CHANGE DETECTION WITH MULTI-SOURCE DEFECTIVE REMOTE SENSING IMAGES BASED ON EVIDENTIAL FUSION

Abstract. Remote sensing images with clouds, shadows or stripes are usually considered as defective data which limit their application for change detection. This paper proposes a method to fuse a series of defective images as evidences for change detection. In the proposed method, post-classification comparison process is firstly performed on multi-source defective images. Then, the classification results of all the images, together with their corresponding confusion matrixes are used to calculate the Basic Belief Assignment (BBA) of each pixel. Further, based on the principle of Dempster-Shafer evidence theory, a BBA redistribution process is introduced to deal with the defective parts of multi-source data. At last, evidential fusion and decision making rules are applied on the pixel level, and the final map of change detection can be derived. The proposed method can finish change detection with data fusion and image completion in one integrated process, which makes use of the complementary and redundant information from the input images. The method is applied to a case study of landslide barrier lake formed in Aug. 3rd, 2014, with a series of multispectral images from different sensors of GF-1 satellite. Result shows that the proposed method can not only complete the defective parts of the input images, but also provide better change detection accuracy than post-classification comparison method with single pair of pre- and post-change images. Subsequent analysis indicates that high conflict degree between evidences is the main source of errors in the result. Finally, some possible reasons that result in evidence conflict on the pixel level are analysed.

[1]  Quan Pan,et al.  Change Detection in Heterogeneous Remote Sensing Images Based on Multidimensional Evidential Reasoning , 2014, IEEE Geoscience and Remote Sensing Letters.

[2]  R. Lunetta,et al.  Land-cover characterization and change detection using multitemporal MODIS NDVI data , 2005, International Workshop on the Analysis of Multi-Temporal Remote Sensing Images, 2005..

[3]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[4]  Chao Zeng,et al.  Recovering missing pixels for Landsat ETM + SLC-off imagery using multi-temporal regression analysis and a regularization method , 2013 .

[5]  Josef Cihlar,et al.  Detection and removal of cloud contamination from AVHRR images , 1994, IEEE Trans. Geosci. Remote. Sens..

[6]  Mingjun Song,et al.  A KNOWLEDGE-BASED APPROACH FOR REDUCING CLOUD AND SHADOW , 2002 .

[7]  J. Nichol,et al.  Satellite remote sensing for detailed landslide inventories using change detection and image fusion , 2005 .

[8]  Michael Schmidt,et al.  Geostatistical interpolation of SLC-off Landsat ETM+ images , 2009 .

[9]  Isabelle Bloch,et al.  Introduction of neighborhood information in evidence theory and application to data fusion of radar and optical images with partial cloud cover , 1998, Pattern Recognit..

[10]  S. L. Hégarat-Mascle,et al.  Automatic change detection by evidential fusion of change indices , 2004 .

[11]  D. Roy,et al.  Multi-temporal MODIS-Landsat data fusion for relative radiometric normalization, gap filling, and prediction of Landsat data , 2008 .

[12]  Marguerite Madden,et al.  Closest Spectral Fit for Removing Clouds and Cloud Shadows , 2009 .

[13]  Feng Gao,et al.  A Modified Neighborhood Similar Pixel Interpolator Approach for Removing Thick Clouds in Landsat Images , 2012, IEEE Geoscience and Remote Sensing Letters.

[14]  Ram M. Narayanan,et al.  A shape-based approach to change detection of lakes using time series remote sensing images , 2003, IEEE Trans. Geosci. Remote. Sens..

[15]  Feng Chen,et al.  Exploitation of CBERS-02B as auxiliary data in recovering the Landsat7 ETM+ SLC-off image , 2010, 2010 18th International Conference on Geoinformatics.

[16]  Yi Luo,et al.  Developing clear-sky, cloud and cloud shadow mask for producing clear-sky composites at 250-meter spatial resolution for the seven MODIS land bands over Canada and North America , 2008 .

[17]  R. Devi,et al.  CHANGE DETECTION TECHNIQUES - A SUR VEY , 2015 .

[18]  S. Corgne,et al.  Performance of change detection using remotely sensed data and evidential fusion: comparison of three cases of application , 2006 .

[19]  Qian Du,et al.  Multi-Modal Change Detection, Application to the Detection of Flooded Areas: Outcome of the 2009–2010 Data Fusion Contest , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[20]  Peijun Du,et al.  Information fusion techniques for change detection from multi-temporal remote sensing images , 2013, Inf. Fusion.

[21]  Jean-Yves Tourneret,et al.  Fusion of high resolution optical and SAR images with vector data bases for change detection , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[22]  Jianping Guo,et al.  Change detection of the Tangjiashan barrier lake based on multi-source remote sensing data , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[23]  Jin Chen,et al.  A new geostatistical approach for filling gaps in Landsat ETM+ SLC-off images , 2012 .

[24]  Feng Gao,et al.  A simple and effective method for filling gaps in Landsat ETM+ SLC-off images , 2011 .

[25]  Zied Elouedi,et al.  Discountings of a Belief Function Using a Confusion Matrix , 2010, 2010 22nd IEEE International Conference on Tools with Artificial Intelligence.

[26]  Pol Coppin,et al.  Review ArticleDigital change detection methods in ecosystem monitoring: a review , 2004 .

[27]  Isabelle Bloch,et al.  Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing , 1997, IEEE Trans. Geosci. Remote. Sens..