single-dr.php

JDR Vol.16 No.4 pp. 588-595
(2021)
doi: 10.20965/jdr.2021.p0588

Paper:

Study on Combining Two Faster R-CNN Models for Landslide Detection with a Classification Decision Tree to Improve the Detection Performance

Asadang Tanatipuknon*1,*2,†, Pakinee Aimmanee*1, Yoshihiro Watanabe*3, Ken T. Murata*4, Akihiko Wakai*5, Go Sato*6, Hoang Viet Hung*7, Kanokvate Tungpimolrut*2, Suthum Keerativittayanun*2, and Jessada Karnjana*2

*1Sirindhorn International Institute of Technology, Thammasat University
Pathum Thani, Thailand

Corresponding author

*2National Electronics and Computer Technology Center (NECTEC),
National Science and Technology Development Agency, Pathum Thani, Thailand

*3School of Engineering, Tokyo Institute of Technology, Tokyo, Japan

*4National Institute of Information and Communications Technology (NICT), Tokyo, Japan

*5Graduate School of Science and Technology, Gunma University, Gumma, Japan

*6Graduate School of Environmental Informations, Teikyo Heisei University, Tokyo, Japan

*7Faculty of Civil Engineering, Thuyloi University, Hanoi, Vietnam

Received:
November 30, 2020
Accepted:
April 4, 2021
Published:
June 1, 2021
Keywords:
Faster R-CNN, classification decision tree, landslide detection, satellite imagery
Abstract

This study aims to improve the accuracy of landslide detection in satellite images by combining two object detection models based on a faster region-based convolutional neural network (Faster R-CNN) with a classification decision tree. The proposed method combines the predicted results from the two Faster R-CNN models and classifies their features with a classification decision tree to generate a bounding-box that surrounds the landslide area in the input image. The first Faster R-CNN model is trained by using a training set of color images (RGB images). The second model is trained by using grayscale images that represent digital elevation models (DEMs). The results from both models are used to construct features for training a classification decision tree. The resulting bounding-box is selected from the following four classes: the box obtained from the RGB model, the box obtained from the DEM model, the intersection of those two boxes, and the smallest box that contains the union of them. The evaluation results show that the proposed method is better than the RGB model in terms of accuracy, precision, recall, F-measure, and Intersection-over-Union (IoU) score. It is slightly better than the DEM model in almost all evaluation metrics, except the precision.

Cite this article as:
Asadang Tanatipuknon, Pakinee Aimmanee, Yoshihiro Watanabe, Ken T. Murata, Akihiko Wakai, Go Sato, Hoang Viet Hung, Kanokvate Tungpimolrut, Suthum Keerativittayanun, and Jessada Karnjana, “Study on Combining Two Faster R-CNN Models for Landslide Detection with a Classification Decision Tree to Improve the Detection Performance,” J. Disaster Res., Vol.16, No.4, pp. 588-595, 2021.
Data files:
References
  1. [1] World Health Organization (WHO), “Landslides,” https://www.who.int/health-topics/landslides [accessed September 11, 2020]
  2. [2] E. Intrieri, G. Gigli, F. Mugnai, R. Fanti, and N. Casagli, “Design and implementation of a landslide early warning system,” Engineering Geology, Vol.147-148, pp. 124-136, 2012.
  3. [3] S. N. K. B. Amit and Y. Aoki, “Disaster detection from aerial imagery with convolutional neural network,” Proc. of 2017 Int. Electronics Symp. on Knowledge Creation and Intelligent Computing (IES-KCIC), pp. 239-245, 2017.
  4. [4] U. Niethammer, M. James, S. Rothmund, J. Travelletti, and M. Joswig, “UAV-based remote sensing of the Super-Sauze landslide: Evaluation and results,” Engineering Geology, Vol.128, pp. 2-11, 2012.
  5. [5] O. Ghorbanzadeh, T. Blaschke, K. Gholamnia, S. R. Meena, D. Tiede, and J. Aryal, “Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection,” Remote Sensing, Vol.11, No.2, Article No.196, 2019.
  6. [6] H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, “Generalized intersection over union: A metric and a loss for bounding box regression,” Proc. of 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 658-666, 2019.
  7. [7] R. Soeters and C. J. Van Westen, “Slope instability recognition, analysis, and zonation,” A. K. Turner and R. L. Schuster (Eds.), “Landslides: Investigation and mitigation (Transportation Research Board Special Report 247),” pp. 129-177, National Academy of Science, 1996.
  8. [8] S. Ji, D. Yu, C. Shen, W. Li, and Q. Xu, “Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks,” Landslides, Vol.17, No.6, pp. 1337-1352, 2020.
  9. [9] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” Proc. of the 28th Int. Conf. on Neural Information Processing Systems (NIPS’15), Vol.1, pp. 91-99, 2015.
  10. [10] R. Girshick, “Fast R-CNN,” Proc. of 2015 IEEE Int. Conf. on Computer Vision (ICCV), pp. 1440-1448, 2015.
  11. [11] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. of 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016.
  12. [12] Stanford Vision Lab, Stanford University, and Princeton University, “ImageNet,” https://image-net.org [accessed February 1, 2021]
  13. [13] L. Breiman, J. Friedman, C. J. Stone, and R. A. Olshen, ”Classification and regression trees,” CRC Press, 1984.
  14. [14] M. Pal and P. M. Mather, “An assessment of the effectiveness of decision tree methods for land cover classification,” Remote Sensing of Environment, Vol.86, No.4, pp. 554-565, 2003.
  15. [15] P.-N. Tan, M. Steinbach, and V. Kumar, ”Introduction to data mining,” 1st Edition, Pearson Education, 2016.
  16. [16] M. Buckland and F. Gey, “The relationship between Recall and Precision,” J. of the American Society for Information Science, Vol.45, No.1, pp. 12-19, 1994.
  17. [17] M. Story and R. G. Congalton, “Accuracy assessment: A user’s perspective,” Photogrammetric Engineering and Remote Sensing, Vol.52, No.3, pp. 397-399, 1986.
  18. [18] P. Lu, Y. Qin, Z. Li, A. C. Mondini, and N. Casagli, “Landslide mapping from multi-sensor data through improved change detection-based Markov random field,” Remote Sensing of Environment, Vol.231, Article No.111235, 2019.
  19. [19] S. Nowozin, “Optimal decisions from probabilistic models: The intersection-over-union case,” Proc. of 2014 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 548-555, 2014.
  20. [20] J. C. Huang and S. J. Kao, “Optimal estimator for assessing landslide model performance,” Hydrology and Earth System Sciences, Vol.10, No.6, pp. 957-965, 2006.
  21. [21] K. Sentz and S. Ferson, ”Combination of evidence in Dempster-Shafer theory,” Sandia National Laboratories, doi: 10.2172/800792, 2002.
  22. [22] S. Mohajerani and P. Saeedi, “Cloud-Net: An end-to-end cloud detection algorithm for Landsat 8 imagery,” Proc. of 2019 IEEE Int. Geoscience and Remote Sensing Symp. (IGARSS 2019), pp. 1029-1032, 2019.
  23. [23] S. L. Phung, A. Bouzerdoum, and D. Chai, “Skin segmentation using color pixel classification: Analysis and comparison,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.27, No.1, pp. 148-154, 2005.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jun. 22, 2021