Abstract
Change Detection from remote sensing images is one of the most challenging and controversial topics among researchers in this field. Given the variety of types of surveyed areas and the data used, it cannot be claimed that there is a comprehensive way to identify different types of remote sensing data.This research aims to represent three robust and novel cost functions based on improving conventional thresholding techniques (i.e., Otsu, Fisher, and Kittler & Illingworth) combined with Particle Swarm Optimization method. The aim of the research is to detect the local-global variation of bi-temporal remotely sensed images based on images statistics but without any a-prior assumptions. The proposed method consists of four fundamental steps. The first step is a preprocessing step, as an indispensable step, in order to equalize the spectral domains of inputs images and also the geometric correction of them. The second step is a process of difference image generation to highlight the changed regions in the study areas. Then, the generated difference image is split to smaller size non-overlapped blocks with the aim of local change analysis. The third step emphasizes the importance of the proposed method and also discusses in improving the cost functions of conventional thresholding techniques as local-global techniques in detail. Next, the final change map is created based on the maximum vote method and image bands combination results. At the final step, accuracy assessment and sensitivity analysis were applied to evaluate the performance of the proposed method. Experimental result on Landsat data (i.e., Alaska region and Uremia Lake) demonstrated the accuracy improvement of three proposed change detection methods about (2% -11%) over different thresholding cost functions. Therefore, the results prove the efficiency and robustness of the proposed cost function compared to the initial cost function.
Similar content being viewed by others
References
C, Adak (2014). "rough clustering based unsupervised image change detection." arXiv preprint arXiv:1404.6071
Asokan A, Anitha J (2019) Change detection techniques for remote sensing applications: a survey. Earth Sci Inf 12(2):143–160
Bazi, Y., L. Bruzzone and F. Melgani (2004). An approach to unsupervised change detection in multitemporal SAR images based on the generalized Gaussian distribution. Geoscience and remote sensing symposium, 2004. IGARSS'04. Proceedings. 2004 IEEE international, IEEE
Bazi Y, Bruzzone L, Melgani F (2006) Automatic identification of the number and values of decision thresholds in the log-ratio image for change detection in SAR images. IEEE Geosci Remote Sens Lett 3(3):349–353
Bovolo F, Bruzzone L (2007) A split-based approach to unsupervised change detection in large-size multitemporal images: application to tsunami-damage assessment. IEEE Trans Geosci Remote Sens 45(6):1658–1670
Bruzzone L, Prieto DF (2000) Automatic analysis of the difference image for unsupervised change detection. IEEE Trans Geosci Remote Sens 38(3):1171–1182
Celik T (2009a) Multiscale change detection in multitemporal satellite images. IEEE Geosci Remote Sens Lett 6(4):820–824
Celik T (2009b) Unsupervised change detection in satellite images using principal component analysis and k-means clustering. IEEE Geosci Remote Sens Lett 6(4):772–776
Celik T (2010) Change detection in satellite images using a genetic algorithm approach. IEEE Geosci Remote Sens Lett 7(2):386–390
Coppin P, Jonckheere I, Nackaerts K, Muys B, Lambin E (2004) Review ArticleDigital change detection methods in ecosystem monitoring: a review. Int J Remote Sens 25(9):1565–1596
Dai X, Khorram S (1998) The effects of image misregistration on the accuracy of remotely sensed change detection. IEEE Trans Geosci Remote Sens 36(5):1566–1577
R. C, Eberhart And Y. Shi (2001). Tracking and optimizing dynamic systems with particle swarms. Proceedings of the 2001 congress on evolutionary computation (IEEE cat. No. 01TH8546), IEEE
Ghanbari M, Akbari V, Abkar A, Sahebi M (2015) Minimum-error Thresholding for unsupervised change detection in multilook Polarimetric SAR images. Journal of Geomatics Science and Technology 5(2):17–29
Guo C (2003) The fisher criterion function method of image thresholding. Chin J Sci Instrum 24(6):564–567
M, Hasanlou and S. T. Seydi (2018). Sensitivity analysis on performance of different unsupervised threshold selection methods in hyperspectral change detection. 2018 10th IAPR workshop on pattern recognition in remote sensing (PRRS), IEEE
Hussain M, Chen D, Cheng A, Wei H, Stanley D (2013) Change detection from remotely sensed images: from pixel-based to object-based approaches. ISPRS J Photogramm Remote Sens 80:91–106
Islam K, Jashimuddin M, Nath B, Nath TK (2018) Land use classification and change detection by using multi-temporal remotely sensed imagery: the case of Chunati wildlife sanctuary, Bangladesh. Egyptian Journal of Remote Sensing and Space Science 21(1):37–47
Kennedy J (2011) Particle swarm optimization. Springer, Encyclopedia of machine learning, pp 760–766
Kittler J, Illingworth J (1986) Minimum error thresholding. Pattern Recogn 19(1):41–47
Kurita T, Otsu N, Abdelmalek N (1992) Maximum likelihood thresholding based on population mixture models. Pattern Recogn 25(10):1231–1240
Liu Y, Yano T, Nishiyama S, Kimura R (2007) Radiometric correction for linear change-detection techniques: analysis in bi-temporal space. Int J Remote Sens 28(22):5143–5157
Lu D, Mausel P, Brondizio E, Moran E (2004) Change detection techniques. Int J Remote Sens 25(12):2365–2401
Melgani F, Moser G, Serpico SB (2002) Unsupervised change-detection methods for remote-sensing images. Opt Eng 41(12):3288–3298
Moghimi A, Khazai S, Mohammadzadeh A (2017a) An improved fast level set method initialized with a combination of k-means clustering and Otsu thresholding for unsupervised change detection from SAR images. Arab J Geosci 10(13):293
Moghimi A, Mohammadzadeh A, Khazai S (2017b) Integrating thresholding with level set method for unsupervised change detection in multitemporal SAR images. Can J Remote Sens 43(5):412–431
Moser G, Serpico SB (2006) Generalized minimum-error thresholding for unsupervised change detection from SAR amplitude imagery. IEEE Trans Geosci Remote Sens 44(10):2972–2982
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics 9(1):62–66
Patra S, Ghosh S, Ghosh A (2011) Histogram thresholding for unsupervised change detection of remote sensing images. Int J Remote Sens 32(21):6071–6089
Sadeghi V, Ebadi H, Mohammadzadeh A, Ahmadi FF (2016) Change detection in multitemporal remote sensing imagery with Thresholding of PSO-based fused change index. Journal of Geomatics Science and Technology 5(3):175–192
Solano-Correa YT, Bovolo F, Bruzzone L (2019) An approach to multiple change detection in VHR optical images based on iterative clustering and adaptive thresholding. IEEE Geosci Remote Sens Lett 16(8):1334–1338
Sumaiya M, Kumari RSS (2017) Gabor filter based change detection in SAR images by KI thresholding. Optik-International Journal for Light and Electron Optics 130:114–122
Venkateswaran, K., N. Kasthuri, C. Arathy, V. Haran and D. D. Jeni (2013). A survey on unsupervised change detection algorithms. 2013 International conference on circuits, Power and Computing Technologies (ICCPCT), IEEE
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by: H. Babaie
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Khanbani, S., Mohammadzadeh, A. & Janalipour, M. Unsupervised change detection of remotely sensed images from rural areas based on using the hybrid of improved Thresholding techniques and particle swarm optimization. Earth Sci Inform 13, 681–694 (2020). https://doi.org/10.1007/s12145-020-00455-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-020-00455-8