Species recognition of Pistacia and Amygdalus individuals using combination of UAV-based RGB imagery and digital surface model

Document Type : Complete scientific research article

Authors

Dept. of Remote Sensing and GIS, Faculty of Geography, University of Tehran, Tehran, Iran

Abstract

Background and objectives: Identification and mapping of tree species at single-tree levels using remotely sensed data is important in sustainable forest management. On the other hand, UAVs provide possibilities to acquire remotely sensed data with high spatial and temporal resolution that facilitate monitoring single tree and assessing quantitative and qualitative characteristics of trees such as species types. Methods based on machine learning can identify species types on UAV colour images but not with high accuracies. Additionally, similarity of trees in visible wavelengths registered on UAV colour images causes errors in species recognition. Therefore, this study was aimed to evaluate combination of UAV-based colour imagery and digital surface model (DSM) and deep learning algorithms in species recognition of a Pistacia-Amygdalus stand.
Material and Methods: A part of Pistacia-Amygdalus stands in the wild pistachio research forest with an area of 24 ha was selected for this study. The study area was covered by 649 colour images with spatial resolution of 3.5 cm in 16 flight lines acquired by a Phantom 4Pro UAV. In addition to orthophoto, the DSM with similar spatial resolution was obtained by inverse distance weighted (IDW) method. The colour images and the combination of colour images and DSM were then used by Convolutional Neural Networks (CNNs) to identify Pistacia trees and Amygdalus shrubs. Results were evaluated by indices of accuracy assessment (e.g., accuracy, area under curve (AUC) of receiver operating characteristics).
Results: The results on colour images showed that Amygdalus shrubs (accuracy=0.77, AUC=0.82) were identified with slightly higher accuracy than Pistacia trees (accuracy=0.76, AUC=0.80). Moreover, the results on combination of colour images and DSM showed that Pistacia trees (accuracy=0.85, AUC=0.85) were identified with higher accuracy than Amygdalus shrubs (accuracy=0.81, AUC=0.83). The final map was consisted of 455 Pistacia trees and 1951 Amygdalus shrubs. In addition, the visual interpretation of results revealed that species recognition on the combination of colour images and DSM had higher accuracy despite almost similar values of the indices of accuracy assessment.
Conclusions: In general, the present study explored that combination of colour images and DSM can facilitate species recognition of Pistacia trees and Amygdalus shrubs. Furthermore, this study confirms the capability of CNN in mapping of species at the individual level.
Conclusions: In general, the present study explored that combination of colour images and DSM can facilitate species recognition of Pistacia trees and Amygdalus shrubs. Furthermore, this study confirms the capability of CNN in mapping of species at the individual level.

Keywords

References

1.Egli, S., and Höpke, M. 2020. CNN-based tree species classification using high resolution RGB image data from automated UAV observations. Remote Sensing. 12: 3892. 1-17.
2.Guo, X., Liu, Q., Sharma, R.P., Chen, Q., Ye, Q., Tang, S., and Fu, L. 2021. Tree recognition on the plantation using UAV images with ultrahigh spatial resolution in a complex environment. Remote Sensing. 13: 4122. 1-23.
3.Yang, K., Zhang, H., Wang, F., and Lai, R. 2022. Extraction of broad-leaved tree crown based on UAV visible images and OBIA-RF model: A case study for Chinese olive trees. Remote Sensing. 14: 2469. 1-23.
4.Marzolff, I., Kirchhoff, M., Stephan, R., Seeger, M., Aït Hssaine, A., and Ries, J.B. 2022. Monitoring dryland trees with remote sensing. Part A: Beyond CORONA-Historical HEXAGON satellite imagery as a new data source for mapping open-canopy woodlands on the tree level. Frontiers in Environmental Sciences. 10: 896702. 1-21.
5.Onishi, M., and Ise, T. 2021. Explainable identification and mapping of trees using UAV RGB image and deep learning. Scientific Reports. 11: 903. 1-15.
6.Onishi, M., Watanabe, S., Nakashima, T., and Ise, T. 2022. Practicality and robustness of tree species identification using UAV RGB image and deep learning in temperate forest in Japan. Remote Sensing. 14: 1710. 1-22.
7.Erfanifard, Y., Kraszewski, B., and Stereńczak, K. 2021. Integration of remote sensing in spatial ecology: assessing the interspecific interactions
of two plant species in a semi-arid woodland using unmanned aerial vehicle (UAV) photogrammetric data. Oecologia. 196: 115-130.
8.Kattenborn, T., Eichel, J., Wiser, S., Burrows, L., Fassnacht, F.E., and Schmidtlein, S. 2020. Convolutional neural networks accurately predict cover fractions of plant species and communities in Unmanned Aerial Vehicle imagery. Remote Sensing in Ecology and Conservation. 6: 472-486.
9.Kattenborn, T., Eichel, J., and Fassnacht, F.E. 2019. Convolutional neural networks enable efficient, accurate and fine-grained segmentation of plant species and communities from high-resolution UAV imagery. Scientific Reports. 9: 17656. 1-9.
10.Gonroudobou, O.B.H., Silvestre, L.H., Diez, Y., Nguyen, H.T., and Caceres, M.L.L. 2022. Treetop detection in mountainous forests using UAV terrain awareness function. Computation. 10: 90. 1-14.
11.Al-Najjar, H., Kalantar, B., Pradhan, B., Saeidi, V., Halin, A., Ueda, N., and Mansor, S. 2019. Land cover classification from fused DSM and UAV images using Convolutional Neural Networks. Remote Sensing. 11: 1461. 1-18.
12.Wu, S., Deng, L., Guo, L., and Wu. Y. 2022. Wheat leaf area index prediction using data fusion based on high-resolution unmanned aerial vehicle imagery. Plant Methods. 18: 68. 1-16.
13.Garzon-Lopez, C.X., and Lasso, E. 2020. Species classification in a tropical alpine ecosystem using UAV-borne RGB and hyperspectral imagery. Drones. 4: 69. 1-18.
14.Yang, M., Mou, Y., Liu, S., Meng, Y., Liu, Z., Li, P., Xiang, W., Zhou, X., and Peng, C. 2022. Detecting and mapping tree crowns based on convolutional neural network and Google Earth images. International J. of Applied Earth Observation and Geoinformation. 108: 102764. 1-10.
15.Liu, Y., Zheng, X., Ai, G., Zhang, Y., and Zuo, Y. 2018. Generating a high-precision true digital orthophoto map based on UAV images. ISPRS International J. of Geo-Information. 7: 333. 1-15.
16.Aeberli, A., Johansen, K., Robson, A., Lamb, D.W., and Phinn, S. 2021. Detection of banana plants using multi-temporal multispectral UAV imagery. Remote Sensing. 13: 2123. 1-24.
17.Hendria, W.F., Phan, Q.T., Adzaka, F., and Jeong, C. 2022. Combining transformer and CNN for object detection in UAV imagery. ICT Express. https:// doi.org/10.1016/j.icte.2021.12.006.
18.Li, W., Fu, H., Yu, L., and Cracknell, A. 2017. Deep learning based oil palm tree detection and counting for high-resolution remote sensing Images. Remote Sensing. 9: 22. 1-13.
19.Osco, L., Junior, J., Ramos, A., Jorge, L., Fatholahi, S., Silva, J., Matsubara, E., Pistori, H., Gonçalves, W., and Li, J. 2021. A review on deep learning in UAV remote sensing. International J. of Applied Earth Observation and Geoinformation. 102: 102456. 1-38.
20.Congalton, R., and Green, K. 2019. Assesssing the accuracy of remotely sensed data (3rd Ed). CRC Press. USA. 348p.
21.Erfanifard, Y. 2014. Application of ROC curve to assess pixel-based classification methods on UltraCam-D aerial imagery to discriminate tree crowns in pure stands of Brant`s oak in Zagros forests. Iranian J. Forest and Poplar Research. 22: 4. 649-663. (In Persian)
22.Wiegand, T., and Moloney, K.A. 2014. Handbook of spatial point-pattern analysis in ecology. CRC Press. England. 510p.
23.Pourahmad, M., Oladi, J., and Fallah, A. 2018. Detection of tree species in mixed broad-leaved stands of Caspian forests using UAV images (Case study: Darabkola Forest). Ecology of Iranian Forest. 6: 11. 61-75. (In Persian)
24.Barazmand, S., Soosani, J., Naghavi, H., and Sadeghian, S. 2019. Discriminating between Brant`s oak (Quercus brantii Lindl.) and gall oak (Q. infectoria Oliv.) species using the UAV images. Iranian J. of Forest and Poplar Research. 27: 3. 245-257. (In Persian)
25.Miraki, M., Sohrabi, H., Fatehi, P., and Kneubuehler, M. 2020. Comparison of machine learning algorithms for broad leaf species classification using UAV-RGB images. J. of Geomatics Science and Technology. 10: 2. 1-10. (In Persian)
Journal of Wood and Forest Science and Technology
Volume 29, Issue 3
October 2022
Pages 93-111

Files

Share

How to cite

Statistics