不同局部邻域划分SURF描述符的性能分析

翟优; 曾峦; 熊伟

doi:10.3788/OPE.20132109.2395

您当前的位置：

首页 >

文章列表页 >

不同局部邻域划分SURF描述符的性能分析

信息科学 | 更新时间：2020-08-12

- 不同局部邻域划分SURF描述符的性能分析
- Performance analysis of SURF descriptor with different local region partition
- 光学精密工程 2013年21卷第9期页码：2395-2404
- 作者机构：
  
  装备学院重点实验室，北京 101416
- 作者简介：
- 基金信息：
  
  总装备部试验技术研究项目()
- DOI：10.3788/OPE.20132109.2395
  中图分类号： TP391.4
- 收稿日期：2013-03-01，
  
  修回日期：2013-04-24，
  
  网络出版日期：2013-09-30，
  
  纸质出版日期：2013-09-15
- 稿件说明：
移动端阅览
翟优曾峦熊伟. 不同局部邻域划分SURF描述符的性能分析[J]. 光学精密工程, 2013,21(9): 2395-2404

ZHAI You ZENG Luan XIONG Wei. Performance analysis of SURF descriptor with different local region partition[J]. Editorial Office of Optics and Precision Engineering, 2013,21(9): 2395-2404
翟优曾峦熊伟. 不同局部邻域划分SURF描述符的性能分析[J]. 光学精密工程, 2013,21(9): 2395-2404 DOI： 10.3788/OPE.20132109.2395.

ZHAI You ZENG Luan XIONG Wei. Performance analysis of SURF descriptor with different local region partition[J]. Editorial Office of Optics and Precision Engineering, 2013,21(9): 2395-2404 DOI： 10.3788/OPE.20132109.2395.

摘要

研究了加速鲁棒特征（SURF）描述符的局部邻域划分方法，以降低该描述符的维数，提升基于SURF的图像匹配算法的匹配速度和鲁棒性。参考尺度不变特征变换（SIFT）描述符和SURF描述符已有的各种邻域划分方式，将SURF描述符的局部邻域分为栅格状（原SURF划分方式）、三角形和扇形进行分析。首先，分析了图像的尺度和旋转变化对这3种邻域划分方式描述符匹配性能的影响；然后，提出了构建三角形划分和扇形划分SURF描述符的方法；最后，进行了匹配实验，对8种不同划分方式的SURF描述符进行了比较。结果表明：扇形划分SURF描述符的性能要优于三角形划分和栅格划分SURF描述符，其中6扇区、8扇区、12扇区及三角形划分的SURF描述符的性能均比SURF描述符有一定程度的提升，描述符的维数与原SURF描述符（64维）相比分别低了40维、32维、16维和32维。

Abstract

Several local region partition methods for Speeded Up Robust Features (SURF) descriptors were researched to reduce their dimensions and increase the matching speeds and robustnesses of SURF based matching algorithms. With reference to existing local region partition methods of Scale Invariant Feature Transform (SIFT) and SURF descriptors

the local regions were divided into grids(original SURF)

triangles

and sectors. First

the influences of scale change and rotation of the image on the matching performance of SURF descriptors were analyzed. Then

a method to construct the SURF descriptors with local region partitions in triangles and sectors were proposed

and matching experiments were performed. The SURF descriptors with different local region partitions were compared. The experiment results show that the performance of the sector partition based SURF descriptor is better than those of triangle partition and grid partition (original SURF) based SURF descriptors. The performance of SURF descriptors with 6-sector partition

8-sector partition

12-sector partition and triangle partition is better than that of original one

and the dimensions of these new descriptors are 40

16 and 32 lower than that of original SURF (64 dimensions).

关键词

Keywords

references

翟优, 曾峦, 熊伟. 基于不变特征描述符实现星点匹配[J]. 光学精密工程， 2012, 20(11): 2531-2539.ZHAI Y, ZENG L, XIONG W. Star matching based on invariant feature descriptor [J]. Opt. Precision Eng., 2012, 20(11): 2531-2539.(in Chinese)[2]李英, 丘文涛, 赵建,等.结合区域分割的SIFT图像匹配方法[J].液晶与显示，2012, 27(6):827-831.LI Y, QIU W T, ZHAO J, et al.. Image matching algorithm combining SIFT with region segmentation[J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27(6):827-831.(in Chinese)[3]李英，李静宇，徐正平. 结合SURF与聚类分析方法实现运动目标的快速跟踪[J]. 液晶与显示，2011, 26（4）：544-550.LI Y，LI J Y，XU ZH P. Moving target fast tracking using SURF and cluster analysis method [J]. Chinese Journal of Liquid Crystals and Displays, 2011, 26（4）：544-550. (in Chinese)[4]黄彬彬, 唐琎. 一种新的人脸图像中眼睛定位方法[J]. 液晶与显示, 2009, 24(2): 278-282.HUANG B B, TANG J. Novel method of eye detection in facial images [J]. Chinese Journal of Liquid Crystals and Displays, 2009, 24(2): 278-282. (in Chinese)[5]LOWE D G. Object recognition from local scale-invariant features [C].Proc. of the International Conference on Computer Vision, 1999: 11501157.[6]LOWE D G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004:91-110. [7]KE Y,SUKTHANKAR R.PCA-SIFT:a more distinctive representation for local image descriptors [C].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,Washington D C,2004,2:506-513.[8]MIKOLAJCZYK K, SCHMID C.A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27(10): 1615-1630.[9]ZENG L, ZHAI Y. An improved SIFT descriptor[C]. Proc. of SPIE, 2011,8321: 1-8.[10]曾峦,顾大龙. 一种基于扇形区域分割的SIFT特征描述符[J]. 自动化学报, 2012, 38(9): 1513-1519.ZENG L, GU D L. A SIFT feature descriptor based on sector area partitioning [J]. Acta Automatica Sinica, 2012, 38(9): 1513-1519.(in Chinese)[11]ZENG L, XIONG W, ZHAI Y. Gun bore flaw image matching based on improved sift descriptor[C]. Proceedings of the 8th International Symposium on Precision Engineering Measurements and Instrumentation, Chengdu, China, SPIE, 2012.[12]YAN C, HASLER N, THORMHLEN T, et al.. Scale invariant feature transform with irregular orientation histogram binning [C]. 6th International Conference on Image Analysis and Recognition (ICIAR 2009),2009: 258-267.[13]BAY H, TUYTELAARS T,GOOL L J V. Surf: Speeded uprobust features[C]. In A. Leonardis, H. Bischof, and A. Pinz, editors, ECCV (1), volume 3951 of Lecture Notes in Computer Science, pages 404-417. Springer, 2006.[14]BAY H, TUYTELAARS T, GOOL L V, et al.. Speeded up robust features [J]. Computer Vision-ECCV 2006 Lecture wotes in Computer Science, 2006, 3951:404-417.[15]AGRAWAL M, KONOLIGE K, BLAS M R. CenSurE: Center surround extremas for realtime feature detection and matching [C]. Computer Vision-ECCV 2008 Lecture Wotes in Computer Science, 2008, 5305:102-115.[16]EBRAHIMI M, WALTERIO W. SUSurE: speeded up surround extrema feature detector and descriptorfor realtime applications[C]. IEEE Conference on Computer Vision and Pattern Recognition,2009:9-14.[17]LUO J, GWUN O. A comparison of SIFT, PCA-SIFT, and SURF[J]. International Journal of Image Processing (IJIP), 2009, 3(4): 143-152.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

利用单应约束实现结构化场景的匹配扩展

改进的SIFT特征提取和匹配算法

基于双目结构光周视扫描的3D件三维重构与位姿估计研究

重叠分数与匹配矩阵驱动的部分重叠点云配准网络设计

基于Snell窗及偏振模式的水下载体航姿测量