采用多方向插值融合的快速铁路货运图像修复

doi:10.3969/j.issn.0255-8297.2014.02.012

应用科学学报 ›› 2014, Vol. 32 ›› Issue (2): 191-198.doi: 10.3969/j.issn.0255-8297.2014.02.012

采用多方向插值融合的快速铁路货运图像修复

金星1，俞大海1,2，韩建枫3，李晖晖1，韩军伟1

1. 西北工业大学自动化学院，西安710072
2. 天津光电高斯通信工程技术股份有限公司，天津300211
3. 天津商业大学信息工程学院，天津300134

收稿日期:2012-12-13 修回日期:2013-07-04 出版日期:2014-03-25 发布日期:2013-07-04
作者简介:俞大海，博士，高工，研究方向：图像处理技术及模式识别，E-mail: dahai28@yahoo.com；韩军伟，教授，博导，研究方向：计算机视觉、模式识别、多媒体信息处理等，E-mail: jhan@nwpu.edu.cn
基金资助:
国家自然科学基金(No.61005018)；国家科技企业创新基金(No.09C26211200180)；天津市软件专项基金(No.2010[01-3])资助

Fast Inpainting of Railway Freights Images Based on Multiple Direction Interpolation

JIN Xing1, YU Da-hai1,2, HAN Jian-feng3, LI Hui-hui1, HAN Jun-wei1

1. School of Automation, Northwestern Polytechnic University, Xi’an 710072, China
2. Tianjin Optical Electrical Gaosi Communication Engineering Technology Co. Ltd., Tianjin 300211, China
3. School of Information Engineering, Tianjin University of Commerce, Tianjin 300134, China

Received:2012-12-13 Revised:2013-07-04 Online:2014-03-25 Published:2013-07-04

摘要/Abstract

摘要： 由于非目标前景的出现，高分辨率的线阵相机采集到的图像常因表面原始信息被遮挡而产生数据缺失.针对单张图像提出一种基于多方向插值融合的图像修复方法，并成功应用于铁路装载状态检测系统中，实现了监控图像中高压线的去除. 在获得图像中待修复区域的位置后，将待修复区域分为平滑区和边缘区. 对平滑区域，
在3个不同角度方向上选择梯度变化最小方向上的邻域像素，用三次插值算法对待修复像素进行估计；对边缘区域，结合3个方向的三次插值结果进行数据融合，设计融合规则以获得更准确的插值结果. 以HSI色彩空间代替RGB色彩空间对彩色图像进行修复. 与BSCB、FMM等算法进行对比，表明所提出的算法能获得更好的修复效果，并能有效修复色彩复杂的图像，同时还降低了计算复杂度，提高了运行效率，使处理时间达到毫秒级，可满足实时处理要求.

关键词: 图像修复, 快速修复, 数据融合, 插值, 铁路装载状态检测系统

Abstract: High resolution line-scan cameras produce images with missing information due to occlusion caused by foreign objects. In this paper, we propose a framework based on multiple direction interpolation for single image digital restoration to remove high tension wire (HTW) from images for railway loaded condition inspection (LCI) applications. The known region to be reconstructed is automatically segmented into smooth and edge sub-regions. The smooth regions are filled-in with bilinear interpolation based on the information in the neighborhood, which is the minimum among the gradient values in three directions. For the edge regions,the fill-in result is optimized using a data fusion method based on the information in three directions with bi-cubic interpolation. Inpainting is performed for each channel independently based on the HSI color space instead of RGB. Experimental results indicate that better restoration results can be obtained as compared with traditional Bertalmio-Sapiro-Caselles-Bellester (BSCB) and fast marching method (FMM) algorithms. The proposed algorithm can also effectively deal with inpainting of complex color images with high computational efficiency.

Key words: image inpainting, image restoration, data fusion, interpolation, railway loaded condition inspection(RLCI)

中图分类号:

TP391

JIN Xing1, YU Da-hai1,2, HAN Jian-feng3, LI Hui-hui1, HAN Jun-wei1. 采用多方向插值融合的快速铁路货运图像修复[J]. 应用科学学报, 2014, 32(2): 191-198.

金星1，俞大海1,2，韩建枫3，李晖晖1，韩军伟1. Fast Inpainting of Railway Freights Images Based on Multiple Direction Interpolation[J]. Journal of Applied Sciences, 2014, 32(2): 191-198.

参考文献

[1] TAUBER Z, LI Z N, DREW M S. Review and preview: disocclusion by inpainting for image-based rendering [J]. IEEE Trans. Syst., Man, Cybern. C, 2007, 37(4): 527 -540.

[2] BERTALMIO M, SAPIRO G. Image inpainting [C]//Proceedings of the ACM SIGGRAPH Conference on Computer Graphics, New York, USA, 2000: 417-424.

[3] CHAN T, SHEN J. Mathematical models for local deterministic inpaintings. Technical Report CAM 00-11, Image Processing Research Group, UCLA, 2000. ftp://ftp.math.ucla.edu/pub/camreport/cam00-11.ps.gz

[4] CHAN T, SHEN J. Non-Texture inpainting by Curvature-Driven diffusions (CDD) [J]. CAM 00-35, Image Processing Research Group, UCLA,2000. ftp://ftp.math.ucla.edu/pub/camreport/cam00-35.pdf

[5] TELEA A C. An image inpainting technique based on the fast marching method [J], Journal of Graphics Tools, 2004, 9(1): 25-36.

[6] CRIMINISI A， PEREZ P， TOYAMA K. Region filling and object removal by exemplar-based image inpainting[J], IEEE Transactions on Image Processing, 2004, 13(9): 1200-1212.

[7] FENG Tang, YING Yiting, WANG Jin, et al. A novel texture synthesis based algorithm for object removal in photographs [C]//Proceedings of 9th Asian Computing Science Conference, Thailand, 2004: 248-258.

[8] BECK J， STEWART C, RADKE R J. LiDAR inpainting from a single image [C]//Proceedings on 12th International Conference on Computer Vision Workshops, 2009: 1441-1448.

[9] 党向盈，吴锡生. 一种新颖基于边缘最大梯度的多方向优化插值算法[J]. 计算机应用研究，2007, 24(9): 317-320.

DANG Xiangying, WU Xisheng, ZHAO Yong. Novel multi-direction optimization interpolation based on edge max-gradient algorithm[J]. Application Research of Computers, 2007, 24(9):317-320.

[10] 吴锡生，党向盈. 一种阈值控制的边缘自适应快速图像插值算法[J]. 计算机工程，2007, 33(22): 226-228.

WU Xisheng, DANG Xiangying, ZHAO Yong. Fast self-adptive edge-oriented interpolation based on threshold method[J]. Computer Engineering, 2007, 33(22)226-228.

[11] ZHANG Xiangjun, WU Xiaolin. Image interpolation by adaptive 2-D autoregressive modeling and soft-decision estimation[J]. IEEE Transactions on Image Processing, 2008, 17(4): 887-896.

[12] SOLTAN E A, ELKHAMY S E. Wavelet-based image interpolation with a least squares algorithm[J]. Computer Engineering Conference, 2010, 10(21): 103-106.

[13] ADAMCZYK K. WALCZAK A. Digital images interpolation with wavelet edge extractors[J]. Human System Interactions, 2010, 6(12): 399-405.

[14] YAROSLAVSKY L P. DFT and DCT based discrete sinc-interpolation methods for direct fourier tomographic reconstruction[J]. Image and Signal Processing and Analysis, 2003, 1(12): 405-410.

[15] LIN T C, TRUONG T K. DCT-based image codec embedded cubic spline interpolation with optimal quantization[J]. IEEE Eighth International Symposium, 2006, 44(2): 11-15.

[16] WU Zhenyu, YU Yongyang, CHEN Changwen. A new hybrid DCT-wiener_based interpolation scheme for video intra frame up-sampling[J]. IEEE Signal Processing Letters, 2010, 17(10): 827-830.

[17] LUKAC R, PLATANIOTIS N, SMOLKA B, VENESANOPOULOS N. Vector operators for color image zooming [C]//Proceedings of the IEEE International Symposium on Industrial Electronics. Dubrovnik, Croatia: IEEE, 2005: 1273-1277.

[18] JIN Liang Hai, LI De Hua, SONG E. Combining vector ordering and spatial information for color image interpolation[J]. Image and Vision Computing, 2009, 27(4): 10-416.

[19] CHA Y, KIM S. Edge-forming methods for color image zooming[J]. IEEE Transactions on Image Processing, 2006, 15(8): 2315-2323.

采用多方向插值融合的快速铁路货运图像修复

Fast Inpainting of Railway Freights Images Based on Multiple Direction Interpolation

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	孙容海, 施林甫, 俞春强, 劳欢, 唐振军. 面向密文图像信息隐藏的随机插值方法[J]. 应用科学学报, 2020, 38(3): 419-430.
[2]	苏文煊, 方针. 基于CFA插值特性不一致的图像真伪鉴别[J]. 应用科学学报, 2019, 37(1): 33-40.
[3]	陈艳, 俞春强, 侯晓杰, 张显全, 唐振军, 何南. 基于曲面插值的加密图像可逆信息隐藏算法[J]. 应用科学学报, 2018, 36(2): 220-236.
[4]	刘华勇, 李璐, 张大明, 王焕宝. 具有两类形状参数的代数三角混合样条曲线的构造和调配[J]. 应用科学学报, 2017, 35(3): 383-393.
[5]	张磊, 陆宇平, 殷明. 多传感器融合四旋翼协同控制算法及其实现[J]. 应用科学学报, 2016, 34(2): 190-202.
[6]	王伟, 张金艺, 张洪辉, 蔡春艳, 李建宇. 异质双9轴MEMS惯性传感器数据互补-加权迭代融合算法[J]. 应用科学学报, 2015, 33(5): 491-501.
[7]	张晓琳，方针，张新鹏. 利用通道间相关性的CFA图像盲取证[J]. 应用科学学报, 2015, 33(1): 87-94.
[8]	李熙1，陈锋锐2，于之锋1,3. 小波系数插值支持下的遥感影像混合像元分解[J]. 应用科学学报, 2012, 30(6): 613-618.
[9]	宋磊1，李立华1，高向川2，裴郁杉1，王化磊1. 不精确帧同步对幅值相位线性插值影响的分析[J]. 应用科学学报, 2012, 30(5): 441-447.
[10]	任亚飞，柯熙政. 多尺度小波分解融合在微机电陀螺数据处理中的应用[J]. 应用科学学报, 2010, 28(4): 394-398.
[11]	丁琦，平西建. 基于子带谱平滑度的音频篡改检测[J]. 应用科学学报, 2010, 28(2): 142-146.
[12]	谢伟松;熊燕. 有理三次Bezier样条的曲线修正方法[J]. 应用科学学报, 2007, 25(2): 216-216 .
[13]	王永利, 徐宏炳, 董逸生, 钱江波, 刘学军. 数据流上异常数据的在线检测与修正[J]. 应用科学学报, 2006, 24(3): 256-261.
[14]	刘以安, 陈松灿, 张明俊, 马秀芳. 缓冲算子及数据融合技术在目标跟踪中的应用[J]. 应用科学学报, 2006, 24(2): 154-158.
[15]	金施群, 丁晓牧, 费业泰, 余晓芬, 陈晓怀. 大轴直径的高精度多滚轮法测量[J]. 应用科学学报, 2005, 23(2): 200-203.