Continuous Change Detection and Classification Using Hidden Markov Model: A Case Study for Monitoring Urban Encroachment onto Farmland in Beijing
Open Access
- 13 November 2015
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 7 (11) , 15318-15339
Abstract
In this paper, we propose a novel method to continuously monitor land cover change using satellite image time series, which can extract comprehensive change information including change time, location, and “from-to” information. This method is based on a hidden Markov model (HMM) trained for each land cover class. Assuming a pixel’s initial class has been obtained, likelihoods of the corresponding model are calculated on incoming time series extracted with a temporal sliding window. By observing the likelihood change over the windows, land cover change can be precisely detected from the dramatic drop of likelihood. The established HMMs are then used for identifying the land cover class after the change. As a case study, the proposed method is applied to monitoring urban encroachment onto farmland in Beijing using 10-year MODIS time series from 2001 to 2010. The performance is evaluated on a validation set for different model structures and thresholds. Compared with other change detection methods, the proposed method shows superior change detection accuracy. In addition, it is also more computationally efficient.Keywords
Funding Information
- Open Project Program of the State Key Laboratory of Remote Sensing Science in China (OFSLRSS201406)
- National Natural Science Foundation of China (41301393, 41401474)
This publication has 34 references indexed in Scilit:
- NDVI-based land-cover change detection using harmonic analysisInternational Journal of Remote Sensing, 2015
- Detecting changes in vegetation trends using time series segmentationRemote Sensing of Environment, 2015
- Continuous change detection and classification of land cover using all available Landsat dataRemote Sensing of Environment, 2014
- Segmentation uncertainty in multiple change-point modelsStatistics and Computing, 2013
- Using Page's Cumulative Sum Test on MODIS Time Series to Detect Land-Cover ChangesIEEE Geoscience and Remote Sensing Letters, 2012
- Land Cover Change Detection Using Autocorrelation Analysis on MODIS Time-Series Data: Detection of New Human Settlements in the Gauteng Province of South AfricaIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012
- Unsupervised Land Cover Change Detection: Meaningful Sequential Time Series AnalysisIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2010
- A change detection method for sequential patternsDecision Support Systems, 2009
- Review ArticleDigital change detection methods in ecosystem monitoring: a reviewInternational Journal of Remote Sensing, 2004
- Efficient anomaly detection by modeling privilege flows using hidden Markov modelComputers & Security, 2003