Please wait a minute...
img

官方微信

遥感技术与应用  2005, Vol. 20 Issue (5): 483-488    DOI: 10.11873/j.issn.1004-0323.2005.5.483
技术研究与图像处理     
高分辨率遥感图像隧道入口自动识别方法的研究
薛东升, 尹东
中国科学技术大学电子工程和信息科学系,安徽 合肥 230027
A Study of Tunnel Entries Automatic Recognition from Super Resolution Remote Sensing Images
XUE Dong-sheng, YIN Dong
Department of Electronic Engineering and Information Science, University of Science & Technology of China, Hefei 230027, China
 全文: PDF 
摘要: 提出了一种在高分辨率可见光图像中山体隧道入口的自动识别方法。该方法首先从遥感图像中屏蔽掉绝大部分无关的地物细节,提取出潜在的道路目标区域,然后利用动态规划的搜索策略从道路种子点进行搜索,其中道路种子点由改进的随机Hough变换(GRHT)自动确立,最后利用搜索费用函数和山体的纹理特征对隧道入口进行定位。整个算法可以进行自动识别。实验中选取QuickBird图像为例,结果证明该算法具有很好的识别效果。
关键词: 随机Hough变换 种子点 动态规划 纹理特征 共生矩阵    
Abstract: In this paper, a technique to tunnel entries automatic recognition from super resolution remote sensing images is presented. First, it screen a majority of irrelevant objects such as mountain and woods in remote sensing images, and extract the area which include potential road information from remote sensing images. Because these task are for reducing the area which include road seed and shortening the time for searching road, so it is based on simple and quick threshold segmentation. In the potential road area, it automatically find road seed in terms of improved randomized Hough transformation (GRHT), which is superior to traditionary randomized Hough transformation on detecting speed and detecting precision, then automatically search road from road seed point according to tactic of dynamic programming. Lastly, it find entries of tunnels through estimating the function of expense that has be used to search road from road seed and texture feature of mountain. The function of expense and the texture feature of mountain are key of find entries of tunnels, in this paper, they all are based on classical technique. Every step of the algorithm can automatically run. The experiment has based on QuickBird images and the result of experiment shown that this technique is primarily effective and that result of detecting is satisfiable.
Key words: Randomized hough transformation    Seed point    Dynamic programming    Texture feature    Co-occurrence matrix
收稿日期: 2005-03-01 出版日期: 2011-11-17
:  TP 75  
基金资助: 北京市自然科学基金项目“岩石剪切红外成像与首都圈地震短临遥感预报基础研究”。
作者简介: 薛东升(1975-),男,硕士研究生,主要从事图像处理与分析、模式识别方面的研究。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
薛东升
尹东

引用本文:

薛东升, 尹东. 高分辨率遥感图像隧道入口自动识别方法的研究[J]. 遥感技术与应用, 2005, 20(5): 483-488.

Xue Dong-Sheng , YIN Dong. A Study of Tunnel Entries Automatic Recognition from Super Resolution Remote Sensing Images. Remote Sensing Technology and Application, 2005, 20(5): 483-488.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2005.5.483        http://www.rsta.ac.cn/CN/Y2005/V20/I5/483

〔1〕 Steger C, Mayer H, Radig B. The Role of Grouping for Road Extraction〔A〕. Automatic Extraction of Manmade Objects from Aerial and Space Images(2)〔C〕. Basel: BirkHaeuser Verlag, 1997.245~255. 〔2〕 Gunst M E dc. Automatic Extraction of Roads from Spot Image〔R〕. Graduation Report PB91~188110(U. S.), 1990. 〔3〕 Vergnet R L, Saint-Mare P, Jezouin J L. A Generic Bridge Finder〔A〕. Automated CAD-Based Vision〔C〕. Workshop on Directions,1991. 〔4〕 Chen Haixin, Shen Zhenkang, Shen Jianjun. Method for Se arching Bridge in IR Images〔J〕. IEEA Aerospace and Electr onics Systems Magazine,1998,13(7):21~24. 〔5〕 Michel A. Airport Detection Using A Simple Model, Multi-source Images and Altimetric Information〔J〕. SPIE, 1998, (2315): 604~615. 〔6〕 Shaban M A, Dikshit O. Improvement of Classification in Urban Areas by the Use of Textural Features. The Case study of Lucknow City,Uttar Pradesh〔J〕.International Journal of Remote Sensing, 2001, 22:565~593. 〔7〕 Gastellu-Etchegorry J P. An Assessment of SPOT XS and Landsat MSS Data for Digital Classification of Near-urban Land Cover〔J〕. International Journal of Remote Sensing, 1990,11:225~235. 〔8〕 王厚大,梁栋,杨恒新.自动阈值选取的两种算法〔J〕.南京邮电学院学报,2002,22(4):86~88. 〔9〕 Leavers V F. Which Hough transform?〔J〕. Image Unders tanding, 1993,58(2):250~264. 〔10〕 Illingworth J, Kittler J. A Survey of the Hough Transform〔J〕. Image Understanding, 1988, 44(1): 87~116. 〔11〕 Yu-Tai Ching. Detecting Line Segments in A Image-a New Implementation for Hough Transform〔J〕. Pattern Recognition Letters, 2001,22(3~4):421~429. 〔12〕 Kesidis A L, Papamarkos N. On the Gray-scale Inverse Hough Transform〔J〕. Image and Vision Computin, 2000, 18(8):607~618. 〔13〕 Xu Lei, Oja Erkki. Randomized Hough Transform (RHT): Basic Mechanism, Algorithms, and Computational Comple xities〔J〕. Image Understanding, 1993,57(2):131~154. 〔14〕 Heikki Kalviainen, Petri Hirvonen, Xu Lei, et al. Probabil istic and Non-probabilistic Hough Transform〔J〕. Image and Vision Computing, 1995, 13(4): 239~252. 〔15〕 Heikki Kalviainen Petri Hirvonen. Anextension to the Rando mized Hough Transform Exploiting Connectivity〔J〕. Pattern Recognition Letters, 1997, 19(1):77~85. 〔16〕 唐珉,李军,胡占义.随机Hough变换与Tabu搜索算法在基元提取中的比较〔J〕.计算机学报,1999,22(5):56~65. 〔17〕 Merlet N, Zerubia J. New Prospects in Line Detection by Dynamic Programming〔J〕. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(4):426~431. 〔18〕 Gruen A, Li H. Road Extraction from Aerial and Satellite Images by Dynamic Programming〔J〕. Journal of Photogram metry and Remote Sensing, 1995,50(4):11~20. 〔19〕 Milan Sonka, Vaclav Hlavac, Roger Blyle.图像处理、分析与机器视觉(第2版)〔M〕.北京:人民邮电出版社,2003. 〔20〕 Laws K L. Textured Image Segmentation〔D〕.Los Angeles. University of Southern California, 1980. 〔21〕 Haralick R M. Statistical and Structural Approaches to Tex ture〔J〕. Proceeding of the IEEE, 1979, 67:786~804.
[1] 杨朦朦,汪汇兵,欧阳斯达,范奎奎,戚凯丽. 基于双树复小波分解的BP神经网络遥感影像分类[J]. 遥感技术与应用, 2018, 33(2): 313-320.
[2] 翟玮,沈焕锋,黄春林. 结合PolSAR影像纹理特征分析提取倒塌建筑物[J]. 遥感技术与应用, 2016, 31(5): 975-982.
[3] 邓滢,张红,王超,刘萌. 结合纹理与极化分解的面向对象极化SAR水体提取方法[J]. 遥感技术与应用, 2016, 31(4): 714-723.
[4] 桂容,徐新,董浩,宋超. 全极化SAR影像城区建筑密度分析[J]. 遥感技术与应用, 2016, 31(2): 267-274.
[5] 赵玉,王红,张珍珍. 基于遥感光谱和空间变量随机森林的黄河三角洲刺槐林健康等级分类[J]. 遥感技术与应用, 2016, 31(2): 359-367.
[6] 廖小超,胡坚,李传荣,吴克,薛博,李群智. 基于迭代式动态规划的影像密集匹配[J]. 遥感技术与应用, 2015, 30(1): 92-98.
[7] 邹亚荣,黄磊,张治平. 结合纹理特征的SVM岛礁信息提取分析[J]. 遥感技术与应用, 2014, 29(5): 812-817.
[8] 刘萌萌,刘亚岚,孙国庆,彭立. 结合纹理特征的SVM样本分层土地覆盖分类[J]. 遥感技术与应用, 2014, 29(2): 315-323.
[9] 孙建国,姜烨,颜长珍. 利用专题指数改善沙漠化土地遥感分类精度[J]. 遥感技术与应用, 2013, 28(4): 655-658.
[10] 郝利娜,张志,张翠芬. 山东省寿光市滨海地区盐田信息提取方法研究[J]. 遥感技术与应用, 2013, 28(3): 526-532.
[11] 徐 佳,陈媛媛,黄其欢,何秀凤. 综合灰度与纹理特征的高分辨率星载SAR图像建筑区提取方法研究[J]. 遥感技术与应用, 2012, 27(5): 692-698.
[12] 刘友山,吕成文,祝凤霞,高 超. 基于PCA和多尺度纹理特征提取的高分辨率遥感影像分类[J]. 遥感技术与应用, 2012, 27(5): 706-711.
[13] 邵晓敏, 刘勇. 基于纹理的乌兰布和沙漠地区植被信息提取[J]. 遥感技术与应用, 2010, 25(5): 687-694.
[14] 傅文杰, 林明森. 利用SVM与灰度共生矩阵从QuickBird 影像中提取枇杷信息[J]. 遥感技术与应用, 2010, 25(5): 695-699.
[15] 刘廷祥,黄丽梅,鲍文东. 基于CBERS-02B和SPOT-5全色波段的图像融合纹理信息评价研究[J]. 遥感技术与应用, 2009, 24(1): 103-108.