MULTI-MODAL REMOTE SENSING DATA FUSION FRAMEWORK

Abstract. The inconsistency between the freely available remote sensing datasets and crowd-sourced data from the resolution perspective forms a big challenge in the context of data fusion. In classical classification problems, crowd-sourced data are represented as points that may or not be located within the same pixel. This discrepancy can result in having mixed pixels that could be unjustly classified. Moreover, it leads to failure in retaining sufficient level of details from data inferences. In this paper we propose a method that can preserve detailed inferences from remote sensing datasets accompanied with crowd-sourced data. We show that advanced machine learning techniques can be utilized towards this objective. The proposed method relies on two steps, firstly we enhance the spatial resolution of the satellite image using Convolutional Neural Networks and secondly we fuse the crowd-sourced data with the upscaled version of the satellite image. However, the covered scope in this paper is concerning the first step. Results show that CNN can enhance Landsat 8 scenes resolution visually and quantitatively.

[1]  Steffen Fritz,et al.  Geo-Wiki: An online platform for improving global land cover , 2012, Environ. Model. Softw..

[2]  Hongyi Liu,et al.  A New Pan-Sharpening Method With Deep Neural Networks , 2015, IEEE Geoscience and Remote Sensing Letters.

[3]  J. L. Harris,et al.  Diffraction and Resolving Power , 1964 .

[4]  Hussain Al-Ahmad,et al.  Superresolution algorithm for satellite still images , 2015, 2015 International Conference on Information and Communication Technology Research (ICTRC).

[5]  Moataz Ahmed,et al.  CROWD-2-CLOUD – Remote Sensing Land Cover Verification With Crowd-Sourcing Data , 2015 .

[6]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Peyman Milanfar,et al.  RAISR: Rapid and Accurate Image Super Resolution , 2016, IEEE Transactions on Computational Imaging.

[8]  A simplified training data collection method for sequential remote sensing image classification , 2016, 2016 4th International Workshop on Earth Observation and Remote Sensing Applications (EORSA).

[9]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[10]  Kostas Stamatiou,et al.  Mapping Human Settlements and Population at Country Scale From VHR Images , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[11]  Xiao Xiang Zhu,et al.  Data Fusion and Remote Sensing: An ever-growing relationship , 2016, IEEE Geoscience and Remote Sensing Magazine.

[12]  Aline Roumy,et al.  Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding , 2012, BMVC.

[13]  Ryutaro Tateishi,et al.  A hybrid pansharpening approach and multiscale object-based image analysis for mapping diseased pine and oak trees , 2013 .

[14]  Xiaoou Tang,et al.  Accelerating the Super-Resolution Convolutional Neural Network , 2016, ECCV.

[15]  Umberto Castellani,et al.  On-line Compendium of Computer Vision , 2002 .

[16]  Zhenzhong Chen,et al.  Remote sensing image super-resolution: Challenges and approaches , 2015, 2015 IEEE International Conference on Digital Signal Processing (DSP).

[17]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[18]  Yue Liu,et al.  Remote Sensing Image Super-resolution Based on Sparse Representation , 2018 .

[19]  Kamaldeep Joshi,et al.  PSNR and MSE based investigation of LSB , 2016, 2016 International Conference on Computational Techniques in Information and Communication Technologies (ICCTICT).

[20]  Steffen Fritz,et al.  Building a hybrid land cover map with crowdsourcing and geographically weighted regression , 2015 .

[21]  D. Yeung,et al.  Super-resolution through neighbor embedding , 2004, CVPR 2004.

[22]  Gustavo Camps-Valls,et al.  Machine learning in remote sensing data processing , 2009, 2009 IEEE International Workshop on Machine Learning for Signal Processing.