使用形态Haar小波法检测目标感兴趣区域

宋燕星; 袁峰; 丁振良; 孙春凤

doi:null

您当前的位置：

首页 >

文章列表页 >

使用形态Haar小波法检测目标感兴趣区域

信息科学 | 更新时间：2020-08-12

- 使用形态Haar小波法检测目标感兴趣区域
- Detection of region-of-interest by morphological Haar wavelet method
- 光学精密工程 2009年17卷第7期页码：1752-1758
- 作者机构：
  
  哈尔滨工业大学自动化测试与控制系,黑龙江哈尔滨,150001
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.50275040)()
- DOI：
  中图分类号： TP391.4
- 收稿日期：2008-08-18，
  
  修回日期：2008-10-09，
  
  网络出版日期：2009-07-25，
  
  纸质出版日期：2009-07-25
- 稿件说明：
移动端阅览
宋燕星, 袁峰, 丁振良, 孙春凤. 使用形态Haar小波法检测目标感兴趣区域[J]. 光学精密工程, 2009,17(7): 1752-1758

SONG Yan-xing, YUAN Feng, DING Zhen-liang, SUN Chun-feng. Detection of region-of-interest by morphological Haar wavelet method[J]. Editorial Office of Optics and Precision Engineering, 2009,17(7): 1752-1758
宋燕星, 袁峰, 丁振良, 孙春凤. 使用形态Haar小波法检测目标感兴趣区域[J]. 光学精密工程, 2009,17(7): 1752-1758 DOI：

SONG Yan-xing, YUAN Feng, DING Zhen-liang, SUN Chun-feng. Detection of region-of-interest by morphological Haar wavelet method[J]. Editorial Office of Optics and Precision Engineering, 2009,17(7): 1752-1758 DOI：

摘要

对图像进行面向自动目标识别(Auto Target Recognition

ATR)的压缩其关键是快速而准确地检测到目标感兴趣区域ROI(Region-of-interest)

并将其与背景区域分别进行不同比特率的压缩。本文将形态Haar小波法与数学形态学方法相结合来实现目标ROI的检测

设计了新的目标ROI检测算子。对采集图像进行二维形态Haar小波分解

结合目标ROI检测要求的特点

仅在尺度信号域内应用设计的目标ROI检测算子

最终完成目标ROI的检测。仿真实验表明

该方法对目标ROI的检测率最高可达到1.000 0

而最低虚警率仅为0.001 2;对含像素级别为10

的图像

所需运算时间仅为10

-1

s。与传统方法相比

本文算法对目标ROI检测效果好

运算简单

节省了运算时间和硬件资源。

Abstract

The Auto Target Recognition (ATR) has been used to solve the problem that the huge data flows provided by a high speed image acquistion system are not easily transferred and stored

in which the key is how to find the Region-of-interest (ROI) of a target quickly and exactly. To detect the ROI of the target

a morphology Haar wavelet method and a mathematic morphology are combined to use in the ROI detection and a new target ROI detection operator is designed. An image is decomposed with morphology Haar wavelet

then the new ROI detection operator is used in the field of scale signal decomposed by morphology Haar wavelet to find the ROI of target. The simulation results indicate that the highest detection ratio of the ROI can reach 1.000 0 and the lowest false alarm ratio of the ROI only is 0.001 2. Moreover

the time consumption is only 10

-1

s for a image with a pixel level of 10

. In comparison with traditional algorithmns

this method can find the ROI of the target effectively and can save the time consumption and hardware resource.

关键词

Keywords

references

汪洋.面向自动目标识别的图像压缩关键技术研究 . 长沙:国防科学技术大学,2006. WANG Y. The research on key techniques of ATR-Directed image compression .Changsha:Graduate National University of Defense Technology,2006.(in Chinese)[2] 同武勤,凌永顺,黄超超,等. 数学形态学和小波变换的红外图像处理方法[J]. 光学精密工程,2007,15(1):139-143. TONG W Q, LING Y SH, HUANG CH CH, et al.. Processing method of IR image based on mathematical morphology and wavelet transform[J]. Opt. Precision Eng., 2007,15(1): 139-143.(in Chinese)[3] 王江安,肖伟岸. 基于双波段的目标红外辐射特征分析[J]. 激光与红外,2001,31(8):351-353. WANG J A, XIAO W A. Analysis of infrared radiation feature of targets based on double bands[J]. Laser and Infrared, 2001, 31(8):351-353.(in Chinese)[4] 隋玉萍,何昕,魏仲慧. ROI的海洋监视卫星遥感图像压缩算法[J]. 光学精密工程,2008,16(7):1325-1326. SUI Y P, HE X, WEI ZH H. A compression algorithm of remote sensing image based on ROI for ocean surveillance satellite[J]. Opt. Precision Eng., 2008,16(7):1325-1326.(in Chinese)[5] JIANG M Y, YUAN D F. A multi-grade mean morphologic edge detection . 2002 6th International Conference on Signal Processing, Beijing, China: ICSP, 2002:1079-1082.[6] HENK J A M H. Nonlinear multiresolution signal decomposition schemes-part II: morphological wavelets[J]. IEEE Transactions on Image Processing, 2000,11(9):1901-1904. [7] 林玉池,崔彦平,黄银国. 复杂背景下边缘提取与目标识别方法研究[J]. 光学精密工程,2006,14(3):510-511. LIN Y CH, CUI Y P, HUANG Y G. Study on edge detection and target recognition in complex background[J]. Opt.Precision Eng., 2006, 14(3):510-511.(in Chinese)

浏览量

461

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据