一种适合于大尺寸航拍图像的特征点提取方法

doi:10.7527/S1000-6893.2013.0326

电子与控制

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

一种适合于大尺寸航拍图像的特征点提取方法

石祥滨^1,2, 张劲松², 陈润锋², 刘进立²

1. 沈阳航空航天大学计算机学院, 辽宁沈阳 110136;
2. 辽宁大学信息学院, 辽宁沈阳 110136

收稿日期:2013-04-07 修回日期:2013-06-28 出版日期:2014-01-25 发布日期:2013-07-12
通讯作者: 石祥滨，Tel.：024-89723398 E-mail：sxb@sau.edu.cn E-mail:sxb@sau.edu.cn
作者简介:石祥滨男，博士，教授，硕士生导师。主要研究方向：分布式虚拟现实、大规模网络游戏、图像目标识别与融合、视频分析。Tel：024-89723398 E-mail：sxb@sau.edu.cn；张劲松男，硕士研究生。主要研究方向：虚拟现实，图像处理。Tel：024-89723487 E-mail：yqzjs@foxmail.com
基金资助:
国家自然科学基金（61170185）；辽宁省科技攻关计划项目（2011217002）

A Feature Point Extraction Method for Large Size Aerial Images

SHI Xiangbin^1,2, ZHANG Jinsong², CHEN Runfeng², LIU Jinli²

1. College of Computer Science, Shenyang Aerospace University, Shenyang 110136, China;
2. College of Information, Liaoning University, Shenyang 110136, China

Received:2013-04-07 Revised:2013-06-28 Online:2014-01-25 Published:2013-07-12
Supported by:
National Natural Science Foundation of China (61170185);Scientific and Technological Research Projects in Liaoning (2011217002)

摘要/Abstract

摘要：

一些航拍图像的尺寸较大，现有的特征点提取算法在对其处理时均要耗费大量的时间，针对这一问题，提出一种快速有效的特征点提取算法。首先构造原始图像的拉普拉斯金字塔，以获得图像的尺度信息，同时保留图像的方向信息；再使用非均匀多方向滤波器组将金字塔图像分解在不同方向上，在分解后的图像中提取局部极值点作为候选特征点集；采用特定的合并策略合并候选特征点最终得到特征点集，并根据方向滤波器组为特征点分配方向向量。试验结果表明，本文算法在基本保证提取到的特征点匹配率及正确率的前提下，有较高的效率。

关键词: 航拍图像, 特征点提取, 特征点匹配, 拉普拉斯金字塔, 方向滤波器组

Abstract:

The existing feature point extraction methods usually cost a lot of CPU time when they are applied to large size aerial images. For the purpose of fast extraction of feature points in these large size aerial images, a novel method is developed. Usually these aerial images have not only large sizes but also wide ranges of shooting. They usually have different feature point performances on different scales and the distributions of spectra are uniform in the frequency domain. In this paper, the scales of the feature points are kept by employing the Laplacian pyramid, and a specified non-uniform N-dimensional directional filter bank is applied to decompose the pyramid images. The scales and the directions of the images are extracted. Then the local extreme points are extracted as a candidate feature points set. Finally, the candidate feature points in different directions are merged by a specified merge-strategy. Thus, we obtain the final feature points set and the directions of the feature point described by the direction filter bank. Experimental results are presented that demonstrate the proposed method is efficient for large size aerial images while meeting the match rate and precision rate requirements.

Key words: aerial image, feature point extraction, feature point matching, Laplacian pyramid, directional filter bank

中图分类号:

V19
TP391

石祥滨, 张劲松, 陈润锋, 刘进立. 一种适合于大尺寸航拍图像的特征点提取方法[J]. 航空学报, 2014, 35(1): 240-248.

SHI Xiangbin, ZHANG Jinsong, CHEN Runfeng, LIU Jinli. A Feature Point Extraction Method for Large Size Aerial Images[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2014, 35(1): 240-248.

参考文献

[1] Bellavia F, Tegolo D, Valenti C. Improving Harris corner selection strategy[J]. IET Computer vision, 2011, 5(2): 87-96.

[2] Chang X Z, Gao L Q. Corner detection based on disk[J]. Element Journal of Computer-Aided Design and Computer Graphics, 2007, 19(10): 1342-1347. (in Chinese) 常兴治, 高立群. 利用圆结构元的形态学角点检测[J]. 计算机辅助设计与图形学学报, 2007, 19(10): 1342-1347.

[3] Zhong B J, Liao W H. Corner detection based on accumulative chord length of refined digital curves[J]. Element Journal of Computer-Aided Design and Computer Graphics 2004, 16(7): 939-943. (in Chinese) 钟宝江, 廖文和. 基于精化曲线累加弦长的角点检测技术[J]. 计算机辅助设计与图形学学报, 2004, 16(7): 939-943.

[4] Ryu J B, Lee C G, Park H H. Formula for Harris corner detector[J]. Electronics Letters, 2011, 47(3): 180-181.

[5] Mikolajczyk K, Schmid C. Scale and affine invariant interest point detectors[J]. International Journal of Computer Vision, 2004, 60(1): 63-86.

[6] Gao C, Zhang X, Wang Y L, et al. Automatic stitching approach of aerial image sequence based on SIFT features[J]. Computer Applications, 2007, 27(11): 2789-2792. (in Chinese) 高超, 张鑫, 王云丽, 等. 一种基于SIFT特征的航拍图像序列自动拼接方法[J]. 计算机应用, 2007, 27(11): 2789-2792.

[7] Liao C, Wang G J, Shen Y L, et al. Aerial video stitching via multi-direction strips[J]. Acta Aeronautica et Astronautica Sinica, 2012, 33(11): 2065-2073. (in Chinese) 廖超, 王贵锦, 沈永玲, 等. 航拍视频的多向条带拼接算法[J]. 航空学报, 2012, 33(11): 2065-2073.

[8] Yi M, Guo B L, Aerial video image registration method based on invariant feature and mapping restraint[J]. Acta Aeronautica et Astronautica Sinica, 2012, 33(10): 1872-1880. (in Chinese) 易盟, 郭宝龙. 基于不变特征和映射抑制的航拍视频图像配准[J]. 航空学报, 2012, 33(10): 1872-1880.

[9] Gao J, Huang X H, Peng G, et al. Simplified SIFT feature point detecting method[J]. Application Research of Computers, 2008, 25(7): 2213-2215. (in Chinese) 高健, 黄心汉, 彭刚, 等. 一种简化的SIFT图像特征点提取算法[J]. 计算机应用研究, 2008, 25(7): 2213-2215.

[10] Zhong S H, Liu Y, Wu G S. S-SIFT: A shorter SIFT without least discriminative visual orientation[C]//2012 IEEE/WIC/ACM International Conference on Web Intelligence, 2012: 669-672.

[11] Moreno P, Bernardino A, Santos-Victor J. Improving the SIFT descriptor with smooth derivative filters[J]. Pattern Recognition Letters, 2009, 30(1): 18-26.

[12] Shen H, Li S X, Shen Y P, et al. Fast image registration in aerial video[J]. Acta Aeronautica et Astronautica Sinica, 2013, 34(6): 1065-1413. (in Chinese) 申浩, 李书晓, 申意萍, 等. 航拍视频帧间快速配准算法[J]. 航空学报, 2013, 34(6): 1065-1413.

[13] Rosten E, Drummond T. Machine learning for high-speed corner detection[C]//Computer Vision-ECCV 2006, 2006: 430-443.

[14] Malik J, Sainarayanan G, Dahiya R. Corner detection using phase congruency features[C]//2010 International Conference on Signal and Image Processing (ICSIP), 2010: 217-221.

[15] Shang L, Chen J, Su P G, et al. ROI extraction of palmprint images using modified harris corner point detection algorithm[C]//Intelligent Computing Theories and Applications, 2012: 479-486.

[16] Gevrekci M, Gunturk B K. Illumination robust interest point detection[J]. Computer Vision and Image Understanding, 2009, 113(4): 565-571.

[17] Tu D W, Zhang Y C. Auto-detection of checkerboard corners based on grey-level difference[J]. Optics and Precision Engineering, 2011, 19(6): 1360-1366. (in Chinese) 屠大维, 张翼成. 基于灰度差异的棋盘格角点自动检测[J]. 光学精密工程, 2011, 19(6): 1360-1366.

[18] Liu R K, Hu W, Gao Y, et al. Design and implementation of airborne high definition video encoder based on DSP platform[J]. Acta Aeronautica et Astronautica Sinica, 2011, 32(3): 507-514. (in Chinese) 刘荣科, 胡伟, 高杨, 等. 基于DSP平台的机载高清视频编码器设计与实现[J]. 航空学报, 2011, 32(3): 507-514.

[19] Do M N, Vetterli M. The contourlet transform: an efficient directional multiresolution image representation[J]. IEEE Transactions on Image Processing, 2005, 14(12): 2091-2106.

[20] Wang Z H, Dou L H, Chen J. An adaptive Gaussian filter with scale adjustable[J]. Optical Technique, 2007, 32(3): 395-397, 402. (in Chinese) 王振华, 窦丽华, 陈杰. 一种尺度自适应调整的高斯滤波器设计方法[J]. 光学技术, 2007, 32(3): 395-397, 402.

[21] De Valois R L, Cottaris N P, Mahon L E, et al. Spatial and temporal receptive fields of geniculate and cortical cells and directional selectivity[J]. Vision Research, 2000, 40(27): 3685-3702.

[22] Nguyen T T, Oraintara S. Multiresolution direction filterbanks: theory, design, and applications[J]. IEEE Transactions on Signal Processing, 2005, 53(10): 3895-3905.

[23] Nguyen T T, Oraintara S. A class of multiresolution directional filter banks[J]. IEEE Transactions on Signal Processing, 2007, 55(3): 949-961.

[24] Calonder M, Lepetit V, Strecha C, et al. Brief: Binary robust independent elementary features[C]//Computer Vision-ECCV 2010, 2010: 778-792.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

一种适合于大尺寸航拍图像的特征点提取方法

A Feature Point Extraction Method for Large Size Aerial Images

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	钟梦帆, 裴继红. 局部特征点对称约束的图像拼接增强方法[J]. 航空学报, 2022, 43(S1): 726948-726948.
[2]	蔡佳, 黄攀峰. 基于改进SURF和P-KLT算法的特征点实时跟踪方法研究[J]. 航空学报, 2013, 34(5): 1204-1214.
[3]	刘宝泉;冯大政;武楠;李军侠. 基于点特征的干涉合成孔径雷达(InSAR)复图像自动配准算法[J]. 航空学报, 2007, 28(1): 161-166.