快速鲁棒性非线性尺度不变的特征匹配算子 -- 西北工业大学学报,2016,34(6):1108-1119
论文:2016,Vol:34,Issue(6):1108-1119
引用本文:
张岩, 李建增, 李德良, 杜玉龙. 快速鲁棒性非线性尺度不变的特征匹配算子[J]. 西北工业大学学报
Zhang Yan, Li Jianzeng, Li Deliang, Du Yulong. Speeded up Robust Nonlinear Scale-Invariant Feature[J]. Northwestern polytechnical university

快速鲁棒性非线性尺度不变的特征匹配算子
张岩, 李建增, 李德良, 杜玉龙
军械工程学院, 河北 石家庄 050003
摘要:
提出了一种快速鲁棒性非线性尺度不变的特征匹配算子(speeded up robust nonlinear scale invariant feature,SURNSIF),通过检测子非线性尺度空间的快速求解去除了噪声,同时保证了图像边缘细节,并将自适应选取尺度空间组数、adaptive and generic corner detection based on the accelerated segment test(AGAST)与框状拉普拉斯滤波器去除边缘响应相结合,兼顾了检测的准确性与实时性;描述子交叠带的构建、规范微分响应与非线性尺度空间约束的引入增强了描绘准确性。通过与scale invariant feature transform(SIFT)、speeded up robust features(SURF)、KAZE、binary robust invariant scalable keypoints(BRISK)、AGAST以及快速海森(fast-Hessian)的实验对比,SURNSIF的5种变换鲁棒性均较强,同时速度也更快,综合性能较KAZE提高约10.87%,速度提高约47%。
关键词:    特征匹配    SURNSIF    KAZE    AGAST   
Speeded up Robust Nonlinear Scale-Invariant Feature
Zhang Yan, Li Jianzeng, Li Deliang, Du Yulong
Ordnance Engineering College, Shijiazhuang 050003, China
Abstract:
This paper puts forward a speeded up robust nonlinear scale invariant feature(SURNSIF). Noise is wiped off and edge response is guaranteed through the fast solving of nonlinear scale space. Adaptive selection of number of scale space and the Adaptive and Generic corner detection based on the accelerated segment test(AGAST), combined with frame Laplace filter via removing edge response take account of the detection accuracy and real-time performance. Constructing descriptor overlap, introduction of gauge derivatives and the constraint of feature point in the nonlinear scale space location enhance the accuracy. Comparing to scale invariant feature transform(SIFT), speeded up robust features(SURF), KAZE, binary robust invariant scalable keypoints(BRISK), AGAST and fast-Hessian experiments, the SURNSIF reveals stronger robustness with 5 kinds of changes, and its registration speed is faster. Compared with KAZE, comprehensive robustness is increased about 10.87%, and the speed is increased about 47%.
Key words:    feature registration    SURNSIF    KAZE    AGAST   
收稿日期: 2016-03-08     修回日期:
DOI:
基金项目: 国家自然科学基金(51307183)资助
通讯作者:     Email:
作者简介: 张岩(1991-),军械工程学院博士研究生,主要从事计算机视觉与无人机图像信息处理技术研究。
相关功能
PDF(7638KB) Free
打印本文
把本文推荐给朋友
作者相关文章
张岩  在本刊中的所有文章
李建增  在本刊中的所有文章
李德良  在本刊中的所有文章
杜玉龙  在本刊中的所有文章

参考文献:
[1] 樊曼曼. 多源卫星遥感影像配准技术研究[D]. 秦皇岛:燕山大学, 2011 Fan Manman. Resarch of Multi-Source Image Matching Technology[D]. Qinhuangdao, Yanshan University, 2011(in Chinese)
[2] 宋芳, 李勇, 陈勇. 多源遥感图像中的图像配准方法[J]. 激光杂志, 2008, 29(3):26-27 Song Fang, Li Yong, Chen Yong. Match Methods for Multisensor Remote Sensing Image Registration[J]. Laser Journal, 2008, 29(3):26-27(in Chinese)
[3] 廖斌. 基于特征点的图像配准技术研究[D]. 长沙:国防科学技术大学, 2008 Liao Bin. Feature Aided Target Maneuver Detection Technology[D]. Changsha, National University of Defense Technology, 2008(in Chinese)
[4] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110
[5] Bay H, Tuytelaars T, Van Gool L. SURF:Speeded Up Robust Features[C]//Proceedings of 9th European Conference on Computer Vision. Graz, Austria:Springer Berlin Heidelberg, 2006:404-417
[6] Calonder M, Lepetit V, Strecha C, et al. Brief:Binary Robust Independent Elementary Features[C]//Proceedings of 11th European Conference on Computer Vision Crete, Greece:Springer Berlin Heidelberg, 2010:778-792
[7] Leutenegger S, Chli M, Siegwart R Y. BRISK:Binary Robust Invariant Scalable Keypoints[C]//Proceedings of 2011 International Conference on Computer Barcelona, Spain, 2011:2548-2555
[8] Mair E, Hager G D, Burschka D, et al. Adaptive and Generic Corner Detection Based on the Accelerated Segment Test[C]//Proceedings of 11th European Conference on Computer, Heraklion, Crete, Greece:Springer Berlin Heidelberg, 2010:183-196
[9] Alahi A, Ortiz R, Vanderrgheynst P. FREAK:Fast Retina Keypoint[C]//Proceedings of Computer Version and Pattern Recognition, 2011:510-517
[10] Pablo F, Adrien B, Andrew J. KAZE Features[C]//Proceedings of 12th European Conference on Computer Version, Florence, Italy:Springer Berlin Heidelberg, 2012:214-227
[11] 李鹏, 武文波, 王宗伟. 基于非线性尺度空间的多源遥感影像匹配[J]. 测绘科学, 2015, 40(7):41-44 Li Peng, Wu Wenbo, Wang Zongwei. Muti-Source Remote Sensing Images Matching Based on Nonlinear Scale Space[J]. Science of Surveying and Mapping, 2015, 40(7):41-44(in Chinese)
[12] Pablo F, Jesus N, Adrien B. Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces[C]//Proceedings of 2013 British Machine Vision Conference. Bristol, UK, 2013:2157-2163
[13] Edward R, Tom D. Machine Learning for High-Speed Corner Detection[C]//Proceedings of 9th European Conference on Computer Vision, Graz, Austria, 2006:430-443
[14] 胡波. 基于颜色不变量的特征匹配算法研究[D]. 沈阳:辽宁大学, 2014 Hu Bo. Study of Feature Matching Algorithm Based on Color Invariant[D]. Shengyang, Liaoning University, 2014(in Chinese)
[15] 王飞宇, 邸男, 贾平. 结合尺度空间FAST角点检测器和SURF描绘器的图像特征[J]. 液晶与显示, 2014, 29(4):598-604 Wang Feiyu, Di Nan, Jia Ping. Image Features Using Scale-Space FAST Corner Detector and SURF Descriptor[J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(4):598-604(in Chinese)
[16] Pablo F, Luis M, Andrew J. Gauge-SURF Descriptor[J]. Image and Vision Computing, 2013, 31(1):103-116
[17] 余淮, 杨文. 一种无人机航拍影像快速特征提取与匹配算法[J]. 电子与信息学报, 2016, 38(3):509-516 Yu Huai, Yang Wen. A Fast Feature Extraction and Matching Algorithm for Unmanned Aerial Vehicle Images[J]. Journal of Electronics and Information Technology, 2016, 38(3):509-516(in Chinese)
[18] 张宝龙, 李洪蕊, 李丹, 等. 一种针对车载全景系统的图像拼接算法的仿真[J]. 电子与信息学报, 2015, 37(5):1149-1153 Zhang Baolong, Li Hongrui, Li Dan, et al. A Simulation of Image Mosaic Algorithm Based on Vehicle Panorama System[J]. Journal of Electronics and Information Technology, 2015, 37(5):1149-1153(in Chinese)
[19] Mikolajczyk K, Tuytelaars T, Schmid C, et al. A Comparison of Affine Region Detectors[J]. International Journal of Computer Vision, 2005, 65(1/2):43-72(in Chinese)
[20] Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(10):1615-1630
[21] Winder S A J, Brown M. Learning Local Image Descriptors[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, Redmond, 2007:1-8
[22] Chum O, Matas J. Matching with PROSAC-Progressive Sample Consensus[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Minneapolis, 2005:220-226