基于局部哈希学习的大面阵CCD航拍图像匹配方法

陈苏婷; 郭子烨; 张艳艳

doi:doi:10.5768/jao201940.0202003

应用光学, 2019, 40 (2): 259, 网络出版: 2019-03-26

基于局部哈希学习的大面阵CCD航拍图像匹配方法

Matching method of large array CCD aerial images based on local hashing learning

论文大纲

陈苏婷 ^*郭子烨张艳艳

作者单位

南京信息工程大学江苏省气象探测与信息处理重点实验室,江苏南京 210044

CCD航拍图像特征匹配局部哈希学习快速匹配 CCD aerial images feature matching local hash learning fast matching

摘要

为实现大面阵CCD航拍图像准确快速匹配, 提出一种局部多特征哈希学习LMFH(local multi-feature hashing)方法。依据航向重叠率构建预测区域, 在预测区域内检测特征点并进行多特征描述, 以现有上万幅航拍图像为训练样本, 通过哈希函数将高维的特征描述向量映射为紧凑的二进制哈希编码, 在汉明空间通过汉明距离实现特征点的快速匹配。实验结果表明, 相对于SURF算子, LMFH算法在准确度上提高了10%, 匹配时间上减少了0.2 s。LMFH算法可更快更准确地实现CCD航拍图像的匹配。

Abstract

In order to realize the fast and accurate matching of large array charge coupled-device (CDD) aerial images, a local multi-feature hashing (LMFH) method is proposed. Firstly, the prediction area is constructed according to the course overlap rate, and the feature points detected in the area are described by multi-feature. Then, the hash functions are learned by tens of thousands of existing aerial images. Finally, the high-dimensional feature description vectors are mapped to compact binary hash codes by the learned hash functions. Fast hashing matching is achieved according to the Hamming distance in the Hamming space. Experiments show that compared to the classical speeded up robust features (SURF) algorithm, accuracy is improved about 10%, meanwhile, the matching time is decreased 0.2s. The proposed LMFH algorithm for aerial images matching is much more efficient.

参考文献

[1] TRZCINSKI T, CHRISTOUDIAS M, LEPETIT V. Learning image descriptors with boosting［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015,37(3): 597-610.

[2] 罗会兰, 郭敏杰, 孔繁胜. 一种基于多级空间视觉词典集的图像分类方法［J］. 电子学报, 2015, 43 (4): 684-693.

LUO Huilan,GUO Minjie,KONG Fansheng. Image classification based on multi-stage spatial visual lexicon set［J］. Electronic Journal, 2015, 43 (4): 684-693.

[3] 陈清江, 李毅, 柴煜洲, 等. 结合深度学习的非下采样剪切波遥感图像融合［J］. 应用光学. 2018, 39(5): 655-666.

CHEN Qingjiang, LI Yi, CHAI Yuzhou, et al. Remote sensing image fusion based on deep learning non-subsampled shearlet［J］. Journal of Applied Optics, 2018, 39(5): 655-666.

[4] 陈清江, 张彦博, 柴煜洲, 等. 基于改进对比度的有限离散剪切波图像融合［J］. 应用光学, 2016, 37(2): 221-228.

CHEN Qingjiang, ZHANG Yanbo, CHAI Yuzhou, et al. Finite discrete shear wave image fusion based on improved contrast［J］. Journal of Applied Optics, 2016, 37(2): 221-228.

[5] 张琦, 胡广地, 李雨生, 等. 改进Fast-RCNN的双目视觉车辆检测方法［J］. 应用光学, 2018, 39(6): 832-838.

ZHANG Qi, HU Guangdi, LI Yusheng, et al. Binocular vision vehicle detection method based on improved fast-RCNN［J］. Journal of Applied Optics, 2018, 39(6): 832-838.

[6] RUBLEE E, RABAUD V ,KONOLIGE K.Orb: an efficient alternative to sift or surf［J］. IEEE International Conference on Computer Vision, 2011,58(11): 2564-2571.

[7] SUN Y, ZHAO L, HUANG S, et al. L2-SIFT: SIFT feature extraction and matching for large images in large-scale aerial photogrammetry［J］. ISPRS Journal of Photogrammetry & Remote Sensing, 2014, 91: 1-16.

[8] BAY H,TUYTELAARS T, GOOL L V. Speeded up robust features［J］. Computer Vision Image & Underst anding, 2006, 110(3): 404-417.

[9] CALONDER M, LEPETIT V,STRECHA C. Brief: Binary robust independent elementary features［J］. European Conference on Computer Vision, 2010,6314: 778-792.

[10] HAN X, LEUNG T, JIA Y, et al. Matchnet: unifying feature and metric learning for patch-based matching［C］.USA: IEEE, 2015: 3279-3286.

[11] 田伟刚, 郭雷, 黄雷. 一种应用于图像配准中的点特征匹配算法［J］. 微电子学与计算机, 2008, 25(3): 172-174.

TIAN Weigang, GUO Lei, HUANG Lei. Points feature matching algorithm applied to image registration［J］. Microellectronics & Computer, 2008, 25(3): 172-174.

[12] LOWE D. Distinctive image features from scale in variant key points［J］. International Journal of Computer Vision, 2004, 60(2): 91-110.

[13] 毕国玲, 赵建, 续志军,等. 基于角点和局部特征描述子的快速匹配算法［J］. 光电工程, 2014(9): 63-68.

BI Guoling, ZHAO Jian, XU Zhijun, et al. Fast matching algorithn based on corner points and local feature descriptors［J］. Optoelectronic Engineering, 2014(9): 63-68.

[14] 冯伟国. 视频监控中运动对象提取与海量对象快速检索［D］. 合肥: 中国科学技术大学, 2015.

FENG Weiguo. Moving object extraction in video surveillance and fast retrieval of massive objects［D］. Hefei: University of Science & Technology China, 2015.

[15] MIKOLAJCZYK K, SCHMID C. A performance evaluation of local descriptors［C］. USA: IEEE, 2003.

[16] TSAI C, LIN Y. An accelerated image matching technique for UAV orthoimage registration［J］. ISPRS Journal of Photogrammetry and Remote Sensing 2017, 128: 130-145.

陈苏婷, 郭子烨, 张艳艳. 基于局部哈希学习的大面阵CCD航拍图像匹配方法[J]. 应用光学, 2019, 40(2): 259. CHEN Suting, GUO Ziye, ZHANG Yanyan. Matching method of large array CCD aerial images based on local hashing learning[J]. Journal of Applied Optics, 2019, 40(2): 259.

基于局部哈希学习的大面阵CCD航拍图像匹配方法

关于本站 Cookie 的使用提示

全站搜索

基于局部哈希学习的大面阵CCD航拍图像匹配方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索