Deep contextual description of superpixels for aerial urban scenes classification

This paper proposes a new approach for contextual feature extraction from superpixels in aerial urban scenes. Our method extracts features with many levels of context from superpixels by exploiting different layers of a pre-trained convolutional neural network. Experimental results show the effectiveness of the proposed approach, which outperforms traditional methods based on handcrafted feature extraction algorithms.

[1]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Andrea Vedaldi,et al.  Objects in Context , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[3]  Thomas Blaschke,et al.  Geographic Object-Based Image Analysis – Towards a new paradigm , 2014, ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing.

[4]  Martin A. Fischler,et al.  The Representation and Matching of Pictorial Structures , 1973, IEEE Transactions on Computers.

[5]  Gregory Shakhnarovich,et al.  Feedforward semantic segmentation with zoom-out features , 2014, CVPR.

[6]  Sylvie Philipp-Foliguet,et al.  Improving texture description in remote sensing image multi-scale classification tasks by using visual words , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[7]  Serge J. Belongie,et al.  Context based object categorization: A critical survey , 2010, Comput. Vis. Image Underst..

[8]  Thomas M. Strat,et al.  Context-Based Vision: Recognizing Objects Using Information from Both 2D and 3D Imagery , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Jitendra Malik,et al.  Context by region ancestry , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[10]  Jefersson Alex dos Santos,et al.  Towards better exploiting convolutional neural networks for remote sensing scene classification , 2016, Pattern Recognit..

[11]  Jefersson Alex dos Santos,et al.  Contextual superpixel description for remote sensing image classification , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[12]  Graeme G. Wilkinson,et al.  Results and implications of a study of fifteen years of satellite image classification experiments , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Tsuhan Chen,et al.  Exploring Tiny Images: The Roles of Appearance and Contextual Information for Machine and Human Object Recognition , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Siome Goldenstein,et al.  Image classification based on bag of visual graphs , 2013, 2013 IEEE International Conference on Image Processing.

[15]  Peng Gong,et al.  Mapping Urban Land Use by Using Landsat Images and Open Social Data , 2016, Remote. Sens..

[16]  Michele Volpi,et al.  Dense Semantic Labeling of Subdecimeter Resolution Images With Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Antonio Torralba,et al.  Contextual Priming for Object Detection , 2003, International Journal of Computer Vision.

[18]  Arnaldo de Albuquerque Araújo,et al.  Star: A Contextual Description of Superpixels for Remote Sensing Image Classification , 2016, CIARP.

[19]  S. Süsstrunk,et al.  SLIC Superpixels ? , 2010 .

[20]  Antonio Criminisi,et al.  TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context , 2007, International Journal of Computer Vision.

[21]  Sanja Fidler,et al.  The Role of Context for Object Detection and Semantic Segmentation in the Wild , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.