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...

基于视觉统计概率模型的目标定位

DOI: 10.11834/jig.20070727

Keywords: 视觉概率模型,区域分割,边缘检测,尺度

Full-Text   Cite this paper   Add to My Lib

Abstract:

复杂场景中的目标定位是目标检测和识别的重要过程,为了更好地对复杂场景中的目标进行定位,基于视觉的概率模型,提出了一种目标定位的新方法。区别于一般的区域分割和边缘检测方法,该方法首先通过建立平滑、纹理、阴影和杂乱等4种不同类型区域特性的概率模型,对场景中的前景和背景进行了概率分析;然后结合不同的尺度大小,标记出图像中显著度较高的目标区域;最后经过边缘轮廓的概率建模和连通性分析来提取完整目标区域。实验结果表明,该方法具有较好的鲁棒性和通用性,不仅符合人的视觉注意特性,而且具有一定的抗背景干扰能力。

References

[1]  Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[A].In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C],Hawaii,USA,2001:511~518.
[2]  Schneiderman H,Kanade T.Object detection using the statistics of parts[J].International Journal of Computer Vision,2004,56(3):151~177.
[3]  Ye Qi-xiang,Gao Wen,Wang Wei-qiang,et al.A colour image segmentation algorithm using colour and spatial information[J].Journal of Software,2004,15(4) ; 522~530.[叶奇祥,高文,王伟强等.一种基于图像颜色空间信息的彩色图像分割算法[J].软件学报,2004,15(4):522~530.
[4]  Borenstein E,Ullman S.Class specific top down-segmentation[A].In:Proceedings of the European Conference on Computer Vision[C],Copenhagen,Denmark,2001:110~122.
[5]  Itti L,Koch C,Niebur E.A model of saliency-based visual attention for rapid scene analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(11):1254~1259.
[6]  Ullman S,Vidal-Naquet M,Sali E.Visual features of intermediate complexity and their use in classification[J].Nature Neuroscience,2002,5(7):682~687.
[7]  Tu Z W,Zhu S C.Image segmentation by data-driven Markov Chain Monte Carlo[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):657~673.
[8]  Wang Hai-chuan,Zhang Li-ming.A novel fast training algorithm for Adaboost[J].Journal of Fudan University(Natural Science),2004,43(1):27~33.[王海川,张立明.一种新的Adaboost快速训练算法[J].复旦学报(自然科学版),2004,43(1):27~33.]
[9]  Shi J,Malik J.Normalized cuts and image segmentation[A].In:Proceedings of the IEEE Conference on Computer Vision and Pattern Reeognition[C],San Juan,Puerto Rico,1997:731~737.
[10]  Sun Y R,Fisher R.Object-based visual attention for computer vision[J].Journal of Artificial Intelligence,2003,146(1):77~123.
[11]  Gao Wen,Chen Xi-ling.Computer vision[M].Beijing; Tsinghua University Publisher Press,1999.[高文,陈熙霖著.计算机视觉[M].北京:清华大学出版社,1999.]
[12]  Zhu S C.Statistical modeling and conceptualization of visual patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(6):1~22.
[13]  Berkeley image base[EB/OL].http;//www.cs.berkeley.edu/projects/ vision/ grouping/ segbench/

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133