Parsing Natural Scenes Based on Hierarchical Region Merge
CSTR:
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [8]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    The goal of scene understanding is to recognize what objects in the image and where the objects are located. Hierarchical structure is commonly found in the natural scene images. This structure not only can help us to identity the objects but also how the small units interact to form the whole objects. Our algorithm is based on the level structure. We merge the neighboring segments continuously until they combined into the whole object. The result is a forest which contains several trees, one tree commonly represents one object. We introduce a machine learning model to describe the merge process, greedy inference to compute the best merge trees, and the max margin to learn the parameters. We cluster the segments features to initialize the parameter. The experiment result could be accepted.

    Reference
    1 Cordelia S. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. The Conference on Computer Vision and Pattern Recognition, New York, 2006.
    2 Socher R, Fei-Fei L. Connecting modalities: Semisupervised segmentation and annotation of images using unaligned text corpora. The Conference on Computer Vision and Pattern Recognition, San Francisco, 2010.
    3 Rabinovich A, Vedaldi A, Galleguillos C, eds. Objects in context. Conference on Computer Vision. Rio de Janeiro. 2007.
    4 Shotton J, Winn J, Rother C, eds. Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. The European Conference on Computer Vision, Graz, 2006.
    5 Socher R, Lin CC, Ng AY, eds. Parsing natural scenes and natural language with recurisve neural networks. The International Conference on Machine Learning, Bellevue, 2011
    6 Liu B, Fan HQ. Semantic labeling of indoor scenes from RGB-D images with discriminative learning. The international Conference on Machine Vision, London, 2013.
    7 Gupta A, Davis L. Beyond nouns: Exploiting prepositions and comparative adjectives for learning visual classifiers. The European Conference on Computer Vision, Marseille, 2008.
    8 Gould S, Fulton R, Koller D. Decomposing a scene into geometric and semantically consistent regions. The International Conference on Computer Vision, Kyoto, 2009.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

孙丽坤,刘波.基于分层区域合并的自然场景理解.计算机系统应用,2014,23(11):116-121

Copy
Share
Article Metrics
  • Abstract:1551
  • PDF: 2909
  • HTML: 0
  • Cited by: 0
History
  • Received:March 19,2014
  • Revised:April 14,2014
  • Online: November 20,2014
Article QR Code
You are the first990817Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063