Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2021, Vol. 18, No. 1, pp. 116-126

Semantic segmentation of damaged fir trees in unmanned aerial vehicle images

I.A. Kerchev 1 , К.А. Maslov 2 , N.G. Markov 2 , O.S. Tokareva 2 
1 Institute of Monitoring of Climatic and Ecological Systems SB RAS, Tomsk, Russia
2 National Research Tomsk Polytechnic University, Tomsk, Russia
Accepted: 09.12.2020
DOI: 10.21046/2070-7401-2021-18-1-116-126
A number of recent studies have shown that convolutional neural networks have found their application in the analysis of satellite images and images of the Earth surface, acquired with the use of unmanned aerial vehicles. Especially useful is their capability to automatically extract image features, such as textures and shapes of objects. This paper addresses the problem of the analysis of the state of fir trees in unmanned aerial vehicle images, provides the description of the research objects and conducts an exploratory analysis of the source data that allowed to build a new model of a convolutional neural network. A new convolutional neural network model, which is based on fully convolutional network U-Net architecture, is proposed. This model is used to do semantic segmentation of unmanned aerial vehicle images of fir forests damaged by Polygraphus proximus. In the paper, the architecture of the proposed neural network model is presented, and the main problems are solved regarding the processes of its training and assessment of the quality of semantic segmentation results obtained using the model. The results have shown a relatively high performance of the model while classifying pixels of the classes «Background», «Living trees», «Recently dead trees» and «Long dead trees». At the end, several ways are proposed to increase the performance of the developed model.
Keywords: Polygraphus proximus, fir trees, unmanned aerial vehicle, semantic image segmentation, convolutional neural network, U-Net.
Full text

References:

  1. Krivets S. A., Bisirova E. M., Volkova E. S., Debkov N. M., Kerchev I. A., Melnik M. A., Nikiforov A. N., Chernova N. A., Tekhnologiya monitoringa pikhtovykh lesov v zone invazii ussuriiskogo poligrafa v Sibiri (Fir forest monitoring technology in the invasion zone of the Ussuri polygraph in Siberia), Tomsk: UMIUM, 2018, 74 p.
  2. Pashenova N. V., Petko V. M., Kerchev I. A., Babichev N. S., Perenos ofiostomovykh gribov ussuriiskim poligrafom Polygraphus proximus Blandford (Coleoptera, Scolytidae) v Sibiri (Transfer of ophiostomatoid fungi by Polygraphus proximus Blandford (Coleoptera, Scolytidae) in Siberia), Izvestiya Sankt-Peterburgskoi lesotekhnicheskoi akademii, 2012, No. 200, pp. 114–120.
  3. http://perm.rcfh.ru/news/22860.html.
  4. Sannikov P. Yu., Andreev D. N., Buzmakov S. A., Vyyavlenie i analiz sukhostoya pri pomoshchi bespilotnogo letatel’nogo apparata (Identification and analysis of deadwood using an unmanned aerial vehicle), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 3, pp. 103–113, DOI: 10.21046/2070-7401-2018-15-3-103-113.
  5. Berie H. T., Burud I., Application of unmanned aerial vehicles in earth resources monitoring: focus on evaluating potentials for forest monitoring in Ethiopia, European J. Remote Sensing, 2018, Vol. 51, Issue 1, pp. 326–335, DOI: 10.1080/22797254.2018.1432993.
  6. Bystrov S. O., Antonov I. A., First record of the four-eyed fir bark beetle Polygraphus proximus Blandford, 1894 (Coleoptera, Curculionidae: Scolytinae) from Irkutsk province, Russia, Entomological Review, 2019, Vol. 99, No. 1, pp. 54–55, DOI: 10.1134/S001387381901007X.
  7. Chenari A., Erfanifard Y., Dehghani M., Pourghasemi H. R., Woodland Mapping at Single-Tree Levels Using Object-Oriented Classification of UAV Images, Intern. Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, Vol. XLII-4/W4, pp. 43–49, DOI: 10.5194/isprs-archives-XLII-4-W4-43-2017.
  8. Gini R., Sona G., Ronchetti G., Passoni D., Pinto L., Improving Tree Species Classification Using UAS Multispectral Images and Texture Measures, Intern. J. Geo-Informatics, 2018, Vol. 7, Issue 8, p. 315, DOI: 10.3390/ijgi7080315.
  9. Hossin M., Sulaiman M. N., A Review on Evaluation Metrics for Data Classification Evaluations, Intern. J. Data Mining and Knowledge Management Process, 2015, Vol. 5, No. 2, pp. 1–11, DOI: 10.5121/ijdkp.2015.5201.
  10. Ioffe S., Szegedy C., Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, arXiv preprint, arXiv:1502.03167, 2015, 11 p., available at: https://arxiv.org/abs/1502.03167.
  11. Kingma D. P., Ba J., Adam: A Method for Stochastic Optimization, arXiv preprint, arXiv:1412.6980, 2015, 15 p., available at: https://arxiv.org/abs/1412.6980.
  12. Lee S., Park S., Baek G., Kim H., Lee C., Detection of Damaged Pine Tree by the Pine Wilt Disease Using UAV Image, Korean J. Remote Sensing, 2019, Vol. 35, No. 3, pp. 359–373, DOI: 10.7780/kjrs.2019.35.3.2.
  13. McInnes L., Healy J., Melville J., UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction, arXiv preprint, arXiv:802.03426, 2018, 51 p., available at: https://arxiv.org/abs/1802.03426.
  14. Onishi M., Ise T., Automatic Classification of Trees Using a UAV Onboard Camera and Deep Learning, arXiv preprint, arXiv:1804.10390, 2018, 9 p., available at: https://arxiv.org/abs/1804.10390.
  15. Pashenova N. V., Kononov A. V., Ustyantsev K. V., Blinov A. G., Pertsovaya A. A., Baranchikov Yu. N., Ophiostomatoid fungi associated with the four-eyed fir bark beetle on the territory of Russia, Russian J. Biological Invasions, 2018, Vol. 9, No. 1, pp. 63–74, DOI: 10.1134/S2075111718010137.
  16. Rahman M. A., Wang Y., Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation, In: Advances in Visual Computing: Intern. Symp. Visual Computing, Lecture Notes in Computer Science, Springer, 2016, Vol. 10072, pp. 234–244, DOI: 10.1007/978-3-319-50835-1_22.
  17. Ronneberger O., Fischer P., Brox T., U-Net: Convolutional Networks for Biomedical Image Segmentation, arXiv preprint, arXiv:1505.04597, 2015, 8 p., available at: https://arxiv.org/abs/1505.04597.
  18. Rousseeuw P. J., Silhouettes: A graphical aid to the interpretation and validation of cluster analysis, J. Computational and Applied Mathematics, 1987, Vol. 30, pp. 33–65, DOI: 10.1016/0377-0427(87)90125-7.
  19. Safonova A., Tabik S., Alcaraz-Segura D., Rubtsov A., Maglinets Y., Herrera F., Detection of Fir Trees (Abies sibirica) Damaged by the Bark Beetle in Unmanned Aerial Vehicle Images with Deep Learning, Remote Sensing, 2019, Vol. 11, No. 6, Art. No. 643, 19 p., DOI: 10.3390/rs11060643.