基于透视不变二值特征描述子的图像匹配算法

doi:10.11959/j.issn.1000-436x.2015086

通信学报 ›› 2015, Vol. 36 ›› Issue (4): 105-114.doi: 10.11959/j.issn.1000-436x.2015086

基于透视不变二值特征描述子的图像匹配算法

耿利川^1,²,苏松志^1,²,李绍滋^1,²()

¹ 厦门大学信息科学与技术学院，福建厦门 361005
² 福建省仿脑智能系统重点实验室，福建厦门 361005

出版日期:2015-04-25 发布日期:2015-04-15
基金资助:
国家自然科学基金资助项目;国家自然科学基金资助项目;厦门大学中央高校基金资助项目;厦门大学中央高校基金资助项目;厦门大学985平台建设基金资助项目;福建省自然科学基金资助项目;福建省自然科学基金资助项目;福建省自然科学基金资助项目;厦门市科技重点基金资助项目;高等学校博士学科点专项科研基金资助项目;深圳市战略性新兴产业发展专项基金资助项目;湖南省自然科学基金资助项目;教育厅科研基金资助项目

Li-chuan GENG^1,²,Song-zhi SU^1,²,Shao-zi LI^1,²()

¹ College of Information Science and Technology，Xiamen University，Xiamen 361005，China
² Fujian Key Laboratory of the Brain-like Intelligent Systems，Xiamen 361005，China

Online:2015-04-25 Published:2015-04-15
Supported by:
The National Natrual Science Foundation of China;The National Natrual Science Foundation of China;The Fundamental Research Funds for the Central Universities;The Fundamental Research Funds for the Central Universities;The 985 Project of Xiamen University;The Key Projects Fund of Science and Technology in Xiamen;The Research Fund for the Doctoral Program of Higher Education of China;The Special Fund for Developing Shenzhen's Strategic Emerging Industries;The Natural Science Foundation of Hunan Province;The Research Foundation of Education Committee

摘要/Abstract

摘要：

针对基于局部特征的图像匹配算法普遍存在对透视变换顽健性差的缺点，提出了一种新的二值特征描述子PIBC（perspective invariant binary code），提高了图像匹配算法的透视变换顽健性。首先，在提取金字塔图像FAST特征点的基础上，利用Harris角点响应值去除非极大值点和边缘响应点；其次，通过模拟相机不同视角成像之间的透视变换，对单个FAST特征点生成不同视角变换下图像的二值描述子，使描述子具备描述不同视角图像中同一特征点的能力。实验结果表明，算法在提高描述子透视不变性的同时时间复杂度与SURF算法近似。

关键词: 图像匹配, 二值特征描述子, 透视不变, PIBC

Abstract:

Current local feature based image matching algorithms are usually less robust to image perspective transformation.Aiming to solve this problem，a new perspective invariant binary code (PIBC) based image matching algorithm is proposed.Firstly，FAST corners are detected on the pyramid images，those corners with non-maximum Harris corner response value and the edge points are further eliminated.And then，by simulating the perspective transformations of images taken from different viewpoints，a single FAST corner is described with binary descriptors under different viewpoint transformations，which makes the descriptor could describe the identical feature point on different perspective transform images.Experimental results show its robustness to image perspective transformation，while its complexity is similar with SURF.

Key words: image matching, binary feature descriptor, perspective invariant, PIBC

耿利川,苏松志,李绍滋. 基于透视不变二值特征描述子的图像匹配算法[J]. 通信学报, 2015, 36(4): 105-114.

Li-chuan GENG,Song-zhi SU,Shao-zi LI. [J]. Journal on Communications, 2015, 36(4): 105-114.

图/表 16

图1

图2

图3

图4

图5

表1

图6

表2

图7

图8

图9

图10

图11

表3

图12

表4

参考文献 23

[1]	蒋淑静，黑保琴，张九星，等. 基于PDE的自适应各向异性图像配准方法研究[J]. 通信学报， 2013，34(5): 192-199. JIANG S J ， HEI B Q ， ZHANG J X ，et al. Research on PDE-based adaptive anisotropic image registration[J]. Journal on Communications， 2013，34(5): 192-199.
[2]	LOWE D G . Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision， 2004，60(2): 91-110.
[3]	LOWE D G . Object recognition from local scale-invariant features[A]. Proceedings of IEEE International Conference on Computer Vision[C]. Kerkyra，Greece， 1999. 1150-1157.
[4]	杨化超，姚国标，王永波 . 基于 SIFT 的宽基线立体影像密集匹配[J]. 测绘学报， 2011，40(5): 537-543. YANG H C YAO G B ， WANG Y B . Dense matching for wide base-line stereo images based on SIFT[J]. Acta Geodaetica et Cartorgraphica Sinica， 2011，40(5): 537-543.
[5]	BAY H ， TUYTELAARS T ， VANGOOL L . SURF:speeded up robust features[A]. Proceedings of European Conference on Computer Vision[C]. Graz，Austria， 2006. 404-417.
[6]	BAY H E ， ESS A ， TUYTELAARS T ，et al. SURF:speeded up robust features[J].Computer Vision and Image Understanding，2008，110(3)，346-359.Computer Vision and Image Understanding， 2008，110(3): 346-359.
[7]	KE Y ， SUKTHANKAR R . PCA-SIFT:a more distinctive representation for local image descriptors[A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C]. 2004. 506-513.
[8]	STRECHA C ， BRONSTEIN A M ， BRONSTEIN M M ，et al. LDAHash:improved matching with smaller descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2012，34(1): 66-78.
[9]	ALCANTARILLA P F ， NUEVO J ， BARTOLI A . KAZE features[A]. Proceedings of European Conference on Computer Vision[C]. Springer Berlin Heidelberg， 2012. 214-227.
[10]	ALCANTARILLA P F ， NUEVO J ， BARTOLI A . Fast explicit diffusion for accelerated features in nonlinear scale spaces[A]. Proceedings of British Machine Vision Conference[C]. Bristol，UK， 2013. 1-11.
[11]	CALONDER M ， LEPETIT V ， STRECHA C ，et al. Brief:binary robust independent elementary features[A]. Proceedings of European Conference on Computer Vision[C]. Heraklion，Crete，Greece， 2010. 1-14.
[12]	RUBLEE E ， RABAUD V ， KONOLIGE K ，et al. ORB:an efficient alternative to SIFT or SURF[A]. Proceedings of International Conference on Computer Vision[C]. 2011. 2564-2571.
[13]	ROSTEN E ， DRUMMOND T . Fusing points and lines for high performance tracking[A]. Proceedings of International Conference on Computer Vision[C]. 2005. 1508-1511.
[14]	LEUTENEGGER S ， CHLI M ， SIEGWART R Y . BRISK:binary robust invariant scalable keypoints[A]. Proceedings of International Conference on Computer Vision[C]. 2011. 2548-2555.
[15]	MAIR E ， HAGER G D ， BURSCHKA D ，et al. Adaptive and generic corner detection based on the accelerated segment test[A]. Proceedings of European Conference on Computer Vision[C]. Springer Berlin Heidelberg， 2010. 183-196.
[16]	MOREL J M ， YU G S . ASIFT:a new framework for fully affine invariant image comparison[J]. SIAM Journal on Imaging Sciences， 2009，2(2): 438-469.
[17]	CAI G ， JODOIN P M ， LI S ，et al. Perspective-SIFT:an efficient tool for low-altitude remote sensing image registration[J]. Signal Processing， 2013，93(11).
[18]	蔡国榕，李绍滋，吴云东，等 . 一种透视不变的图像匹配算法[J]. 自动化学报， 2013，39(7): 1053-1061. CAI G R ， LI S Z WU Y D et al . A perspective invariant imagematching algorithm[J]. Acta Automatica Sinica， 2013，39(7): 1053-1061.
[19]	SMITH S M ， BRADY J M . SUSAN—a new approach to low level image processing[J]. International Journal of Computer Vision， 1997，23(1): 45-78.
[20]	HARRIS C ， STEPHENS M . A combined corner and edge detector[A]. Proceedings of Alvey Vision Conference[C]. 1988.50.
[21]	HASHIMOTO T ， TAKAGI M K，KAJIWARE ， et al . Remote Sensing Note[M]. Japan Association on Remote Sensing， 1999.
[22]	ROSIN P L . Measuring corner properties[J]. Computer Vision and Image Understanding， 1999，73(2): 291-307.
[23]	MIKOLAJCZYK K ， SCHMID C . Scale and affine invariant Interest point detectors[J]. International Journal of Computer Vision， 2004，60(1): 63-86.

算法	1\|2	1\|3	1\|4	1\|5	1\|6
SIFT	499	369	155	0	0
SURF	467	280	34	0	0
ORB	695	435	198	28	0
BRIEF	509	366	0	42	0
BRISK	236	58	18	0	0
KAZE	523	257	67	0	0
PIBC	675	530	384	286	173

算法	1\|2	1\|3	1\|4	1\|5	1\|6
SIFT	537	446	296	46	4
SURF	540	416	271	56	5
ORB	518	453	81	20	0
BRIEF	765	695	420	233	25
BRISK	192	156	43	16	0
KAZE	597	559	338	74	0
PIBC	646	585	473	365	260

数据集	ASIFT算法	PIBC算法
Graf	1 699/31 169	410/1 003
Wall	3 789/36 922	465/1 002
magazine	4 134/26 178	662/1 004
painting	7 92/102 82	200/402
tilt_t2	1 078/17 185	334/603
tilt_t4	179/7 608	153/503
XMU_UAVImg	583/34 672	196/1 005

基于透视不变二值特征描述子的图像匹配算法

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 23

相关文章 1

Metrics

推荐阅读 0

结果	SIFT	SURF	BRIEF	ORB	BRISK	KAZE	PIBC
UAV_1	195	87	0	213	35	65	263
UAV_2	60	61	0	27	23	16	145
UAV_3	92	52	0	73	15	23	182
UAV_4	21	22	8	12	7	0	64
全数据集平均结果	116	64	11	92	33	39	196