全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于纹理基元与颜色的室外自然场景分类

Keywords: 纹理基元,自然场景分类,混合模型,KD-tree

Full-Text   Cite this paper   Add to My Lib

Abstract:

为解决算法生成纹理地图时时间耗费量大的问题,提出采用KD-tree算法对数据结构进行划分、减小KNN算法搜索复杂度、提高搜索速度的方法.针对基于纹理基元的分类算法无法准确检测室外某些纹理相似性较高的自然场景,提出加入颜色特征、设置相应权值构建混合模型的方法.实验结果表明,基于KD-tree的KNN算法可缩短分类时间、满足实时性的要求,基于纹理基元与颜色的分类算法在室外自然场景中能够获得较高的分类精确度.

References

[1]  Hui K, Audibert J, Ponce J. Vanishing point detection for road detection //Proceedings of Conference on Computer Vision and Pattern Recognition. Paris: Ecole Normale Super Press, 2009:96-103.
[2]  Moisés A M, Lourdes M G, Ricardo S O, et al. Color-image classification using MRF\'s for an outdoor mobile robot //Proceedings of Conference on the 8th World Multiconference on Systemics, Cybernetics and Informatics. Florida, USA: IIISCI Press, 2004:165-171.
[3]  Jansen P, Van M W, Van H J, et al. Colour based off-road environment and terrain type classification //Proceedings of Conference on Intelligent Transportation Systems. Amsterdam, Netherlands: Tryllian Solutions Press, 2005:216-221.
[4]  Varma M, Zisserman A. A statistical approach to texture classification from single images [J]. International Journal of Computer Vision, 2005,62(1-2):61-81.
[5]  Felzenszwalb P F, Huttenlocher D P. Efficient graph-based image segmentation[J]. International Journal of Computer Vision, 2004,59(2):167-181.
[6]  Geusebroek J, Smeulders A W, Van W J. Fast anisotropic gauss filtering[J]. IEEE Transactions on Image Processing, 2003,12(8):938-943.
[7]  Cover T M, Hart P E. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, IT-13(1):21-27.
[8]  Verbeek J, Triggs B. Region classification with Markov field aspect models //Proceedings of Conference on Computer Vision and Pattern Recognition. Montbonnot, France: INRIA Press, 2007:1-8.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133