Color-Boosted Saliency-Guided Rotation Invariant Bag of Visual Words Representation with Parameter Transfer for Cross-Domain Scene-Level Classification

Scene classification on remote sensing imagery is usually based on supervised learning but collecting labelled data in remote sensing domains is expensive and time-consuming. Bag of Visual Words (BOVW) achieves great success in scene classification but there exist problems in domain adaptation tasks, such as the influence of background and the rotation transformation on BOVW representation, and the transfer of SVM parameters from the source domain to the target domain, which may lead to decreased cross-domain scene classification performance. In order to solve the three problems, Color-boosted saliency-guided rotation invariant bag of visual words representation with parameter transfer is proposed for cross-domain scene classification. The global contrast-based salient region detection method is combined with the color-boosted method to increase the accuracy of detected salient regions and reduce the effect of background information on the BOVW representation. The rotation invariant BOVW representation is also proposed by sorting the BOVW representation in each patch in order to decrease the effect of rotation transformation. The several best configurations in the source domain are also applied to the target domain so as to reduce the distribution bias between scenes in the source and target domain. These configurations deliver the top classification performance the optimal parameter in the target domain. The experimental results on two benchmark datasets confirm that the proposed method outperforms most previous methods in scene classification when instances in the target domain are limited. It is also proved that color boosted global contrast-based salient region detection (CBGCSRD) method, rotation invariant BOVW representation, and transfer of SVM parameters from the source to the target domain are all effective in improving the classification accuracy with 2.5%, 3.3%, and 3.1%. These three contributions may increase about 7.5% classification accuracy in total.

[1]  Carlos Soares,et al.  A Meta-Learning Method to Select the Kernel Width in Support Vector Regression , 2004, Machine Learning.

[2]  Qihao Weng,et al.  Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends , 2012 .

[3]  Lorenzo Bruzzone,et al.  Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances , 2016, IEEE Geoscience and Remote Sensing Magazine.

[4]  Huanxin Zou,et al.  Transfer Sparse Subspace Analysis for Unsupervised Cross-View Scene Model Adaptation , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[5]  Cécile Barat,et al.  Spatial histograms of soft pairwise similar patches to improve the bag-of-visual-words model , 2015, Comput. Vis. Image Underst..

[6]  Liangpei Zhang,et al.  Scene Classification Based on the Multifeature Fusion Probabilistic Topic Model for High Spatial Resolution Remote Sensing Imagery , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Lorenzo Bruzzone,et al.  A Multilevel Context-Based System for Classification of Very High Spatial Resolution Images , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Gui-Song Xia,et al.  AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[10]  Lei Guo,et al.  Remote Sensing Image Scene Classification Using Bag of Convolutional Features , 2017, IEEE Geoscience and Remote Sensing Letters.

[11]  Jie Wang,et al.  Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery , 2014, Remote. Sens..

[12]  Imdad Ali Rizvi,et al.  Object-Based Image Analysis of High-Resolution Satellite Images Using Modified Cloud Basis Function Neural Network and Probabilistic Relaxation Labeling Process , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Mihai Datcu,et al.  Bridging the Semantic Gap for Satellite Image Annotation and Automatic Mapping Applications , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  Melba M. Crawford,et al.  Domain Adaptation With Preservation of Manifold Geometry for Hyperspectral Image Classification , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[15]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[16]  Jonathan Cheung-Wai Chan,et al.  Improved Classification of VHR Images of Urban Areas Using Directional Morphological Profiles , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Lorenzo Bruzzone,et al.  Semisupervised Classification of Hyperspectral Images by SVMs Optimized in the Primal , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Saurabh Prasad,et al.  Decision Fusion With Confidence-Based Weight Assignment for Hyperspectral Target Recognition , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Steven A. Shafer,et al.  Using color to separate reflection components , 1985 .

[20]  Lorenzo Bruzzone,et al.  Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation Strategy , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Nanning Zheng,et al.  Learning to Detect a Salient Object , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Andreas Dengel,et al.  Meta-learning for evolutionary parameter optimization of classifiers , 2012, Machine Learning.

[23]  Gustau Camps-Valls,et al.  Kernel Manifold Alignment for Domain Adaptation , 2015, PloS one.

[24]  Yuan Yan Tang,et al.  Dictionary Learning-Based Feature-Level Domain Adaptation for Cross-Scene Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Byoung Chul Ko,et al.  Object-of-interest image segmentation based on human attention and semantic region clustering. , 2006, Journal of the Optical Society of America. A, Optics, image science, and vision.

[26]  Melba M. Crawford,et al.  Adaptive Classification for Hyperspectral Image Data Using Manifold Regularization Kernel Machines , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Lorenzo Bruzzone,et al.  A Novel Approach to the Selection of Spatially Invariant Features for the Classification of Hyperspectral Images With Improved Generalization Capability , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[29]  Robert Marti,et al.  Which is the best way to organize/classify images by content? , 2007, Image Vis. Comput..

[30]  Xue Li,et al.  Iterative Reweighting Heterogeneous Transfer Learning Framework for Supervised Remote Sensing Image Classification , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[31]  P Reinagel,et al.  Natural scene statistics at the centre of gaze. , 1999, Network.

[32]  Shawki Areibi,et al.  Domain Adaptation Using Representation Learning for the Classification of Remote Sensing Images , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[33]  Hongxun Yao,et al.  Deep Feature Fusion for VHR Remote Sensing Scene Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Claudio Persello,et al.  Interactive Domain Adaptation for the Classification of Remote Sensing Images Using Active Learning , 2013, IEEE Geoscience and Remote Sensing Letters.

[35]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[36]  Gui-Song Xia,et al.  Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery , 2015, Remote. Sens..

[37]  Li Yan,et al.  Improved Class-Specific Codebook with Two-Step Classification for Scene-Level Classification of High Resolution Remote Sensing Images , 2017, Remote. Sens..

[38]  Huanxin Zou,et al.  Unsupervised Cross-View Semantic Transfer for Remote Sensing Image Classification , 2016, IEEE Geoscience and Remote Sensing Letters.

[39]  Kate Smith-Miles,et al.  A meta-learning approach to automatic kernel selection for support vector machines , 2006, Neurocomputing.

[40]  Francesca Bovolo,et al.  A Novel Domain Adaptation Bayesian Classifier for Updating Land-Cover Maps With Class Differences in Source and Target Domains , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Lorenzo Bruzzone,et al.  Active and Semisupervised Learning for the Classification of Remote Sensing Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[42]  Ping Tang,et al.  Land-Use Scene Classification Using a Concentric Circle-Structured Multiscale Bag-of-Visual-Words Model , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[43]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[44]  Andrew Zisserman,et al.  Scene Classification Using a Hybrid Generative/Discriminative Approach , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[45]  Mikhail F. Kanevski,et al.  SVM-Based Boosting of Active Learning Strategies for Efficient Domain Adaptation , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[46]  Lihi Zelnik-Manor,et al.  Context-Aware Saliency Detection , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[47]  King Ngi Ngan,et al.  Unsupervised extraction of visual attention objects in color images , 2006, IEEE Transactions on Circuits and Systems for Video Technology.

[48]  Emma Izquierdo-Verdiguier,et al.  Encoding Invariances in Remote Sensing Image Classification With SVM , 2013, IEEE Geoscience and Remote Sensing Letters.

[49]  Lorenzo Bruzzone,et al.  Kernel-Based Domain-Invariant Feature Selection in Hyperspectral Images for Transfer Learning , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[50]  Chao Yang,et al.  A Multiscale Deeply Described Correlatons-Based Model for Land-Use Scene Classification , 2017, Remote. Sens..

[51]  Joost van de Weijer,et al.  Boosting color saliency in image feature detection , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[52]  Lorenzo Bruzzone,et al.  Active Learning for Domain Adaptation in the Supervised Classification of Remote Sensing Images , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[53]  Xia Li,et al.  Domain adaptation for land use classification: A spatio-temporal knowledge reusing method , 2014 .

[54]  Melba M. Crawford,et al.  Spectral and Spatial Proximity-Based Manifold Alignment for Multitemporal Hyperspectral Image Classification , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[55]  Melba M. Crawford,et al.  Active Learning: Any Value for Classification of Remotely Sensed Data? , 2013, Proceedings of the IEEE.

[56]  Hanyun Wang,et al.  Learn Multiple-Kernel SVMs for Domain Adaptation in Hyperspectral Data , 2013, IEEE Geoscience and Remote Sensing Letters.