2017.1337 820
18. Ok, A. O., & Ozdarici-Ok, A. (2018). Dijital yüzey modelinden turunçgil meyve ağaçlarinin tespiti, çıkarımı ve kümelenmesi: bütünleşik bir sistem, VII. UZAL-CBS Sempozyumu (Birinci En İyi Sözlü Sunum Ödülü). VII. UZAL-CBS Sempozyumu, Eskişehir, Türkiye.
19. Ramli, M. F., & Tahar, K. N. (2020). Homogeneous tree height derivation from tree crown delineation using seeded region growing (SRG) segmentation. Geo-Spatial Information Science, 23(3), 195-208. https://doi.org/10.1080/10095020.2020.1805366
20. Sönmez, N. K., Çoşlu, M., & Demir, N. (2021). Farklı insansız hava araçlarından (İHA) elde edilen veriler ile buğday bitkisinin boyunun belirlenmesi. Mediterranean Agricultural Sciences, 34(2), 195-203. https://doi.org/10.29136/ mediterranean.823440
21. Sunar, F., Özkan, C., & Osmanoğlu, B. (2013). Uzaktan algılama (2. Baskı). T.C. Anadolu Üniversitesi, Yayın No: 2320, Açıköğretim Fakültesi Yayın No:1317, Eskişehir.
22. Trimble, (2014). eCognition developer 9.0 reference book. Trimble Germany GmbH, Arnulfstrasse 126, D-80636 Munich, Germany.
23. TÜİK (2021). Zeytin üretimi, 1988-2020. Access address https://data.tuik.gov.tr/Search/Search?text=zeytin
24. Yin, D., & Wang, L. (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, 4521-4553. https://doi.org/10.1080/01431161.2016.1214302
25. Zohary, D., & Spiegel-Roy, P. (1975). Beginnings of fruit growing in the old world. Science, 187, 319-327. https://doi.org/10.1126/science.187.4174.319.