基于改进SURF算法的移动目标实时图像配准方法研究

doi:10.11959/j.issn.1000-436x.2017020

Abstract

Abstract:

For the unstability of the real-time visual image characteristic point extraction and matching for the mobile target,an improved registration method of the multiple algorithm-fusion was introduced.Firstly,the method of bilateral filtering,Canny edge detection and morphological processing,was adopted to get the more robust image's edge map.And the founded points were limited in this edge map,then the Hessian matrix of SURF based on the discrete Gaussian-Hermite moment was modified.The character description vector was redefined in the algorithm.Following the above analysis,the Kendall coefficient constraint was discussed in image matching characteristic points.Secondly,the spectral radiant color invariant model and the I_SURF algorithm were used to match the real-time color image.Finally,the improved algorithm was combined with the update algorithm of adaptive target to match the mobile target in indoor environment.The experimental results show that the static image registration accuracy of the improved algorithm is higher than that of the SURF algorithm,and also the stability of the mobile image feature points extraction and the registration number have achieved over 97% under different rotating scales.

Key words: improved SURF, mobile target, image registration, real-time, Gaussian-Hermite moment

CLC Number:

TN911.73

Gang JU,Liang YUAN,Xiao-yue LIU,Hao-en YUE. Study on mobile target real-time image registration based on improved SURF algorithm[J]. Journal on Communications, 2017, 38(1): 177-186.

Figures/Tables 11

References 13

[1]	BAY H , ESS A , TUYTELAARS T ,et al. Speeded-up robust features(SURF)[J]. Computer Vision and Image Understanding, 2008,110(3): 346-359.
[2]	吴一全, 沈毅, 陶飞翔 . 基于 NSCT 和 SURF 的遥感图像匹配[J]. 遥感学报, 2014,18(3): 618-629.
	WU Y Q , SHEN Y , TAO F X . Remote sensing image matching based on non-subsampled contourlet transform and speed up robust features[J]. Journal of Remote Sensing, 2014,18(3): 618-629.
[3]	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.
[4]	丁南南, 刘艳滢, 张叶 ,等. 基于SURF-DAISY算法和随机KD树的快速图像配准[J]. 光电子:激光, 2012,(7): 1395-1402.
	DING N N , LIU Y Y , ZHANG Y ,et al. Fast image registration based on SURF-DAISY algorithm and randomized KD trees[J]. Journal of optoelectronics:laser, 2012,(7): 1395-1402.
[5]	谢雨来, 李醒飞, 吕津玮 ,等. 基于 SURF 算法的水下图像实时配准方法[J]. 计算机辅助设计与图形学学报, 2010(12): 2215-2220.
	XIE Y L , LI X F , LV J W ,et al. Underwater images real-time registration method based on SURF[J]. Journal of Computer-Aided Design ＆Computer Graphics, 2010(12): 2215-2220.
[6]	闫自庚, 蒋建国, 郭丹 . 基于SURF特征和Delaunay三角网格的图像匹配[J]. 自动化学报, 2014,40(6): 1216-1222.
	YAN Z G , JANG J G , GUO D . Image matching based on SURF feature and delaunay triangular meshes[J]. Acta Automatica Sinica, 2014,40(6): 1216-1222.
[7]	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.
	CAI J , HUANG P F . Research of a real-time feature point tracking method based on the combination of improved SURF and P-KLT algorithm[J]. Acta Aeronautica ET Astronautica Sinica, 2013,34(5): 1204-1214.
[8]	张子龙, 薛静, 乔鸿海 ,等. 基于改进 SURF 算法的交通视频车辆检索方法研究[J]. 西北工业大学学报, 2014(2): 297-302.
	ZHANG Z L , XUE J , QIAO H H ,et al. The vehicle retrieval methods of traffic video based on improved SURF algorithm[J]. Journal of Northwestern Polytechnical University, 2014(2): 297-302.
[9]	WONG D R , HAYES M P , BAINBRIDGE S A . IMU-aided SURF feature matching for relative pose estimation[C]// Image ＆ Vision Computing New Zealand,International Conference. 2010: 1-6.
[10]	GOH K M , MOKJI M M , ABUBAKAR S A R . Improved rotational matching of SIFT and SURF[J]. Proceedings of SPIE-The International Society for Optical Engineering, 2012,8334:83341.
[11]	YANG K . Missile placement analysis based on improved SURF feature matching algorithm[J]. Proceedings of SPIE-The International Society for Optical Engineering, 2015,9443.
[12]	YANG B , DAI M . Image analysis by Gaussian-Hermite moments[J]. Signal Processing, 2011,91(10): 2290-2303.
[13]	HOSNY K M . Fast computation of accurate Gaussian-Hermite moments for image processing applications[J]. Digital Signal Processing, 2012,22(3): 476-485.

Metrics

Recommended 0

No Suggested Reading articles found!

图像	增加信噪比/dB		检测时间/s		特征点数量		配准对数		误配对数			配准率
图像	SURF	I_CSURF	SURF	I_CSURF	SURF	I_CSURF	SURF	I_CSURF	SURF	I_CSURF	SURF		I_CSURF
Lena 30^o	0	0.8	0.846	0.849	343	1 042	212	473	86	1	0.711		0.998
猴脸45^o	0	0.8	1.624	1.743	1 843	2 413	1 241	1 643	243	3	0.836		0.998
蔬菜60^o	0	0.8	0.813	0.821	314	394	196	288	93	1	0.678		0.996
水果75^o	0	0.8	1.711	1.721	1 764	1 970	986	743	338	2	0.745		0.997

	密叶小车30^o			猴脸60^o			水果90^o
配准图像	坐标	角度/(°)	配准图像	坐标	角度/(°)	配准图像	坐标	角度/(°)
11帧	324,278]	0	17帧	175,206]	?23	16帧	166,239]	?7
26帧	297,284]	30	25帧	171,187]	43	19帧	221,165]	187
34帧	319,248]	45	38帧	192,152]	51	24帧	251,202]	89
59帧	104,273]	0	67帧	205,66]	51	35帧	370,227]	0
81帧	569,178]	0	92帧	188,295]	51	67帧	208,38]	0
104帧	505,429]	0	111帧	393,221]	12	98帧	163,219]	11

密叶小车30^o颜色模型（像素）						猴脸60^o颜色模型（像素）						水果90^o颜色模型（像素）
帧数	Π_init	Π_old	Π_current	Π_new	实际值	帧数	Π_init	Π_old	Π_current	Π_new	实际值	帧数	Π_init	Π_old	Π_current	Π_new	实际值
11帧	12.2	23.5	17.8	53.5	54.2	17帧	17.8	31.3	26.4	75.5	79.3	16帧	20.4	23.8	26.7	70.9	71.1
26帧	12.2	22.4	21.7	56.3	55.1	25帧	17.8	29.7	30.5	78	76.4	19帧	20.4	26.6	24.5	71.5	70.6
34帧	12.2	23.4	19.8	55.4	56.3	38帧	17.8	31.2	29.4	78.4	79.7	24帧	20.4	27.3	28.4	76.1	77.4
59帧	12.2	26.8	16.4	55.4	57.6	67帧	17.8	33.4	31.2	82.4	83.1	35帧	20.4	29.3	30.7	80.4	81.4
81帧	12.2	27.4	22.6	62.2	58.7	92帧	17.8	29.8	26.7	74.3	76.2	67帧	20.4	30.8	29.7	80.9	78.9
104帧	12.2	24.1	23.1	59.4	62.3	111帧	17.8	28.4	30.0	76.2	75.5	98帧	20.4	29.4	30.2	80.0	79.5

密叶小车30^o结构模型(节点数)						猴脸60^o结构模型(节点数)						水果90^o结构模型(节点数)
帧数	pro	hold	dis	M	实际值	结构模型	pro	hold	dis	M	实际值	结构模型	pro	hold	dis	M	实际值
11帧	214	293	79	428	439	17帧	456	491	96	851	842	16帧	371	471	106	736	743
26帧	223	289	83	429	436	25帧	471	497	101	867	864	19帧	382	486	118	750	739
34帧	218	334	101	451	440	38帧	483	478	118	843	854	24帧	375	441	98	718	732
59帧	219	289	87	421	413	67帧	443	521	106	858	849	35帧	381	472	121	732	741
81帧	205	289	91	412	422	92帧	420	530	103	847	856	67帧	351	492	97	746	731
104帧	220	317	96	441	432	111帧	423	517	97	843	851	98帧	376	470	91	755	750

性能参数									图像
性能参数			密叶小车30^o						猴脸60^o						水果90^o
图像帧数	11	26	34	59	81	104	17	25	38	67	92	111	16	19	24	35	67	98
有效特征点数量	439	436	440	413	422	432	842	864	854	849	856	851	743	739	732	741	731	750
配准对数	262	243	261	239	258	249	479	482	476	469	480	470	410	404	412	402	354	401
误配对数	1	1	0	2	3	0	3	0	0	2	1	4	0	3	2	4	2	3
配准率	0.99	0.99	1.0	0.99	0.98	1.0	0.99	1.0	1.0	0.99	0.99	0.99	1.0	0.99	0.99	0.99	0.99	0.99

Study on mobile target real-time image registration based on improved SURF algorithm

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 13

Related Articles 15

Metrics

Recommended 0

[1]	Jinkang ZHU, Mingyang CHAI, Wuyang ZHOU. Three-three-three network architecture and learning optimization mechanism for B5G/6G [J]. Journal on Communications, 2021, 42(4): 62-75.
[2]	Wufei WU,Renfa LI,Gang ZENG,Yong XIE,Guoqi XIE. Survey of the intelligent and connected vehicle cybersecurity [J]. Journal on Communications, 2020, 41(6): 161-174.
[3]	Ying GUO,Lun LI,Peng WANG. Real time interpolation algorithm based on Lanczos kernel [J]. Journal on Communications, 2017, 38(6): 142-147.
[4]	Quan CHEN,Hong GAO. Dynamic switching based real-time routing in low-duty-cycle wireless sensor networks [J]. Journal on Communications, 2015, 36(10): 224-234.
[5]	Quan CHEN,Hong GAO. Link quality based path delay analysis in wireless sensor networks [J]. Journal on Communications, 2014, 35(6): 100-109.
[6]	. Link quality based path delay analysis in wireless sensor networks [J]. Journal on Communications, 2014, 35(6): 13-109.
[7]	. Spectrum access scheme of MAC layer for real-time traffic in cognitive radio network [J]. Journal on Communications, 2014, 35(4): 5-43.
[8]	Rui-fang LI,Quan LIU,Ren-fa LI. Spectrum access scheme of MAC layer for real-time traffic in cognitive radio network [J]. Journal on Communications, 2014, 35(4): 35-43.
[9]	. Fault-tolerant scheduling algorithm for real-time tasks in virtualized cloud [J]. Journal on Communications, 2014, 35(10): 20-180.
[10]	Ji WANG,Wei-dong BAO,Xiao-min ZHU. Fault-tolerant scheduling algorithm for real-time tasks in virtualized cloud [J]. Journal on Communications, 2014, 35(10): 171-180.
[11]	Quan CHEN,Hong GAO. RSPEED：the reliability and real-time routing based on uncertain delay in wireless sensor network [J]. Journal on Communications, 2013, 34(8): 110-119.
[12]	. RSPEED：the reliability and real-time routing based on uncertain delay in wireless sensor network [J]. Journal on Communications, 2013, 34(8): 15-119.
[13]	Shu-jing JIANG,Bao-qin HEI,Jiu-xing ZHANG,Qian-nan LI. Research on PDE-based adaptive anisotropic image registration [J]. Journal on Communications, 2013, 34(5): 192-199.
[14]	. Research on PDE-based adaptive anisotropic image registration [J]. Journal on Communications, 2013, 34(5): 22-199.
[15]	Guo-qi XIE,Ren-fa LI,Fan YANG,Wei-hong HUANG. Multiple DAG off-line task scheduling for heterogeneous networked automobile electronic systems [J]. Journal on Communications, 2013, 34(12): 20-32.