采用局部分形的高效图像分割方法在红外云图处理中的应用

刘洋; 田小建; 王晴; 高博

doi:10.3788/OPE.20111906.1367

您当前的位置：

首页 >

文章列表页 >

采用局部分形的高效图像分割方法在红外云图处理中的应用

信息科学 | 更新时间：2020-08-12

- 采用局部分形的高效图像分割方法在红外云图处理中的应用
- Application of efficient image segmentation method based on local fractal in the infrared cloud image processing
- 光学精密工程 2011年19卷第6期页码：1367-1374
- 作者机构：
  
  1. 吉林大学通信工程学院,吉林长春,130022
  2. 吉林大学电子科学与工程学院,吉林长春,130012
- 作者简介：
- 基金信息：
  
  国家863高技术研究发展计划资助项目(No.2008AA8080502)()
- DOI：10.3788/OPE.20111906.1367
  中图分类号： TP391.41
- 收稿日期：2010-04-30，
  
  修回日期：2010-11-04，
  
  网络出版日期：2011-06-25，
  
  纸质出版日期：2011-06-25
- 稿件说明：
移动端阅览
刘洋, 田小建, 王晴, 高博. 采用局部分形的高效图像分割方法在红外云图处理中的应用[J]. 光学精密工程, 2011,19(6): 1367-1374

LIU Yang, TIAN Xiao-jian, WANG Qing, GAO Bo. Application of efficient image segmentation method based on local fractal in the infrared cloud image processing[J]. Editorial Office of Optics and Precision Engineering, 2011,19(6): 1367-1374
刘洋, 田小建, 王晴, 高博. 采用局部分形的高效图像分割方法在红外云图处理中的应用[J]. 光学精密工程, 2011,19(6): 1367-1374 DOI： 10.3788/OPE.20111906.1367.

LIU Yang, TIAN Xiao-jian, WANG Qing, GAO Bo. Application of efficient image segmentation method based on local fractal in the infrared cloud image processing[J]. Editorial Office of Optics and Precision Engineering, 2011,19(6): 1367-1374 DOI： 10.3788/OPE.20111906.1367.

摘要

针对已有的基于分形维数的图像分割算法难以快速计算一个小区域的分形维数

计算复杂

效率低的问题

通过分析云的分形特征

提出一种采用局部分形维数的方法对红外云彩图像进行分割。首先

提出了一种高效算法来计算一段区间内的分形维数

使用树状数组作为数据结构

利用已经计算出来的信息

在

(log

)的时间内得到结果;然后

通过计算云图每个水平线的分形维数

将分形维数超过一定阈值的区域确定为云彩区域;最后

将每条水平线的高维数区间结合在一起得出整个分割结果。实验结果表明

该方法解决了传统的分形维数算法在大量计算维数时算法复杂度高、计算时间长的问题

对于640 pixel480 pixel的大型图像计算时间

0.1 s;同时该算法能够有效地将云彩和其他人工遮挡物以及背景光线变化和局部噪声区分开

取得满意的处理效果。

Abstract

An efficient image segmentation method based on local fractal dimension was proposed by analyzing the fractal characteristics of clouds to solve the problems existed in image segmentation algorithms in high complexity

low efficiency and difficult to calculate the fractal dimension of a small area quickly. Firstly

an efficient algorithm to calculate the fractal dimension of a small area was proposed. By utilizing a tree array as data structure and taking the advantage of calculated information

the result could be obtained in the time of

(log

). Then

through calculating the fractal dimension of each horizontal line in the infrared cloud image

the fractal dimension that exceeds a certain threshold area was identified as the cloud area. Finally

the segmentation result was gotten through combining all the high dimensions of each horizontal line. The result demonstrates that this method solves the problems of complexity and inefficiency of the traditional methods based on fractal dimension

and the computing time remains less than 0.1 s for a large image of 640 pixel480 pixel. The algorithm can effectively separate the clouds from the other artificial objects

changed background light

and the local noise to obtain good segmentation results.

关键词

Keywords

references

孙学金,高太长,翟东力,等. 基于非制冷红外焦平面阵列的全天空红外测云系统[J]. 红外与激光工程,2008,37(5):763-764. SUN X J, GAO T CH, CUI D L, et al.. Whole sky infrared cloud measuring system based on the uncooled infrared focal plane array [J].Infrared and Laser Engineering, 2008,37(5):763-764. (in Chinese)[2] 王昊京,王建立,王鸣浩,等. 大视场云层分布定位的光电测量系统[J]. 光学精密工程,2010,5(5):1234-1241. WANG H J, WANG J L, WANG M H, et al.. Large field photoelectric measuring system for cloud position determination [J]. Opt. Precision Eng., 2010,5(5):1234-1241. (in Chinese)[3] ANAT L, YAIRWEISS. Learning to combine bottom-up and top-down segmentation [J]. International Journal of Computer Vision, 2009,81(1):105-118.[4] 吴家伟,武春风,庹文波. 红外图像实时显示增强系统设计[J]. 光学精密工程,2009,10(3):52-55. WU J W, WU CH F,TUO W B. Design of real-time infrared image enhancing system [J]. Opt. Precision Eng., 2009,10(3):52-55.(in Chinese)[5] 丁金伟,张葆,李永刚,等. 气象测云红外成像系统的设计与分析[J]. 光学精密工程,2008,16(12):2431-2434. DING J W,ZHANG B,LI Y G,et al.. Design and analysis of infrared imaging system for cloud meteorological observation[J]. Opt. Precision Eng., 2008,16(12):2431-2434.(in Chinese)[6] OTSU N. A threshold selection method from gray level histogram [J]. IEEE Trans. on Syst. Man, Cybern, 1979,9(1):62-66.[7] 陈永强,陆安生,胡汉平. 基于分形的图像分析方法综述[J]. 计算机工程与设计,2005,26(7):1781-1783. CHEN Y Q, LU A SH, HU H P. Summary of image analysis method based on fractal[J]. Computer Engineering and Design,2005,26(7):1781-1783.(in Chinese)[8] 张红,陆谊. 基于局部模糊分形维度的图像边缘检测算法[J]. 微电子学与计算机,2005,22(7):171-177. ZHANG H,LU Y. Image edge detection algorithm based on local fuzzy fractal dimension [J]. Microelectronics & Computer, 2005,22(7):171-177. (in Chinese)[9] 张永亮,卢焕章. 基于图像局部熵的红外图像分割方法[J]. 红外技术,2006,28(11):656-660. ZHANG Y L, LU H ZH. Infrared Image Segmentation Based on Local Entropy of Image [J]. Infrared Technology, 2006,28(11):656-660. (in Chinese)[10] 张薇薇,唐英干. 基于最大熵和粒子群优化的红外图像分割[J]. 电子器件,2007,30(5):1736-1740. ZHANG W W, TANG Y G.Maximum fuzzy entropy and particle swarm optimization (PSO) based infrared image segmentation[J]. Chinese Journal of Electron Decices,2007,30(5):1736-1740.(in Chinese)[11] 夏德深,金盛,王健. 基于分数维与灰度梯度共生矩阵的气象云图识别分数维对纹理复杂度和粗糙度的描述[J]. 南京理工大学学报,1999,23(3):278-281. XIA D SH,JIN SH,WANG J. Fractal dimension and GGCM based meteorology cloud pictures recognition description of texture complexity and roughness by fractal dimension[J]. Journal of Nanjing University of Science and Technology, 1999,23(3):278-281. (in Chinese)[12] CHAUDHURI B, SARKAR N. Texture segmentation using fractal dimension[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995,17(1):72-77.[13] 周培德.计算几何:算法设计与分析[M]. 北京:清华大学出版社,2005. ZHOU P D. Computational geometry:Algorithm Design and Analysis[M].Beijing:Tsinghua Press,2005.(in Chinese)[14] GOUTSIAS J. Non linear multiresolution signal decomposition schemes part Ⅰ: morphological pyramids [J]. IEEE Trans on Image Processing, 2000,9(11):1862-1876.

浏览量

235

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合条形注意力机制的电芯极片计算机断层图像分割

增强型金枪鱼群优化指数熵的砂粒显微图像分割

语义流引导采样结合注意力机制的脑肿瘤图像分割

混沌SSA优化多重熵阈值的骨料图像自动分割

融合分形几何特征Resnet遥感图像建筑物分割