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.
Highlights
The monitoring of land cover requires that changes be distinguished from stable land cover classes over time
We present a novel hidden Markov model (HMM)-based continuous change detection and classification (HCCDC) algorithm that can provide detailed “from–to” change information
The hidden semi-Markov model (HSMM) are used for land cover classification after change to provide “from–to”
Summary
The monitoring of land cover requires that changes be distinguished from stable land cover classes over time. Autocorrelation techniques [4], segmentation algorithms [5], predictive approaches [6], statistical parameter change approaches [7], harmonic analysis [8], and subsequence clustering [9] are some of the time series change detection algorithms that have been successfully applied in the remote sensing field. Most of these methods aim at identifying changes from stable time series. A study on continuous change detection and classification (CCDC) was presented in [6], which used all available
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
