Abstract
Nowadays remote sensing is an important technique for observing Earth surface applied to different areas such as, land use, urban planning, remote monitoring, real time deformation of the soil that can be associated with earthquakes or landslides, the variations in thickness of the glaciers, the measurement of volume changes in the case of volcanic eruptions, deforestation, etc. To follow the evolution of these phenomena and to predict their future states, many approaches have been proposed. However, these approaches do not respond completely to the specialists who process yet more commonly the data extracted from the images in their studies to predict the future. In this paper, we propose an innovative methodology based on hidden Markov models (HMM). Our approach exploits temporal series of satellite images in order to predict spatio-temporal phenomena. It uses HMM for representing and making prediction concerning any objects in a satellite image. The first step builds a set of feature vectors gathering the available information. The next step uses a Baum-Welch learning algorithm on these vectors for detecting state changes. Finally, the system interprets these changes to make predictions. The performance of our approach is evaluated by tests of space-time interpretation of events conducted over two study sites, using different time series of SPOT images and application to the change in vegetation with LANDSAT images.
Highlights
During the last decade there have been many improvements and significant technical breakthroughs in the field of remote sensing to improve the quality of available observations [1]
We propose an innovative methodology based on hidden Markov models (HMM)
The performance of our approach is evaluated by tests of space-time interpretation of events conducted over two study sites, using different time series of SPOT images and application to the change in vegetation with LANDSAT images
Summary
During the last decade there have been many improvements and significant technical breakthroughs in the field of remote sensing to improve the quality of available observations [1]. This analysis is dedicated to automatically label spatiotemporal structures and discover new events To achieve this goal, we exploit two areas: the extraction of information from satellite images and stochastic analyses. The second section deals with our contributions for the exploitation of time series of satellite images, in cooperation with the techniques for extracting information for the spatiotemporal analysis based on a HMM. In the field of automatic information extraction, Lacoste [16] presented a method for unsupervised extraction of line networks, such as roads or water systems, from satellite images This system modeled the line network in the image by a Markov process. HMM is a statistical tool allowing complex stochastic phenomena to be modeled They are used in a lot of areas including speech recognition and synthesis, biology, scheduling, information retrieval, recognition image, temporal series prediction
Sign-in/Register to view highlights & summary 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.
