A Novel Scene Descriptor and Outdoor Scene Recognition Method

Bag-of-Words representation based on visual words has been approved to be used widely in scene classification. Visual words are usually constructed by using SIFT(Scale Invariant Feature Transform) of patches. Traditional SIFT descriptor is limited in describe the outdoor scene completely and accurately because it does not consider the multi-directional context and global color information of image. In this paper, we propose that a new scene descriptor and classification method based on SIFT(NC-SIFT, Color Multi-Directional Context SIFT) feature descriptor of key word of patches. Firstly, local SIFT combined with the context information is extracted based on image patch, Then, BOW(Bag of Words) is obtained by K-means clustering and histogram statistics and the scene recognition based on SVM classifier using BOW which fuse the global color vector is accomplished respectively.

[1]  Sanja Fidler,et al.  Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Joost van de Weijer,et al.  Harmony potentials for joint classification and segmentation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[4]  David A. Forsyth,et al.  The effects of segmentation and feature choice in a translation model of object recognition , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[5]  Pushmeet Kohli,et al.  Associative hierarchical CRFs for object class image segmentation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[6]  Xin Li,et al.  Multi-level Adaptive Active Learning for Scene Classification , 2014, ECCV.

[7]  Cheng Wang,et al.  Scene Classification with Context Pyramid Features: Scene Classification with Context Pyramid Features , 2010 .

[8]  Antonio Criminisi,et al.  Object Class Segmentation using Random Forests , 2008, BMVC.

[9]  Lu Wang,et al.  Multi-View Reconstruction of Annular Outdoor Scenes from Binocular Video Using Global Relaxation Iteration , 2011, Int. J. Robotics Autom..

[10]  Anil K. Jain,et al.  Image classification for content-based indexing , 2001, IEEE Trans. Image Process..

[11]  Roberto Cipolla,et al.  Semantic texton forests for image categorization and segmentation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Antonio Criminisi,et al.  TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation , 2006, ECCV.

[13]  Jenny Benois-Pineau,et al.  Segmentation-based multi-class semantic object detection , 2012, Multimedia Tools and Applications.

[14]  Pushmeet Kohli,et al.  Associative Hierarchical Random Fields , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Qiu Zheng-ding.  A Novel Visual Words Definition Algorithm of Image Patch Based on Contextual Semantic Information , 2010 .