Abstract
The determination of the optimal change threshold is an essential step for very high-resolution (VHR) remote sensing change detection. Although a number of change threshold selection methods have been developed for various applications, no single method can be suitable for all cases. It is difficult for users to select an applicable change threshold selection method for their own purposes. To address this challenge, eight common-used change threshold selection methods were studied from their pros and cons as well as performance. First, a clear analysis of these eight threshold selection methods was presented from the perspective of their pros and cons. Second, four groups of comparative experiments were conducted using VHR remote sensing images from the perspectives of greyscale histogram distribution, scene complexity, greyscale histogram processing, and runtime, respectively. From the experimental results, it is clear that the Otsu method and the FST method are the highest accuracy method for detecting multi-temporal VHR remote sensing images. Considering the time cost, the FST method outperforms the Otsu method. This study could be helpful for researchers to select appropriate change threshold approach for various change detection applications.
Similar content being viewed by others
References
Abutaleb AS (1989) Automatic thresholding of gray-level pictures using two-dimensional entropy. Comput Vision, Graph Image Process 47:22–32. https://doi.org/10.1016/0734-189X(89)90051-0
Aja-Fernández S, Curiale AH, Vegas-Sánchez-Ferrero G (2015) A local fuzzy thresholding methodology for multiregion image segmentation. Knowl Based Syst 83:1–12. https://doi.org/10.1016/j.knosys.2015.02.029
Akther M, Ahmed MK, Hasan MZ (2013) Detection of vehicle’s number plate at nighttime using Iterative Threshold Segmentation (ITS) algorithm. Int J Image Graph Signal Process 5:62–70. https://doi.org/10.5815/ijigsp.2013.12.09
Awty-Carroll K, Bunting P, Hardy A, Bell G (2019) An evaluation and comparison of four dense time series change detection methods using simulated data. Remote Sens 11:2779–2808. https://doi.org/10.3390/rs11232779
Baby D, Devaraj SJ, Mathew S et al (2020) A performance comparison of supervised and unsupervised image segmentation methods. SN Comput Sci 1:1–6. https://doi.org/10.1007/s42979-020-00136-9
Bovolo F, Marchesi S, Bruzzone L (2012) A framework for automatic and unsupervised detection of multiple changes in multitemporal images. IEEE Trans Geosci Remote Sens 50:2196–2212
Bruzzone L, Member S (2000) Automatic analysis of the difference image for unsupervised change detection. IEEE Trans Geosci Remote Sens 38:1171–1182. https://doi.org/10.1109/36.843009
Bruzzone L, Serpico SB (1997) An iterative technique for the detection of land-cover transitions in multitemporal remote-sensing images. IEEE Trans Geosci Remote Sens 35:858–867. https://doi.org/10.1109/36.602528
Cao L, Shi ZK, Cheng EKW (2002) Fast automatic multilevel thresholding method. Electron Lett 38:868–870. https://doi.org/10.1049/el:20020594
Chuang KS, Jan ML, Wu J et al (2005) A maximum likelihood expectation maximization algorithm with thresholding. Comput Med Imaging Graph 29:571–578. https://doi.org/10.1016/j.compmedimag.2005.04.003
Cong-shan GAO, Hong Z, Chao W (2010) SAR change detection based on Generalized Gamma distribution divergence and auto-threshold segmentation. J Remote Sens 14:710–724
Coudray N, Buessler JL, Urban JP (2010) Robust threshold estimation for images with unimodal histograms. Pattern Recognit Lett 31:1010–1019. https://doi.org/10.1016/j.patrec.2009.12.025
De Boer PT, Kroese DP, Mannor S, Rubinstein RY (2005) A tutorial on the cross-entropy method. Ann Oper Res 134:19–67. https://doi.org/10.1007/s10479-005-5724-z
Du P, Wang X, Chen D et al (2020) An improved change detection approach using tri-temporal logic-verified change vector analysis. ISPRS J Photogramm Remote Sens 161:278–293. https://doi.org/10.1016/j.isprsjprs.2020.01.026
Eyupoglu C (2017) Implementation of Bernsen’s Locally Adaptive Binarization Method for Gray Scale Images. J Sci Technol 7:68–72
Fan SKS, Lin Y (2007) A multi-level thresholding approach using a hybrid optimal estimation algorithm. Pattern Recognit Lett 28:662–669. https://doi.org/10.1016/j.patrec.2006.11.005
Fatakdawala H, Xu J, Basavanhally A et al (2010) Expectation-maximization-driven geodesic active contour with overlap resolution (EMaGACOR): Application to lymphocyte segmentation on breast cancer histopathology. IEEE Trans Biomed Eng 57:1676–1689. https://doi.org/10.1109/TBME.2010.2041232
Fung T (1990) An assessment of TM imagery for land-cover change detection. IEEE Trans Geosci Remote Sens 28:681–684. https://doi.org/10.1109/TGRS.1990.572980
Ghaderpour E, Vujadinovic T (2020) Change detection within remotely sensed satellite image time series via spectral Analysis. Remote Sens 12:4001. https://doi.org/10.3390/rs12234001
Ghanbari M, Akbari V (2018) Unsupervised change detection in polarimetric SAR data with the Hotelling-Lawley trace statistic and minimum-error thresholding. IEEE J Sel Top Appl Earth Obs Remote Sens 11:4551–4562. https://doi.org/10.1109/JSTARS.2018.2882412
Hao M, Tan M, Zhang H (2019) A change detection framework by fusing threshold and clustering methods for optical medium resolution remote sensing images. Eur J Remote Sens 52:96–106. https://doi.org/10.1080/22797254.2018.1561156
Hasanlau M, Seydi ST (2018) Sensitivity analysis on performance of different unsupervised threshold selection methods in hyperspectral change detection. 2018 10th IAPR Work Pattern Recognit Remote Sensing, PRRS 2018. https://doi.org/10.1109/PRRS.2018.8486355
Hu Y, Dong Y, Batunacun (2018) An automatic approach for land-change detection and land updates based on integrated NDVI timing analysis and the CVAPS method with GEE support. ISPRS J Photogramm Remote Sens 146:347–359. https://doi.org/10.1016/j.isprsjprs.2018.10.008
Isola P, Xiao J, Parikh D et al (2014) What makes a photograph memorable? IEEE Trans Pattern Anal Mach Intell 36:1469–1482. https://doi.org/10.1109/TPAMI.2013.200
Jawahar CV, Biswas PK, Ray AK (2000) Analysis of fuzzy thresholding schemes. Pattern Recognit 33:1339–1349. https://doi.org/10.1016/S0031-3203(99)00122-3
Jones B (2017) Superpixel-based difference representation learning for change detection in multispectral remote sensing images. IEEE Trans Geosci Remote Sens 55:2658–2673. https://doi.org/10.2307/j.ctt1ffjjf6.16
Kapur JN, Sahoo PK, Wong AKC (1985) A new method for grey-level picture thresholding using the entropy of the histogram. Comput Vision Graph Image Process 29:273–285
Kittler J, Illingworth J, Föglein J (1985) Threshold selection based on a simple image statistic. Comput Vision Graph Image Process 30:125–147. https://doi.org/10.1016/0734-189X(85)90093-3
Lee SU, Yoon Chung S, Park RH (1990) A comparative performance study of several global thresholding techniques for segmentation. Comput Vision Graph Image Process 52:171–190. https://doi.org/10.1016/0734-189X(90)90053-X
Li CH, Leet CK (1993) Minimum cross entropy thresholding. Pattern Recognit 26:617–625
Li CH, Tam PKS (1998) An iterative algorithm for minimum cross entropy thresholding. Pattern Recognit Lett 19:771–776. https://doi.org/10.1016/S0167-8655(98)00057-9
Liew CF, Yairi T (2015) Facial expression recognition and analysis: A comparison study of feature descriptors. IPSJ Trans Comput Vis Appl 7:104–120. https://doi.org/10.2197/ipsjtcva.7.104
Liu H, Yang M, Chen J et al (2018) Line-constrained shape feature for building change detection in VHR remote sensing imagery. ISPRS Int J Geo-Inf 7:410–429. https://doi.org/10.3390/ijgi7100410
Lv ZY, Shi WZ, Zhou XC, Benediktsson JA (2017) Semi-automatic system for land cover change detection using Bi-temporal remote sensing images. Remote Sens 9:1112–1132. https://doi.org/10.3390/rs9111112
Lv ZY, Liu TF, Zhang P et al (2019) Novel adaptive histogram trend similarity approach for land cover change detection by using bitemporal very-high-resolution remote sensing images. IEEE Trans Geosci Remote Sens 57:9554–9574. https://doi.org/10.1109/TGRS.2019.2927659
Mahdianpari M, Salehi B, Mohammadimanesh F et al (2020) Big data for a big country: the first generation of Canadian Wetland Inventory Map at a spatial resolution of 10-m Using Sentinel-1 and Sentinel-2 data on the Google earth engine cloud computing platform. Can J Remote Sens 46:15–33. https://doi.org/10.1080/07038992.2019.1711366
Malila WA (1980) Change vector analysis: an approach for detecting forest changes with landsat. Proc Soc Photo-Optical Instrum Eng 326–336
Mao J, Yao D, Wang C (2013) A novel cross-entropy and entropy measures of IFSs and their applications. Knowl-Based Syst 48:37–45. https://doi.org/10.1016/j.knosys.2013.04.011
Molina I, Martinez E, Arquero A et al (2012) Evaluation of a change detection methodology by means of binary thresholding algorithms and informational fusion processes. Sensors 12:3528–3561. https://doi.org/10.3390/s120303528
Nikhil RP, Sankar KP (1993) A Review on Image Segmentation Techniques. Pattern Recognit 26:1277–1294
Otsu N (1979) Threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern SMC –9:62–66. https://doi.org/10.1109/tsmc.1979.4310076
Pal SK, King RA, Hashim AA (1983) Automatic grey level thresholding through index of fuzziness and entropy. Pattern Recognit Lett 1:141–146. https://doi.org/10.1016/0167-8655(83)90053-3
Pal NR, Bhandari D (1993) Image thresholding: Some new techniques. Sig Process 33:139–158. https://doi.org/10.1016/0165-1684(93)90107-L
Patra S, Ghosh S, Ghosh A (2011) Histogram thresholding for unsupervised change detection of remote sensing images. Int J Remote Sens 32:6071–6089. https://doi.org/10.1080/01431161.2010.507793
Peng J, Mei X, Li W et al (2021) Scene complexity: a new perspective on understanding the scene semantics of remote sensing and designing image-adaptive convolutional neural networks. Remote Sens 13:742. https://doi.org/10.3390/rs13040742
Perez A, Gonzalez RC (1987) An iterative thresholding algorthm for image segmentation. IEEE Trans Pattern Anal Mach Intell 9:742–751. https://doi.org/10.1109/TPAMI.1987.4767981
Ridler TW, Calvard S (1978) Picture thresholding using an iterative slection method. IEEE Trans Syst Man Cybern SMC 8:630–632. https://doi.org/10.1109/tsmc.1978.4310039
Rosin PL (2001) Unimodal thresholding. Pattern Recognit 34:2083–2096. https://doi.org/10.1016/S0031-3203(00)00136-9
Saha S (2009) An analytical study of different document image Binarization methods. IEEE Natl Conf Comput Commun Syst, 71–74
Saha S, Bovolo F, Bruzzone L (2019) Unsupervised deep change vector analysis for multiple-change detection in VHR Images. IEEE Trans Geosci Remote Sens 57:3677–3693. https://doi.org/10.1109/TGRS.2018.2886643
Saha S, Member S, Solano-correa YT et al (2020) Unsupervised deep transfer learning-based change detection for HR multispectral images. IEEE Geosci Remote Sens Lett 99:1–5
Sahoo PK, Soltani S, Wong AKC (1988) A survey of thresholding techniques. Comput Vision Graph Image Process 41:233–260. https://doi.org/10.1016/0734-189X(88)90022-9
Schlüter S, Weller U, Vogel HJ (2010) Segmentation of X-ray microtomography images of soil using gradient masks. Comput Geosci 36:1246–1251. https://doi.org/10.1016/j.cageo.2010.02.007
Sezgin M, Taşaltín R (2000) A new dichotomization technique to multilevel thresholding devoted to inspection applications. Pattern Recognit Lett 21:151–161. https://doi.org/10.1016/S0167-8655(99)00142-7
Singh A (1989) Review Articlel: Digital change detection techniques using remotely-sensed data. Int J Remote Sens 10:989–1003. https://doi.org/10.1080/01431168908903939
Wang D, Guo X, Li S, Xu J (2020) Robust high dimensional expectation maximization algorithm via trimmed hard thresholding. Mach Learn 109:2283–2311. https://doi.org/10.1007/s10994-020-05926-z
Wu C, Zhang L, Zhang L (2016) A scene change detection framework for multi-temporal very high resolution remote sensing images. Sig Process 124:184–197. https://doi.org/10.1016/j.sigpro.2015.09.020
Wu C, Zhang L, Du B (2017) Kernel slow feature analysis for scene change detection. IEEE Trans Geosci Remote Sens 55:2367–2384. https://doi.org/10.1007/springerreference_65703
Xian G, Homer C, Fry J (2009) Updating the 2001 National Land Cover Database land cover classification to 2006 by using Landsat imagery change detection methods. Remote Sens Environ 113:1133–1147. https://doi.org/10.1016/j.rse.2009.02.004
Xiao P, Zhang X, Wang D et al (2016) Change detection of built-up land: A framework of combining pixel-based detection and object-based recognition. ISPRS J Photogramm Remote Sens 119:402–414. https://doi.org/10.1016/j.isprsjprs.2016.07.003
Xing H, Zhu L, Hou D, Zhang T (2021) Integrating change magnitude maps of spectrally enhanced multi-features for land cover change detection. Int J Remote Sens 42:4284–4308. https://doi.org/10.1080/01431161.2021.1892860
Xue JH, Zhang YJ (2012) Ridler and Calvard’s, Kittler and Illingworth’s and Otsu’s methods for image thresholding. Pattern Recognit Lett 33:793–797. https://doi.org/10.1016/j.patrec.2012.01.002
Yampri P, Sotthivirat S, Gansawat D et al (2009) Performance comparison of bone segmentation on dental CT images. IFMBE Proc 23:665–668. https://doi.org/10.1007/978-3-540-92841-6_163
Yang Y, Di Girolamo L, Mazzoni D (2007) Selection of the automated thresholding algorithm for the Multi-angle Imaging SpectroRadiometer Radiometric Camera-by-Camera Cloud Mask over land. Remote Sens Environ 107:159–171. https://doi.org/10.1016/j.rse.2006.05.020
Yang G, Li HC, Yang W et al (2019) Variational Bayesian change detection of remote sensing images based on spatially variant gaussian mixture model and separability criterion. IEEE J Sel Top Appl Earth Obs Remote Sens 12:849–861. https://doi.org/10.1109/JSTARS.2019.2896233
Yen JC, Chang FJ, Chang S (1995) A new criterion for automatic multilevel thresholding. IEEE Trans Image Process 4:370–378. https://doi.org/10.1109/83.366472
Zhang G, Yao T, Chen W et al (2019) Regional differences of lake evolution across China during 1960s–2015 and its natural and anthropogenic causes. Remote Sens Environ 221:386–404. https://doi.org/10.1016/j.rse.2018.11.038
Zhuang H, Fan H, Deng K, Yu Y (2018) An improved neighborhood-based ratio approach for change detection in SAR images. Eur J Remote Sens 51:723–738. https://doi.org/10.1080/22797254.2018.1482523
Zhang Y, Zhao H (2020) Land–use and land-cover change detection using dynamic time warping–based time series clustering method. Can J Remote Sens 46:67–83. https://doi.org/10.1080/07038992.2020.1740083
Acknowledgements
This paper is jointly funded by the National Natural Science Foundation of China (41801308 and 41930107); Open Fund of State Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University (20S01); Doctoral Research Fund of Shandong Jianzhu University (XNBS1804), Key Laboratory of Land Satellite Remote Sensing Application Centre, Ministry of Natural Resources of the People’s Republic of China (KLSMNR-202105), and Science and Technology Support Program for Youth Innovation in Colleges and Universities of Shandong Province (2019KJG005). The authors would like to thank the editor and four anonymous reviewers for their valuable comments and suggestions.
Author information
Authors and Affiliations
Corresponding authors
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
Xing, H., Zhu, L., Chen, B. et al. A comparative study of threshold selection methods for change detection from very high-resolution remote sensing images. Earth Sci Inform 15, 369–381 (2022). https://doi.org/10.1007/s12145-021-00734-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-021-00734-y