首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于多视点多尺度的轮廓畸变图像仿真方法
引用本文:张天序,冯军,翁文杰,赵广州.基于多视点多尺度的轮廓畸变图像仿真方法[J].华中科技大学学报(自然科学版),2007,35(4):1-3.
作者姓名:张天序  冯军  翁文杰  赵广州
作者单位:华中科技大学,图像识别与人工智能研究所;图像信息处理与智能控制教育部重点实验室,湖北,武汉,430074
基金项目:国家自然科学基金 , 国家预研基金
摘    要:针对目标成像中出现的尺度变化和轮廓畸变等问题,提出了飞机目标的多视点多尺度轮廓畸变图像仿真方法.采用MultiGen建立目标的精确三维模型,先通过高斯球仿真其不同视点图像,然后由多视点原始级别图像轮廓通过高斯金字塔进行模糊降分辨率处理,最后对不同尺度图像轮廓叠加不同强度的高斯噪声.仿真试验结果表明,该方法生成的图像能逼真地模拟实际图像,可作为ATR系统性能测试所需实验数据.

关 键 词:图像仿真  轮廓畸变  多尺度  高斯金字塔  高斯白噪声  多视点  多尺度  图像轮廓  畸变图像  仿真方法  simulation  image  noise  实验数据  系统性能测试  实际图像  模拟  结果  仿真试验  高斯噪声  不同强度  叠加  处理  分辨率  模糊
文章编号:1671-4512(2007)04-0001-03
修稿时间:03 20 2006 12:00AM

Multiaspect and multi-scale-based contour noise image simulation
Zhang Tianxu,Feng Jun,Weng Wenjie,Zhao Guangzhou.Multiaspect and multi-scale-based contour noise image simulation[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,2007,35(4):1-3.
Authors:Zhang Tianxu  Feng Jun  Weng Wenjie  Zhao Guangzhou
Institution:Institute for Pattern Recognition and Artificial Intelligence; Image Information Processing and Intelligence Control Lab. of Ministry of Education, Huazhong University of Science and Technology, Wuhan 430074, China
Abstract:A novel method for simulating contour noise images through multi-aspect and multi-scale is proposed to diminish the changing of scales and contour distortion in targets.Three-dimension models of targets were constructed by using MultiGen and the aspect graphs were simulated through Gaussian viewsphere.The contour images of original aspect graphs were blurred to reduce the resolution of images.Gaussian white noise of different intensity was added to the contours of different multi-scale images.The results indicate that the images simulated by this method can be used to test ATR systems.
Keywords:image simulation  contour distortion  multi-scale  Gaussian pyramid  Gaussian white noise
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号