Abstract

Optical sensor time series images allow one to produce land cover maps at a large scale. The supervised classification algorithms have been shown to be the best to produce maps automatically with good accuracy. The main drawback of these methods is the need for reference data, the collection of which can introduce important production delays. Therefore, the maps are often available too late for some applications. Domain adaptation methods seem to be efficient for using past data for land cover map production. According to this idea, the main goal of this study is to propose several simple past data fusion schemes to override the current land cover map production delays. A single classifier approach and three voting rules are considered to produce maps without reference data of the corresponding period. These four approaches reach an overall accuracy of around 80% with a 17-class nomenclature using Formosat-2 image time series. A study of the impact of the number of past periods used is also done. It shows that the overall accuracy increases with the number of periods used. The proposed methods require at least two or three previous years to be used.

Highlights

  • Land cover maps provide key information in many environmental and scientific applications

  • The baseline configurations are defined by the use of a classifier trained with the image time series of one period, which is applied to the same period or to another period

  • The x-axis is the year of the image time series used for producing the maps, and the y-axis corresponds to Overall Accuracy (OA) values

Read more

Summary

Introduction

Land cover maps provide key information in many environmental and scientific applications. They can be used to monitor deforestation [1] or urban pressure [2] over croplands, for instance. By extension, satellite image time series allow one to produce accurate land cover maps. In the past few years, the number of space-borne optical sensors has increased, making a wealth of useful data available for land use monitoring. The Landsat sensors provide useful data for land cover monitoring, especially Landsat 5 and 8, which are used to produce accurate land cover maps [3]. The Sentinel-2 system (S2), a pair of twin satellites dedicated to continental surface monitoring, is already providing high quality data for land cover maps. The first results obtained by using single date S2 images are promising [4], and by using S2 image time series, the performance should increase

Objectives
Methods
Results
Discussion
Conclusion

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 call

Disclaimer: 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.