首页 > 论文 > 光学学报 > 34卷 > s1期(pp:110002--1)

基于多尺度频域分析的遥感图像视觉显著区域检测

Saliency Region Detection of Remote Sensing Image Based on Multi-Scale Frequency Analyses

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

频域分析在遥感图像显著区域检测时可以很好地检测到显著区域的边缘部分,但是,往往在显著区域的内部产生误检测。提出了一种基于图像高频信息多尺度融合的视觉显著区域检测算法,将遥感图像进行多尺度的高斯金字塔分解,对分解后的每一级图像进行傅里叶变换,提取变换后的高频信息进行多尺度融合,获得最终显著图。结合该显著图提取遥感影像视觉显著区域不仅能够有效排除显著区域内部误检测问题,而且获得了更为精确的显著区域细节。此外,该算法较Itti模型具有更低计算复杂度。

Abstract

Frequency domain analysis can well detect the edge of the salient region in the remote sensing imagery detecting. But it may mistakenly regard the inner parts of the saliency region as the background. A new algorithm based on multi-scale fusion techniques of the image high frequency information is proposed. First, the new algorithm creates several spatial scales of remote sensing images by using Gaussian pyramid. Then, for each scale, the new algorithm can get the high frequency information by the Fourier transform. Finally, the new algorithm gets the final saliency map by fusing the high frequency information on one scale. The new algorithm can not only well extract details of the salient region, but also effectively get rid of mistaken detection of the inner parts of the saliency region. Comparing with Itti model, the new algorithm has lower computation complexity.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN919.8

DOI:10.3788/aos201434.s110002

所属栏目:图像处理

基金项目:国家自然科学基金(61071103)、中央高校基本科研业务费专项资金(2012LYB50)

收稿日期:2013-10-23

修改稿日期:2013-12-06

网络出版日期:--

作者单位    点击查看

杨绪业:北京师范大学信息科学与技术学院, 北京 100875
李雪薇:北京师范大学信息科学与技术学院, 北京 100875
张立保:北京师范大学信息科学与技术学院, 北京 100875

联系人作者:杨绪业(yangxuye@sohu.com)

备注:杨绪业(1960—),男,工程师,主要从事遥感图像显著区域检测方面的研究。

【1】Fan Jianchao, Han Min, Wang Jun. Single point iterative weighted fuzzy c-means clustering algorith for remote sensing image segmentation [J]. Pattern Recognition, 2009, 42(11): 2527-2540.

【2】M Bouziani, K Goita, D He. Rule-based classification of a very high resolution image in an urban environment using multispectral segmentation guided by cartographic data [J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(8): 3198-3211.

【3】L Itti, C Koch, E Niebur. A model of saliency-based visual attention for rapid scene analysis [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.

【4】Zhang Peng, Wang Runsheng. An approach to the remote sensing image analysis based on visual attention [J]. 2005, 27(12): 1855-1860.
张鹏, 王润生. 基于视觉注意的遥感图像分析方法 [J]. 电子与信息学报, 2005, 27(12): 1855-1860.

【5】R Palenichka, M Zaremba. Automatic extraction of control points for the registration of optical satellite and LiDAR images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(7): 2864-2879.

【6】D Dai, W Yang. Satellite image classification via two-layer sparse coding with biased image representation [J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(1): 173-176.

【7】Huaizu Jiang, Jingdong Wang, Zejian Yuan, et al.. Salient object detection: a discriminative regional feature integration approach [C]. Computer Vision and Pattern Recognition, 2013. 1-8.

【8】P F Felzenszwalb, D P Huttenlocher. Efficient graph-based image segmentation [J]. International Journal of Computer Vision, 2004, 59(2): 167-181.

【9】Xiaodi Hou, Liqiang Zhang. Saliency detection: a spectral residual approach [C]. Computer Vision and Pattern Recognition, 2007. 1-8.

【10】Radhakrishna Achanta, Sheila Hemami, Francisco Estrada,et al.. Frequency-tuned salient region detection [C]. Computer Vision and Pattern Recognition, 2009. 1597-1604.

【11】Tom Fawcett. An introduction to ROC analysis [J]. Pattern Recognition Letters, 2006, 27(8): 861-874.

【12】R Ma, X Tu, J Ding. To evaluate salience map towards popping out visual objects [J]. Acta Automatica Sinica, 2012, 38(5): 870-876.

引用该论文

Yang Xuye,Li Xuewei,Zhang Libao. Saliency Region Detection of Remote Sensing Image Based on Multi-Scale Frequency Analyses[J]. Acta Optica Sinica, 2014, 34(s1): s110002

杨绪业,李雪薇,张立保. 基于多尺度频域分析的遥感图像视觉显著区域检测[J]. 光学学报, 2014, 34(s1): s110002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF