搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于尺度不变特征变换和区域互信息优化的多源遥感图像配准

赵辽英 吕步云 厉小润 陈淑涵

引用本文:
Citation:

基于尺度不变特征变换和区域互信息优化的多源遥感图像配准

赵辽英, 吕步云, 厉小润, 陈淑涵

Multi-source remote sensing image registration based on scale-invariant feature transform and optimization of regional mutual information

Zhao Liao-Ying, Lü Bu-Yun, Li Xiao-Run, Chen Shu-Han
PDF
导出引用
  • 为了进一步提高遥感图像配准精度, 提出了尺度不变特征变换(SIFT)结合区域互信息优化的遥感图像配准方法. 首先利用混沌序列的随机性和遍历性, 提出一种混沌量子粒子群优化(CQPSO)算法, 在量子粒子群优化(QPSO)算法迭代陷入早熟收敛时, 采用一种新的机理引入混沌序列, 进化粒子克服早熟. 图像配准算法分为预配准和精配准两个过程. 基于SIFT算法提取特征点, 经匹配和有效地外点排除完成预配准, 然后对匹配特征点坐标进行亚像素级微调, 通过最小二乘法求得一系列匹配参数构造初始粒子群, 最后利用混沌量子粒子群优化区域互信息完成精配准, 得到最优匹配参数. 用一些标准测试函数对所提出的CQPSO和QPSO及粒子群优化(PSO)算法进行了实验比较, 另外, 对SIFT, SIFT结合PSO算法优化区域互信息, SIFT结合QPSO算法优化区域互信息和SIFT结合CQPSO算法优化区域互信息(SRC)等四种算法进行了不同分辨率遥感图像配准实验比较和不同时相遥感图像配准实验比较, 实验结果验证了所提出的CQPSO算法的优越性和SRC配准方法的有效性.
    In order to further improve the precision of remote sensing image registration, we propose a new registration scheme by combining the scale-invariant feature transform (SIFT) and the optimization of regional mutual information in this paper. Firstly, taking advantage of the randomness and ergodicity of chaotic sequence, we present a new chaos quantum-behaved particle swarm optimization (CQPSO) algorithm to solve the premature convergence problem of the quantum particle swarm optimization (QPSO) algorithm. By taking full account of the quantity differences among the values of different dimensions for the particle location information, small disturbances are generated as the Hadamard product of chaotic sequence and the particle location information. Before being added to the particle location information, the small disturbances are adjusted by an evolutionary parameter to ensure that each new particle location information is within the scope of reasonable evolution. The image registration scheme consists of two processes, namely the pre-registration process and fine coregistration process. The pre-registration process is implemented by the SIFT approach with a reliable outlier removal procedure. By the repetitive fine-tuning of several selected matched feature point coordinates, a series of registration parameters is estimated by a least square method and used to construct initial particle swarms. Next, the fine coregistration process is implemented to obtain the optimal match parameters by maximizing regional mutual information based on CQPSO. The proposed CQPSO algorithm is tested on several benchmark functions and compared with QPSO as well as standard PSO experimentally. Furthermore, comparative experiments are carried out on the registration of remote sensing images with different ground resolutions and the registration of remote sensing images at different phases by using four algorithms: the SIFT algorithm, SIFT combined with PSO algorithm, SIFT combined with QPSO algorithm, and SIFT combined with CQPSO algorithm. The regional mutual information, root mean square error, and the joint histogram are used to evaluate the performance of the algorithms. The experimental results verify the superiority of CQPSO and the effectiveness of the proposed registration scheme.
    • 基金项目: 浙江省自然科学基金(批准号:LY13F020044,LZ14F030004)和国家自然科学基金(批准号:61171152)资助的课题.
    • Funds: Project supported by the Natural Science Foundation of Zhejiang Province, China (Grant Nos. LY13F020044, LZ14F030004) and the National Natural Science Foundation of China (Grant No. 61171152).
    [1]

    Chen Z G, Yin F C, Sun F 2009 Acta Opt. Sin. 29 2744 (in Chinese) [陈志刚, 尹福昌, 孙孚 2009 光学学报 29 2744]

    [2]

    Xie W D, Zhou Y H, Kou R L 2011 J. Tongji Univ. (Nat. Sci.) 39 1233 (in Chinese) [谢维达, 周宇恒, 寇若岚 2011 同济大学学报(自然科学版) 39 1233]

    [3]

    Chen Q S, Defrise M, Deconinck M 1994 IEEE Trans. Pattern Anal. Mach. Intell. 16 1156

    [4]

    Suri S, Reinartz P 2010 IEEE Trans. Geosci. Remote Sens. 48 939

    [5]

    Lowe D G 2004 Int. J. Comput Vision 60 91

    [6]

    Harris C, Stephens M 1988 Proceedings of Fourth Alvey Vision Conference Manchester, UK, August 31-September 2, 1988 p147

    [7]

    Ling Z G, Liang Y, Cheng Y M, Pan Q, Shen H 2010 Acta Electron. Sin. 38 2892 (in Chinese) [凌志刚, 梁彦, 程咏梅, 潘泉, 沈贺 2010 电子学报 38 2892]

    [8]

    Li L X 2013 M.S.Dissertation (Chengdu: University of Electronic Science and Technology of China) (in Chinese) [李龙勋 2013 硕士学位论文 (成都: 电子科技大学)]

    [9]

    Huang Q Q, Yang J, Wang C Y, Chen J B, Meng Y 2012 International Geoscience and Remote Sensing Symposium (IGARSS) Munich, Germany, July 22-27, 2012 p2360

    [10]

    Gong M G, Zhao S M, Jiao L C, Tian D Y, Wang S 2014 IEEE Trans. Geosci. Remote Sens. 52 4328

    [11]

    Liang J Y, Liu X P, Huang K N, Li X, Wang D G, Wang X W 2014 IEEE Trans. Geosci. Remote Sens. 52 603

    [12]

    Mikolajczyk K, Schmid C 2003 IEEE Trans. Geosci. Remote Sens. 41 2445

    [13]

    Wang C X, Kong Y P, Dong L L 2012 Intelligent Optimization Algorithms and Their Applications (Xi’an: Xibei University Press) p105 (in Chinese) [王超学, 孔月萍, 董丽丽 2012 智能优化算法与应用 (西安: 西北大学出版社) 第105页]

    [14]

    Sun J 2012 Acta Phys. Sin. 61 060302 (in Chinese) [李盼池, 王海英, 宋考平, 杨二龙 2012 物理学报 61 060302]

    [15]

    Li X R, Jin Y X 2014 Acta Phys. Sin. 63 089101 (in Chinese) [王跃钢, 文超斌, 左朝阳, 杨家胜, 郭志斌 2014 物理学报 63 089101]

    [16]

    Liu F C, Jia Y F, Ren L N 2013 Acta Phys. Sin. 62 120509 (in Chinese) [刘福才, 贾亚飞, 任丽娜 2013 物理学报 62 120509]

  • [1]

    Chen Z G, Yin F C, Sun F 2009 Acta Opt. Sin. 29 2744 (in Chinese) [陈志刚, 尹福昌, 孙孚 2009 光学学报 29 2744]

    [2]

    Xie W D, Zhou Y H, Kou R L 2011 J. Tongji Univ. (Nat. Sci.) 39 1233 (in Chinese) [谢维达, 周宇恒, 寇若岚 2011 同济大学学报(自然科学版) 39 1233]

    [3]

    Chen Q S, Defrise M, Deconinck M 1994 IEEE Trans. Pattern Anal. Mach. Intell. 16 1156

    [4]

    Suri S, Reinartz P 2010 IEEE Trans. Geosci. Remote Sens. 48 939

    [5]

    Lowe D G 2004 Int. J. Comput Vision 60 91

    [6]

    Harris C, Stephens M 1988 Proceedings of Fourth Alvey Vision Conference Manchester, UK, August 31-September 2, 1988 p147

    [7]

    Ling Z G, Liang Y, Cheng Y M, Pan Q, Shen H 2010 Acta Electron. Sin. 38 2892 (in Chinese) [凌志刚, 梁彦, 程咏梅, 潘泉, 沈贺 2010 电子学报 38 2892]

    [8]

    Li L X 2013 M.S.Dissertation (Chengdu: University of Electronic Science and Technology of China) (in Chinese) [李龙勋 2013 硕士学位论文 (成都: 电子科技大学)]

    [9]

    Huang Q Q, Yang J, Wang C Y, Chen J B, Meng Y 2012 International Geoscience and Remote Sensing Symposium (IGARSS) Munich, Germany, July 22-27, 2012 p2360

    [10]

    Gong M G, Zhao S M, Jiao L C, Tian D Y, Wang S 2014 IEEE Trans. Geosci. Remote Sens. 52 4328

    [11]

    Liang J Y, Liu X P, Huang K N, Li X, Wang D G, Wang X W 2014 IEEE Trans. Geosci. Remote Sens. 52 603

    [12]

    Mikolajczyk K, Schmid C 2003 IEEE Trans. Geosci. Remote Sens. 41 2445

    [13]

    Wang C X, Kong Y P, Dong L L 2012 Intelligent Optimization Algorithms and Their Applications (Xi’an: Xibei University Press) p105 (in Chinese) [王超学, 孔月萍, 董丽丽 2012 智能优化算法与应用 (西安: 西北大学出版社) 第105页]

    [14]

    Sun J 2012 Acta Phys. Sin. 61 060302 (in Chinese) [李盼池, 王海英, 宋考平, 杨二龙 2012 物理学报 61 060302]

    [15]

    Li X R, Jin Y X 2014 Acta Phys. Sin. 63 089101 (in Chinese) [王跃钢, 文超斌, 左朝阳, 杨家胜, 郭志斌 2014 物理学报 63 089101]

    [16]

    Liu F C, Jia Y F, Ren L N 2013 Acta Phys. Sin. 62 120509 (in Chinese) [刘福才, 贾亚飞, 任丽娜 2013 物理学报 62 120509]

  • [1] 张银胜, 童俊毅, 陈戈, 单梦姣, 王硕洋, 单慧琳. 基于多尺度特征增强的合成孔径光学图像复原. 物理学报, 2024, 73(6): 064203. doi: 10.7498/aps.73.20231761
    [2] 林丹樱, 龚振权, 黄黎琳, 聂梦娇, 于斌, 屈军乐. 用于多通道单分子定位的高精度图像配准方法. 物理学报, 2024, 73(6): 068701. doi: 10.7498/aps.73.20231695
    [3] 孙振辉, 胡丽贞, 徐玉良, 孔祥木. 准一维混合自旋(1/2, 5/2) Ising-XXZ模型的量子相干和互信息. 物理学报, 2023, 72(13): 130301. doi: 10.7498/aps.72.20230381
    [4] 苏博, 陶芬, 李可, 杜国浩, 张玲, 李中亮, 邓彪, 谢红兰, 肖体乔. 同步辐射纳米CT图像配准方法研究. 物理学报, 2021, 70(16): 160704. doi: 10.7498/aps.70.20210156
    [5] 孙延风, 王朝勇. 一种基于文本互信息的金融复杂网络模型. 物理学报, 2018, 67(14): 148901. doi: 10.7498/aps.67.20172490
    [6] 黄宇, 刘玉峰, 彭志敏, 丁艳军. 基于量子并行粒子群优化算法的分数阶混沌系统参数估计. 物理学报, 2015, 64(3): 030505. doi: 10.7498/aps.64.030505
    [7] 李一博, 张博林, 刘自鑫, 张震宇. 基于量子粒子群算法的自适应随机共振方法研究. 物理学报, 2014, 63(16): 160504. doi: 10.7498/aps.63.160504
    [8] 刘福才, 贾亚飞, 任丽娜. 基于混沌粒子群优化算法的异结构混沌反同步自抗扰控制. 物理学报, 2013, 62(12): 120509. doi: 10.7498/aps.62.120509
    [9] 张梅, 崔超, 马千里, 干宗良, 王俊. 基于符号化部分互信息熵的多参数生物电信号的耦合分析. 物理学报, 2013, 62(6): 068704. doi: 10.7498/aps.62.068704
    [10] 张宏立, 宋莉莉. 基于量子粒子群算法的混沌系统参数辨识. 物理学报, 2013, 62(19): 190508. doi: 10.7498/aps.62.190508
    [11] 甘甜, 冯少彤, 聂守平, 朱竹青. 基于分块离散小波变换的图像信息隐藏与盲提取算法. 物理学报, 2012, 61(8): 084203. doi: 10.7498/aps.61.084203
    [12] 李盼池, 王海英, 宋考平, 杨二龙. 量子势阱粒子群优化算法的改进研究. 物理学报, 2012, 61(6): 060302. doi: 10.7498/aps.61.060302
    [13] 郭业才, 胡苓苓, 丁锐. 基于量子粒子群优化的正交小波加权多模盲均衡算法. 物理学报, 2012, 61(5): 054304. doi: 10.7498/aps.61.054304
    [14] 方伟, 孙俊, 谢振平, 须文波. 量子粒子群优化算法的收敛性分析及控制参数研究. 物理学报, 2010, 59(6): 3686-3694. doi: 10.7498/aps.59.3686
    [15] 李爱民, 李子平. 规范不变系统量子水平的变换性质及应用. 物理学报, 2008, 57(12): 7571-7576. doi: 10.7498/aps.57.7571
    [16] 张佃中. 非线性时间序列互信息与Lempel-Ziv复杂度的相关性研究. 物理学报, 2007, 56(6): 3152-3157. doi: 10.7498/aps.56.3152
    [17] 肖海林, 聂在平. 一种研究二元对称离散信道平均互信息的新方法. 物理学报, 2007, 56(4): 1948-1951. doi: 10.7498/aps.56.1948
    [18] 高 飞, 童恒庆. 基于改进粒子群优化算法的混沌系统参数估计方法. 物理学报, 2006, 55(2): 577-582. doi: 10.7498/aps.55.577
    [19] 王东风, 韩 璞. 基于粒子群优化的混沌系统比例-积分-微分控制. 物理学报, 2006, 55(4): 1644-1650. doi: 10.7498/aps.55.1644
    [20] 程南璞, 郑仁蓉, 朱顺泉. 准粒子特征与奇奇核的能谱统计. 物理学报, 2001, 50(6): 1035-1039. doi: 10.7498/aps.50.1035
计量
  • 文章访问数:  6112
  • PDF下载量:  275
  • 被引次数: 0
出版历程
  • 收稿日期:  2014-10-20
  • 修回日期:  2014-11-27
  • 刊出日期:  2015-06-05

/

返回文章
返回