Browse > Article
http://dx.doi.org/10.7780/kjrs.2018.34.6.3.9

Optimal Parameter Analysis and Evaluation of Change Detection for SLIC-based Superpixel Techniques Using KOMPSAT Data  

Chung, Minkyung (Department of Civil and Environmental Engineering, Seoul National University)
Han, Youkyung (School of Convergence and Fusion System Engineering, Kyungpook National University)
Choi, Jaewan (School of Civil Engineering, Chungbuk National University)
Kim, Yongil (Department of Civil and Environmental Engineering, Seoul National University)
Publication Information
Korean Journal of Remote Sensing / v.34, no.6_3, 2018 , pp. 1427-1443 More about this Journal
Abstract
Object-based image analysis (OBIA) allows higher computation efficiency and usability of information inherent in the image, as it reduces the complexity of the image while maintaining the image properties. Superpixel methods oversegment the image with a smaller image unit than an ordinary object segment and well preserve the edges of the image. SLIC (Simple linear iterative clustering) is known for outperforming the previous superpixel methods with high image segmentation quality. Although the input parameter for SLIC, number of superpixels has considerable influence on image segmentation results, impact analysis for SLIC parameter has not been investigated enough. In this study, we performed optimal parameter analysis and evaluation of change detection for SLIC-based superpixel techniques using KOMPSAT data. Forsuperpixel generation, three superpixel methods (SLIC; SLIC0, zero parameter version of SLIC; SNIC, simple non-iterative clustering) were used with superpixel sizes in ranges of $5{\times}5$ (pixels) to $50{\times}50$ (pixels). Then, the image segmentation results were analyzed for how well they preserve the edges of the change detection reference data. Based on the optimal parameter analysis, image segmentation boundaries were obtained from difference image of the bi-temporal images. Then, DBSCAN (Density-based spatial clustering of applications with noise) was applied to cluster the superpixels to a certain size of objects for change detection. The changes of features were detected for each superpixel and compared with reference data for evaluation. From the change detection results, it proved that better change detection can be achieved even with bigger superpixel size if the superpixels were generated with high regularity of size and shape.
Keywords
SLIC; Superpixel; Image Segmentation; OBIA; Change Detection; KOMPSAT;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Achanta, R. and S. Susstrunk, 2017. Superpixels and Polygons using Simple Non-Iterative Clustering, Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, Jul. 21-26, pp. 4895-4904.
2 Achanta, R., A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, 2012. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods, IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11): 2274-2282.   DOI
3 Byun, Y., Y. Han, and T. Chae, 2015. Image Fusion-Based Change Detection for Flood Extent Extraction Using Bi-Temporal Very High-Resolution Satellite Images, Remote Sensing, 7(8): 10347-10363.   DOI
4 Chen, G., K. Zhao, and R. Powers, 2014. Assessment of the image misregistration effects on objectbased change detection, ISPRS Journal of Photogrammetry and Remote Sensing, 87: 19-27.   DOI
5 Choi, J., G. Kim, N. Park, H. Park, and S. Choi, 2017. A Hybrid Pansharpening Algorithm of VHR Satellite Images that Employs Injection Gains Based on NDVI to Reduce Computational Costs, Remote Sensing, 9(10): 976.   DOI
6 Chung, M., Y. Han, J. Choi, and Y. Kim, 2018. Evaluation of Object-based Change Detection using SLIC Superpixels, Proc. of Korean Society of Remote Sensing Fall Conference, Muju, Korea, Oct. 24-26, pp. 19-22 (in Korean).
7 Ester, M., H. P. Kriegel, J. Sander, and X. Xu, 1996. A density-based algorithm for discovering clusters in large spatial databases with noise, Proc. of the 2nd International Conference on Knowledge Discovery and Data Mining, Portland, Oregon, Aug. 2-4, vol. 96, no. 34, pp. 226-231.
8 Han, Y., T. Kim, and C. Lee, 2018. Comparison of Segmentation Inputs for Object-based Unsupervised Change Detection between Very-high-resolution Bi-temporal Images, Proc. of Asian Conference on Remote Sensing, vol. 2, pp. 1165-1169.
9 Hou, B., Y. Wang, and Q. Liu, 2016. A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing Images, Sensors, 16(9): 1377.   DOI
10 Kavzoglu, T. and H. Tonbu, 2017. Selecting Optimal SLIC Superpixels Parameters by Using Discrepancy Measures, Proc. of Asian Conference on Remote Sensing, New Delhi, India, Oct. 23-27, pp. 1-7.
11 Powers, D. M., 2011. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation, Journal of Machine Learning Technologies, 2(1): 37-63.
12 Kovesi, P. D., 2000. MATLAB and Octave Functions for Computer Vision and Image Processing, http://www.peterkovesi.com/matlabfns, Accessed on Dec. 17, 2018.
13 Li, Y., Y. Tan, J. Deng, Q. Wen, and J. Tian, 2015. Cauchy Graph Embedding Optimization for Built-Up Areas Detection from High-Resolution Remote Sensing Images, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(5): 2078-2096.   DOI
14 Neubert, P. and P. Protzel, 2012. Superpixel benchmark and comparison, Forum Bildverarbeitung, 6: 205-208.
15 Ru, H., X. Yang, D. Peng, and P. Huang, 2014. Superparsing based change detection in high resolution remote sensing imagery, Proc. of 2014 12th International Conference on Signal Processing, Hangzhou, China, Oct. 19-23, pp. 996-999.
16 Vargas, J. E., P. T. Saito, A. X. Falcao, P. J. Rezende, and J. A. Santos, 2014. Superpixel-Based Interactive Classification of Very High Resolution Images, Proc. of 2014 27th SIBGRAPI Conference on Graphics, Patterns and Images, Rio de Janeiro, Brazil, Aug. 27-30, pp. 173-179.
17 Wang, B., J. Choi, S. Choi, S. Lee, P. Wu, and Y. Gao, 2017. Image Fusion-Based Land Cover Change Detection Using Multi-Temporal High-Resolution Satellite Images, Remote Sensing, 9(8): 804.   DOI
18 Wu, Z., Z. Hu, and Q. Fan, 2012. Superpixel-based unsupervised change detection using multidimensional change vector analysis and SVMbased classification, Proc. of ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Melbourne, Australia, Aug. 25-Sep. 1, vol. I-7, pp. 257-262.