Gradual land cover change detection based on multitemporal fraction images

• Published in: Pattern recognition Vol. 45; no. 8; pp. 2927 - 2937
• Main Authors: Zanotta, Daniel C., Haertel, Victor
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01-08-2012; Elsevier
• Subjects: Applied sciences; Change detection; Continuums; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Information, signal and communications theory; Land cover; Linear mixture model; Methodology; Pattern recognition; Pixels; Remote sensing; Signal and communications theory; Signal, noise; Spatial context; Telecommunications and information theory; Linear mixture model; Change detection; Remote sensing; Spatial context; Signal mixing; Signal processing; Mixture theory; Implementation; Linear model; Multiple image; Non contact measurement
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2012.02.004

This study proposes a new approach to change detection in remote sensing multi-temporal image data. Rather than allocating pixels to one of two disjoint classes (change, no-change) which is the approach most commonly found in the literature, we propose in this study to define change in terms of degrees of membership to the class change. The methodology aims to model images depicting the natural environment more realistically, taking into account that changes tend to occur in a continuum rather than being sharply distinguished. To this end, a sub-pixel approach is implemented to help detect degrees of change in every pixel. Three experiments employing the proposed approach using synthetic and real image data are reported and their results discussed.
► Change systems are more effectively understood by means of continuous information. ► We investigate a model for detecting degrees of membership to changes in multitemporal remote sensing image data sets. ► Change maps produced showed large degrees of intermediate changes.