A SIMPLE AND EFFICIENT CROSS-SENSOR RETRIEVAL METHOD FOR RETRIEVING STEREO IMAGES BY MULTISPECTRAL IMAGE

Abstract. Some users need to utilize a query multispectral image to quickly locate desired panchromatic stereo images from massive remotely sensed images. A stereo pair or triplet is different with a multispectral image in terms of the viewing number, viewing angle, band, radiometric resolution, spatial resolution, and ability to obtain height information. To perform the cross-sensor retrieval, the orthoimage or digital surface model (DSM) is usually produced from stereo images in a long time, drastically reducing the retrieval efficiency. To achieve a high efficiency, our study explores the potential of the raw viewing images of stereo images to be immediately used in the retrieval. We proposed a simple and efficient cross-sensor retrieval method by doing similarity matching between the query multispectral image and the raw viewing images of stereo images, using probability histograms separately produced from them. Experimental results show that our method outperformed two methods based on the orthoimage in terms of both the retrieval efficiency and precision. Our method handily deals with differences between stereo images and multispectral images, and efficiently achieves the high-accuracy cross-sensor retrieval with no need to produce the orthoimage or DSM.

[1]  Rolando Quintero,et al.  Semantic assessment of similarity between raster elevation datasets , 2011 .

[2]  Chao Yang,et al.  Multi-Task Joint Sparse and Low-Rank Representation for the Scene Classification of High-Resolution Remote Sensing Image , 2016, Remote. Sens..

[3]  Jianya Gong,et al.  Development of a Framework for Stereo Image Retrieval With Both Height and Planar Features , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[4]  Naoto Yokoya,et al.  IMG2DSM: Height Simulation From Single Imagery Using Conditional Generative Adversarial Net , 2018, IEEE Geoscience and Remote Sensing Letters.

[5]  Thierry Toutin,et al.  Review of developments in geometric modelling for high resolution satellite pushbroom sensors , 2012 .

[6]  Lorenzo Bruzzone,et al.  Hashing-Based Scalable Remote Sensing Image Search and Retrieval in Large Archives , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Manuel A. Aguilar,et al.  Generation and Quality Assessment of Stereo-Extracted DSM From GeoEye-1 and WorldView-2 Imagery , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Yongjun Zhang,et al.  Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion , 2016, Remote. Sens..

[9]  Amel Benazza-Benyahia,et al.  Disparity based stereo image retrieval through univariate and bivariate models , 2015, Signal Process. Image Commun..

[10]  Manuel A. Aguilar,et al.  Geometric accuracy assessment of the orthorectification process from very high resolution satellite imagery for Common Agricultural Policy purposes , 2008 .

[11]  Yang Yang,et al.  OBSIR: Object-based stereo image retrieval , 2014, 2014 IEEE International Conference on Multimedia and Expo (ICME).

[12]  Medeni Soysal,et al.  Performance Analysis of State-of-the-Art Representation Methods for Geographical Image Retrieval and Categorization , 2014, IEEE Geoscience and Remote Sensing Letters.

[13]  Thierry Toutin,et al.  Review article: Geometric processing of remote sensing images: models, algorithms and methods , 2004 .

[14]  Hannes Taubenböck,et al.  Performance Evaluation for 3-D City Model Generation of Six Different DSMs From Air- and Spaceborne Sensors , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[15]  P. Reinartz,et al.  Benchmarking and quality analysis of DEM generated from high and very high resolution optical stereo satellite data , 2010 .

[16]  Jianya Gong,et al.  A New Stereo Pair Disparity Index (SPDI) for Detecting Built-Up Areas from High-Resolution Stereo Imagery , 2017, Remote. Sens..

[17]  Manuel A. Aguilar,et al.  Assessing geometric accuracy of the orthorectification process from GeoEye-1 and WorldView-2 panchromatic images , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[18]  Jinchang Ren,et al.  Generic framework for content-based stereo image/video retrieval , 2011 .

[19]  Jing Luo,et al.  Stereo Image Retrieval Using Height and Planar Visual Word Pairs , 2017, IEEE Geoscience and Remote Sensing Letters.

[20]  Naoto Yokoya,et al.  Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art , 2017, IEEE Geoscience and Remote Sensing Magazine.

[21]  Marco Quartulli,et al.  A review of EO image information mining , 2012, 1203.0747.

[22]  Hao Liu,et al.  A Three-Layered Graph-Based Learning Approach for Remote Sensing Image Retrieval , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Wai Yeung Yan,et al.  Urban land cover classification using airborne LiDAR data: A review , 2015 .

[24]  Feifei Peng,et al.  Content-based search of earth observation data archives using open-access multitemporal land cover and terrain products , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[25]  Hossein Arefi,et al.  Height estimation from single aerial images using a deep convolutional encoder-decoder network , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[26]  Deren Li,et al.  Development of a multi-scale object-based shadow detection method for high spatial resolution image , 2015 .