Abstract

Due to the high temporal repetition rates, median/low spatial resolution remote sensing images are the main data source of change detection (CD). It is worth noting that they contain a large number of mixed pixels, which makes adequately capturing the details in the resulting thematic map challenging. The spectral unmixing (SU) method is a potential solution to this problem, as it decomposes mixed pixels into a set of fractions of the land covers. However, there are accumulated errors in the fractional difference images, which lead to a poor change detection results. Meanwhile, the spectra variation of the endmember and the heterogeneity of the land cover materials cannot be fully considered in the traditional framework. In order to solve this problem, a novel change detection approach with image stacking and dividing based on spectral unmixing while considering the variability of endmembers (CD_SDSUVE) was proposed in this paper. Firstly, the remote sensing images at different times were stacked into a unified framework. After that, several patch images were produced by dividing the stacked images so that the similar endmembers according to each land cover can be completely extracted and compared. Finally, the multiple endmember spectral mixture analysis (MESMA) is performed, and the abundant images were combined to produce the entire change detection thematic map. This proposed algorithm was implemented and compared to four relevant state-of-the-art methods on three experimental data, whereby the results confirmed that it effectively improved the accuracy. In the simulated data, the overall accuracy (OA) and Kappa coefficient values were 99.61% and 0.99. In the two real data, the maximum of OA were acquired with 93.26% and 80.85%, which gained 14.88% and 13.42% over the worst results at most. Meanwhile, the Kappa coefficient value was consistent with the OA.

Highlights

  • As is known, change detection (CD) is the main application of remote sensing technology, which is the process of analyzing changes of surface features with multitemporal remote sensing imageries in the same area [1]

  • The variability of the base endmembers according to each land cover can be taken into full consideration. In view of this way of thinking, a novel change detection approach with image stacking and dividing based on spectral unmixing while considering the variability of endmembers (CD_SDSUVE) is proposed in this paper

  • Two pairs of multitemporal images were chosen to test the CD methods, including CD based on the post-classification (CD_PC), CD based on spectral performance of the algorithm in real scenarios

Read more

Summary

Introduction

Change detection (CD) is the main application of remote sensing technology, which is the process of analyzing changes of surface features with multitemporal remote sensing imageries in the same area [1]. The abundances of each land-cover are estimated, and the differential proportions are compared to obtain the final change map In this way, the change detection process is performed from the “full-pixel level” to the “sub-pixel level”, which can be called. Some researchers have proposed that the spectral signatures of the multitemporal images were considered to be a stacked feature space, and changed and unchanged classes can be analyzed in a uniformed unsupervised framework dealing with the issue [24,25]. The variability of the base endmembers according to each land cover can be taken into full consideration In view of this way of thinking, a novel change detection approach with image stacking and dividing based on spectral unmixing while considering the variability of endmembers (CD_SDSUVE) is proposed in this paper.

Relevant Background
Stacking and Patch Generation of theThe
The Initial Endmember Group Construction for Small Patch Image
Construction of theare
Multiple Endmember Spectral Mixture Analysis
Experiments
Simulated Multitemporal Image Data
Real Multitemporal Image
The number of the minimum
Real Multitemporal Image Data 2
10. Multitemporal
Computational
In the
Discussion and Conclusions
Full Text
Published version (Free)

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