首页 | 本学科首页   官方微博 | 高级检索  
     

基于全变分的全向图像稀疏重构算法
引用本文:娄静涛,李永乐,谭树人,王炜,张茂军.基于全变分的全向图像稀疏重构算法[J].电子学报,2014,42(2):243-249.
作者姓名:娄静涛  李永乐  谭树人  王炜  张茂军
作者单位:国防科技大学信息系统与管理学院, 湖南长沙 410073
基金项目:国家自然科学基金(No.61275016,No.61271438)
摘    要:折反射全向成像由于曲面镜的反射作用,导致全向图像存在严重变形,传统的梯度计算方法在全向图像中不能很好地符合折反射成像的特点.为了从压缩采样数据快速有效地重构全向图像,提出了一种结合全向图像特征的全变分模型——全向全变分,并在基于TV范数进行全向图像重构时,采用全向全变分作为目标函数,进行模型的求解.实验结果验证了本文算法的有效性和可行性,其重构结果的主客观效果明显优于传统TV模型.

关 键 词:折反射全向成像  压缩感知  图像重构  TV范数  
收稿时间:2013-03-11

Sparse Reconstruction for Omnidirectional Image Based on Total Variation
LOU Jing-tao,LI Yong-le,TAN Shu-ren,WANG Wei,ZHANG Mao-jun.Sparse Reconstruction for Omnidirectional Image Based on Total Variation[J].Acta Electronica Sinica,2014,42(2):243-249.
Authors:LOU Jing-tao  LI Yong-le  TAN Shu-ren  WANG Wei  ZHANG Mao-jun
Affiliation:College of Information System and Management, National University of Defense Technology, Changsha, Hunan 410073, China
Abstract:Because of the distortions produced by the reflection of a mirror,catadioptric omnidirectional images cannot be processed similarly to classical perspective images.In this paper,we propose to define a new model named omnidirectional total variation (Omni-TV),which reflects the omnidirectional image structure features.In order to reconstruct the images from compressive samples,the Omni-TV is used as the subject function during the image reconstruction.The simulation results show that the omnidirectional images could be reconstructed effectively and accurately.Comparing with classical TV minimization model,the images,which are recovered based on Omni-TV model,can provide higher quality both in subjective evaluation and objective evaluation.
Keywords:catadioptric omnidirectional imaging  compressed sensing  image reconstruction  TV norm  
本文献已被 CNKI 等数据库收录!
点击此处可从《电子学报》浏览原始摘要信息
点击此处可从《电子学报》下载全文
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