ABSTRACT
Owing to the immunity to illumination and atmospheric conditions, synthetic aperture radar (SAR) images have been the main source of data for environmental monitoring. However, it is a challenging task for change detection because of the influence of speckle noise. In this paper, we propose an unsupervised multiobjective particle swarm optimization approach based on decomposition for change detection in SAR images. For the change detection task, it can be modeled as a multiobjective optimization problem (MOP), which consists of two contradictory objectives, namely, retaining image change details and removing the speckle noise. We optimize this MOP by using particle swarm optimization, which decomposes it into a set of subproblems by assigning different weights to these two objectives, thus obtaining the optimal trade-off between them. To accurately identify changed regions, the strategy of majority voting is employed to assemble partial good solutions to generate the final change detection result. The impressive experimental results on both real data sets have demonstrated the effectiveness and superiority of the proposed method.
- Yakoub Bazi, Lorenzo Bruzzone, and Farid Melgani. 2005. An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens. 43, 4 (2005), 874--887.Google ScholarCross Ref
- Mourad Bouziani, Kalifa Goïta, and Dong-Chen He. 2010. Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge. ISPRS J. Photogramm. Remote Sens. 65, 1 (2010), 143--153.Google ScholarCross Ref
- Jürgen Branke, Kalyanmoy Deb, Henning Dierolf, and Matthias Osswald. 2004. Finding knees in multi-objective optimization. In International Conference on Parallel Problem Solving from Nature. Birmingham, UK, Springer, 722--731.Google ScholarCross Ref
- Dominik Brunner, Guido Lemoine, and Lorenzo Bruzzone. 2010. Earthquake damage assessment of buildings using VHR optical and SAR imagery. IEEE Trans. Geosci. Remote Sens. 48, 5 (2010), 2403--2420.Google ScholarCross Ref
- Florentin Bujor, Emmanuel Trouvé, Lionel Valet, J-M Nicolas, and J-P Rudant. 2004. Application of log-cumulants to the detection of spatiotemporal discontinuities in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens. 42, 10 (2004), 2073--2084.Google ScholarCross Ref
- Turgay Celik. 2010. Change detection in satellite images using a genetic algorithm approach. IEEE Geosci. Remote Sens. Lett. 7, 2 (2010), 386--390.Google ScholarCross Ref
- Somayyeh Chamaani, Seyed Abdullah Mirtaheri, Mohammad Teshnehlab, and Mahdi Aliyari Shooredeli. 2007. Modified multi-objective particle swarm optimization for electromagnetic absorber design. In Proc. IEEE Asia-Pacific Conf. Applied Electromagnetics (APACE 2007). Melaka, Malaysia, IEEE, 1--5.Google ScholarCross Ref
- Chi-kin Chow and Hung-tat Tsui. 2004. Autonomous agent response learning by a multi-species particle swarm optimization. In Proc. IEEE Congr. Evolutionary Computation (CEC 2004), Vol. 1. Portland, Oregon, USA, IEEE, 778--785.Google Scholar
- XL Dai and Slamak Khorram. 1999. Remotely sensed change detection based on artificial neural networks. Photogramm. Eng. Remote Sens. 65 (1999), 1187--1194.Google Scholar
- Kalyanmoy Deb. 1989. An investigation of niche and species formation in genetic function optimization. In Proc. 3rd Int. Conf. Genetic Algorithms. Fairfax, Virginia, USA, 42--50. Google ScholarDigital Library
- Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and TAMT Meyarivan. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6, 2 (2002), 182--197. Google ScholarDigital Library
- Joseph C Dunn. 1974. A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters. J. Cyberm. 3 (1974), 32--57.Google ScholarCross Ref
- Russell Eberhart and James Kennedy. 1995. A new optimizer using particle swarm theory. In Proc. 6th Int. Symp. Micromachine Human Sci. Nagoya, Japan, IEEE, 39--43.Google ScholarCross Ref
- Ahmed AA Esmin, Rodrigo A Coelho, and Stan Matwin. 2015. A review on particle swarm optimization algorithm and its variants to clustering high-dimensional data. Artif. Intell. Rev. 44, 1 (2015), 23--45. Google ScholarDigital Library
- Pedram Ghamisi, Micael S Couceiro, Fernando ML Martins, and Jon Atli Benediktsson. 2014. Multilevel image segmentation based on fractional-order Darwinian particle swarm optimization. IEEE Trans. Geosci. Remote Sens. 52, 5 (2014), 2382--2394.Google ScholarCross Ref
- Xiaohui Hu and Russell Eberhart. 2002. Multiobjective optimization using dynamic neighborhood particle swarm optimization. In Proc. IEEE Congr. Evolutionary Computation (CEC 2002), Vol. 2. Hawaii, USA, IEEE, 1677--1681. Google ScholarDigital Library
- Joshua D Knowles and David W Corne. 2000. Approximating the nondominated front using the Pareto archived evolution strategy. Evolut. Comput. 8, 2 (2000), 149--172. Google ScholarDigital Library
- Stelios Krinidis and Vassilios Chatzis. 2010. A robust fuzzy local information C-means clustering algorithm. IEEE Trans. Image Process. 19, 5 (2010), 1328--1337. Google ScholarDigital Library
- Xiaolei Liang, Wenfeng Li, Yu Zhang, and MengChu Zhou. 2015. An adaptive particle swarm optimization method based on clustering. Soft Comput. 19, 2 (2015), 431--448. Google ScholarDigital Library
- Dengsheng Lu, P Mausel, E Brondizio, and Emilio Moran. 2004. Change detection techniques. Int. J. Remote Sens. 25, 12 (2004), 2365--2401.Google ScholarCross Ref
- Seyed Ali Mirjalili, Siti Zaiton Mohd Hashim, and Hossein Moradian Sardroudi. 2012. Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm. Appl. Math. Comput. 218, 22 (2012), 11125--11137.Google ScholarCross Ref
- Gabriele Moser and Sebastiano B Serpico. 2006. Generalized minimum-error thresholding for unsupervised change detection from SAR amplitude imagery. IEEE Trans. Geosci. Remote Sens. 44, 10 (2006), 2972--2982.Google ScholarCross Ref
- W Muttitanon and NK Tripathi. 2005. Land use/land cover changes in the coastal zone of Ban Don Bay, Thailand using Landsat 5 TM data. Int. J. Remote Sens. 26, 11 (2005), 2311--2323.Google ScholarCross Ref
- Konstantinos E Parsopoulos and Michael N Vrahatis. 2002. Particle swarm optimization method in multiobjective problems. In Proc. ACM Symp. Applied Computing (SAC 2002). Madrid, Spain, ACM, 603--607. Google ScholarDigital Library
- George H Rosenfield and Katherine Fitzpatrick-Lins. 1986. A coefficient of agreement as a measure of thematic classification accuracy. Photogramm. Eng. Remote Sens. 52, 2 (1986), 223--227.Google Scholar
- Yuhui Shi et al. 2001. Particle swarm optimization: developments, applications and resources. In Proc. IEEE Congr. Evolutionary Computation (CEC 2001), Vol. 1. IEEE, 81--86.Google Scholar
- Ashbindu Singh. 1989. Review article digital change detection techniques using remotely-sensed data. Int. J. Remote Sens. 10, 6 (1989), 989--1003.Google ScholarCross Ref
- Bing Xue, Mengjie Zhang, and Will N Browne. 2013. Particle swarm optimization for feature selection in classification: A multi-objective approach. IEEE Trans. Cybern 43, 6 (2013), 1656--1671.Google ScholarCross Ref
- Qingfu Zhang and Hui Li. 2007. MOEA/D: A multiobjective evolutionary algorithm based on decomposition. IEEE Trans. Evol. Comput. 11, 6 (2007), 712--731. Google ScholarDigital Library
- Zhi-Hua Zhou, Jianxin Wu, and Wei Tang. 2002, Ensembling neural networks: many could be better than all. Artif. Intell 137, 1--2 (2002), 239--263. Google ScholarDigital Library
Index Terms
- Decomposition-based multiobjective particle swarm optimization for change detection in SAR images
Recommendations
An parallel particle swarm optimization approach for multiobjective optimization problems
GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computationThis paper proposes a parallel particle swarm optimization (PPSO) to solve the multiobjective optimization problems (MOP). PPSO makes the use of the parallel characteristic of the PSO algorithm to deal with the multiple objectives issue of the MOP. PPSO ...
Efficient network architecture search via multiobjective particle swarm optimization based on decomposition
AbstractThe efforts devoted to manually increasing the width and depth of convolutional neural network (CNN) usually require a large amount of time and expertise. It has stimulated a rising demand of neural architecture search (NAS) over these ...
A Novel Boundary Based Multiobjective Particle Swarm Optimization
Proceedings, Part I, of the 6th International Conference on Advances in Swarm and Computational Intelligence - Volume 9140A novel boundary based multiobjective particle swarm optimization is presented in this paper. The proposed multiobjective optimization algorithm searches the border of the objective space unlike other current proposals to look for the Pareto solution ...
Comments