Skip to main content
Log in

Multi-model tree detection in satellite images with weighted boxes fusion

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Forests provide several ecological, sociocultural, and economic advantages to humanity. Rapid loss of forest lands is a result of uncontrolled, unauthorized, and commercial use. Although several methods have been proposed to protect and control forests, none of them was sustainable. One promising approach to monitor forest lands is using satellite images and computer vision techniques. Therefore, researchers proposed tree detection methods for this purpose. In this study, we propose merging the result of these methods via weighted boxes fusion which is a post-processing technique. We aim to eliminate the disadvantages while maintaining the advantages of existing methods this way. Hence, we picked the swin transformer, RCNN, faster RCNN, YOLO, and DETR for tree detection from satellite images. Then, we fuse their results in a combinational way. While doing so, we always keep the swin transformer since it has the highest performance score. We tabulate the fusion results on a diverse dataset. We report the strengths and weaknesses of the proposed fusion method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2

Similar content being viewed by others

Data availibility

No datasets were generated or analysed during the current study.

Code Availability

Data and code will be available upon publication.

References

  1. Durgut, O., Ünsalan, C.: A swin transformer, YOLO, and weighted boxes fusion-based approach for tree detection in satellite images. 32nd Signal Processing and Communications Applications Conference (SIU) 1–4 (2024)

  2. Whitehead, D.: Forests as carbon sinks - benefits and consequences. Tree Phys. 31, 893–902 (2011)

    Article  MATH  Google Scholar 

  3. Bonan, G.B.: Forests and climate change: forcings, feedbacks, and the climate benefits of forests. Science 320, 1444–1449 (2008)

    Article  MATH  Google Scholar 

  4. FAO. Global forest resources assessment 2020: Main report (Food & Agriculture Organization of the UN,) (2020)

  5. Giam, X.: Global biodiversity loss from tropical deforestation. Proceed. Nat. Acad. Sci. 114, 5775–5777 (2017)

    Article  MATH  Google Scholar 

  6. Anderegg, W.R., et al.: Climate-driven risks to the climate mitigation potential of forests. Science 368, eaaz7005 (2020)

    Article  MATH  Google Scholar 

  7. Castelo, T.B.: Brazilian forestry legislation and to combat deforestation government policies in the Amazon (Brazilian Amazon). Ambiente & Soc. 18, 221–242 (2015)

    Article  MATH  Google Scholar 

  8. Coşkun, A.A., Gençay, G.: Kyoto protocol and deforestation: A legal analysis on Turkish environment and forest legislation. Forest Policy Econ. 13, 366–377 (2011)

    MATH  Google Scholar 

  9. Gençay, G., Birben, Ü., Aydın, A.: To be a developed country or not to be? The effect of the Paris agreement on Turkish forest law. Environ. Monitor. Assess. 191, 1–14 (2019)

    Article  MATH  Google Scholar 

  10. Gibril, M.B.A., et al.: Deep convolutional neural networks and swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images. Geocarto Int. 37, 18569–18599 (2022)

    Article  Google Scholar 

  11. Gibril, M.B.A., et al.: Large-scale date palm tree segmentation from multiscale UAV-based and aerial images using deep vision transformers. Drones 7, 93 (2023)

    Article  Google Scholar 

  12. Aburasain, R., Edirisinghe, E., Albatay, A.: Palm tree detection in drone images using deep convolutional neural networks: Investigating the effective use of YOLO v3. Conference on Multimedia, Interaction, Design and Innovation 21–36 (2020)

  13. Luo, M., et al.: Individual tree detection in coal mine afforestation area based on improved faster RCNN in UAV RGB images. Remote Sens. 14, 5545 (2022)

    Article  MATH  Google Scholar 

  14. Dersch, S., Schöttl, A., Krzystek, P., Heurich, M.: Novel single tree detection by transformers using UAV-based multispectral imagery. Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci. 43, 981–988 (2022)

    Article  Google Scholar 

  15. Solovyev, R., Wang, W., Gabruseva, T.: Weighted boxes fusion: ensembling boxes from different object detection models. Image Vis. Comput. 107, 104117 (2021)

    Article  Google Scholar 

  16. Vaswani, A., et al.: Attention is all you need. Advances in Neural Information Processing Systems30 (2017)

  17. Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF International conference on computer vision 10012–10022 (2021)

  18. Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. arXiv: 1311.2524 (2013)

  19. Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv: 1506.01497 (2015)

  20. Nguyen, N.-D., Do, T., Ngo, T.D., Le, D.-D.: An evaluation of deep learning methods for small object detection. J. Electric. Comput. Eng. 2020, 3189691 (2020)

    Article  MATH  Google Scholar 

  21. Liu, Y., Sun, P., Wergeles, N., Shang, Y.: A survey and performance evaluation of deep learning methods for small object detection. Expert Syst. Appl. 172, 114602 (2021)

    Article  Google Scholar 

  22. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: Unified, real-time object detection, You only look once (2016)

  23. Wang, Y., et al.: Remote sensing image super-resolution and object detection: benchmark and state of the art. Expert Syst. Appl. 197, 116793 (2022)

    Article  Google Scholar 

  24. Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. arXiv: 1804.02767 (2018)

  25. Carion, N., et al.: End-to-end object detection with transformers. arXiv 2005, 12872 (2020)

    Google Scholar 

  26. Zhu, X., et al.: Deformable DETR: Deformable transformers for end-to-end object detection. arXiv: 2010.04159 (2020)

  27. Jiang, P., Ergu, D., Liu, F., Cai, Y., Ma, B.: A review of YOLO algorithm developments. Proced. Comput. Sci. 199, 1066–1073 (2022)

    Article  MATH  Google Scholar 

  28. Chen, K., et al.: Mmdetection: Open MMLab detection toolbox and benchmark. arXiv: 1906.07155 (2019)

Download references

Acknowledgements

This study is supported by TUBITAK Project No. 221N393 and Project ForestMap. Project ForestMap is supported under the umbrella of ERANET Cofund ForestValue by Swedish Governmental Agency for Innovation Systems, Swedish Energy Agency, The Swedish Research Council for Environment, Agricultural Sciences and Spatial Planning, Academy of Finland, and the Scientific and Technological Research Council of Turkey (TUBITAK). ForestValue has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 773324 and from TUBITAK Project No. 221N393.

Author information

Authors and Affiliations

Authors

Contributions

All authors contributed equally to the mansucript.

Corresponding author

Correspondence to Cem Ünsalan.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This paper is the extended version of our paper published in 2024 32nd IEEE Conference on Signal Processing and Communications Applications (SIU) [1].

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Durgut, O., Ünsalan, C. Multi-model tree detection in satellite images with weighted boxes fusion. SIViP 19, 32 (2025). https://doi.org/10.1007/s11760-024-03722-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11760-024-03722-z

Keywords

Navigation