[1]牟海维,段朝辉*,李 林,等.基于边缘特征和CNN联合的多视航拍图像配准方法[J].工业仪表与自动化装置,2021,(04):87-91+101.[doi:10.19950/j.cnki.cn61-1121/th.2021.04.018]
　MU Haiwei,DUAN Chaohui*,LI Lin,et al.Multi-view aerial image registration method based on edge feature and CNN[J].Industrial Instrumentation & Automation,2021,(04):87-91+101.[doi:10.19950/j.cnki.cn61-1121/th.2021.04.018]
点击复制

基于边缘特征和CNN联合的多视航拍图像配准方法

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2021年04期
页码:
87-91+101
栏目:
出版日期:
2021-08-15

文章信息/Info

Title:
Multi-view aerial image registration method based on edge feature and CNN
作者:
牟海维1; 2; 段朝辉1; 2*; 李 林1; 2; 万 川1; 2; 郭 颖1; 2
1.东北石油大学 物理与电子工程学院；?div>2.东北石油大学黑龙江省高校共建测试计量技术及仪器仪表研发中心，黑龙江 大庆 163318
Author(s):
MU Haiwei1; 2;  DUAN Chaohui1; 2* ;  LI Lin1; 2 ;  WAN Chuan1; 2 ;  GUO Ying1; 2
1. College of Physics and Electronic Engineering, Northeast Petroleum University；
2. Heilongjiang Province Colleges and Universities Co-built Testing and Measurement Technology and Instrumentation R&D Center, Heilongjiang Daqing 163318, China
关键词:
边缘特征; 卷积神经网络; 多视航拍; 图像配准
Keywords:
edge character;  CCN;  multi-angle aerial photography;  image registration
分类号:
TP751.1
DOI:
10.19950/j.cnki.cn61-1121/th.2021.04.018
文献标志码:
A
摘要:
针对传统卷积神经网络对多视航拍图像进行配准训练时，未能充分利用多视图像间边缘特征之间的联系，为了提取多层图像边缘结构之间的特征信息，提出了一种基于边缘特征和卷积神经网络联合的多视航拍图像配准方法，通过窗口灰度加权算法提取图像的边缘特征图，并将边缘特征图作为卷积神经网络的输入端进行训练，在测试阶段，给出一对新的多视航拍图像，训练后的模型可以预测图像间的空间对应关系。实验结果表明，该算法实现了图像对齐变换，提高了图像配准的精度，优于现有的图像配准方法。
Abstract:
For traditional convolution neural network to view aerial image registration more training, failed to make full use of between multiple views as the connection between the edge character, in order to extract the multi-layer image edge structure between the characteristics of the information, this paper proposes a based on edge character and convolutional neural network combined aerial image registration method, through the window gray weighted algorithm to extract image edge character figure, and the edge character figure as a convolution of the neural network input for training, during the testing phase, give a pair of new visual images, more training model can predict the image after the corresponding relationship between the space.Experimental results show that the proposed algorithm achieves image alignment transformation, improves the accuracy of image registration, and is superior to the existing image registration methods.

参考文献/References:

[1] JIN H B . Accurate multispectral image registration based on keypoint descriptors, Doctoral Dissertation[C]. Beijing: Beijing University of Posts and Telecommunications, 2019.
[2] PENG W , QU Z , PING W , et al. A Coarse-to-Fine Matching Algorithm for FLIR and Optical Satellite Image Registration[J]. Geoscience & Remote Sensing Letters IEEE, 2012, 9(4):599-603.
[3] MARTIN S , DURRANI T S . A New Divergence Measure for Medical Image Registration[J]. IEEE Trans Image Process, 2007, 16:957-966.
[4] LEGG P A , ROSIN P L , MARSHALL D , et al. Improving accuracy and efficiency of mutual information for multi-modal retinal image registration using adaptive probability density estimation[J]. Comput Med Imaging Graph, 2013, 37(7–8):597-606.
[5] KOLAR R , HARABIS V , ODSTRCILIK J . Hybrid retinal image registration using phase correlation[J]. Journal of Photographic Science, 2013, 61(4):369-384.
[6] TAGARAEH D , RAO M . Why does mutual-information work for image registration? A deterministic explanation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015 , 37(6):1286-1296.
[7] WOO J , STONE M , PRINCE J L . Multimodal Registration via Mutual Information Incorporating Geometric and Spatial Context[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2015, 24(2):757.
[8] SONG Z L , LI S , GEORGE T F . Remote sensing image registration approach based on a retrofitted SIFT algorithm and Lissajous-curve trajectories[J]. Optics Express, 2010, 18(2):513-522.
[9] MA J , ZHOU H , ZHAO J , et al. Robust feature matching for remote sensing image registration via locally linear transforming[J]. IEEE Transactions on Geoscience & Remote Sensing, 2015, 53(12):6469-6481.
[10] YU D , YANG F , YANG C , et al. Fast rotation-free feature-based image registration using improved N-SIFT and GMM-based parallel optimization[J]. IEEE Transactions on Biomedical Engineering, 2016, 63(8):1653-1664.
[11] PAUL S , DURGAM U K , PATI U C . Multi-modal optical image registration using modified SIFT[C]// ICACNI - 2016. 2016.
[12] GAO B , LU P , WOO W L , et al. Variational bayesian subgroup adaptive sparse component extraction for diagnostic imaging system[J]. IEEE Transactions on Industrial Electronics, 2018:1.
[13] He K , Yan L , Sclaroff S . Local descriptors optimized for average precision[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 2018:596-605.
[14] Ronneberger O , Fischer P , Brox T . U-Net: Convolutional networks for biomedical image segmentation[J]. Springer, Cham, 2015:234–241.

相似文献/References:

[1]张海静,姚博彬＊,武奇生.基于差分数据图和深度学习的短时交通流预测[J].工业仪表与自动化装置,2020,(02):3.
　ZHANG Haijing,YAO Bobin,WU Qisheng.Short-term traffic flow prediction based on the differential data graph and deep learning[J].Industrial Instrumentation & Automation,2020,(04):3.
[2]张晓华,马 煜,杨晨辉,等.基于卷积神经网络的设备安装位置智能识别方法[J].工业仪表与自动化装置,2021,(01):13.[doi:10.3969/j.issn.1000-0682.2021.01.003]
　ZHANG Xiaohua,MA yu,YANG Chenhui,et al.Intelligent identification method of equipment installation position based on convolution neural network[J].Industrial Instrumentation & Automation,2021,(04):13.[doi:10.3969/j.issn.1000-0682.2021.01.003]
[3]甘 李,姚 智,李 闯,等.基于卷积神经网络的汽轮机抗燃油泄漏智能预警技术研究[J].工业仪表与自动化装置,2022,(04):8.[doi:10.19950/j.cnki.cn61-1121/th.2022.04.002]
　GAN Li,YAO Zhi,LI Chuang,et al.Research on intelligent early warning technology of steam turbine anti fuel leakage based on convolutional neural network[J].Industrial Instrumentation & Automation,2022,(04):8.[doi:10.19950/j.cnki.cn61-1121/th.2022.04.002]
[4]李 娜,曹丽明.一种风力发电机轴承故障智能诊断方法[J].工业仪表与自动化装置,2022,(05):103.[doi:10.19950/j.cnki.cn61-1121/th.2022.05.019]
　LI Na,CAO Liming.An intelligent diagnosis method for wind turbine bearing fault[J].Industrial Instrumentation & Automation,2022,(04):103.[doi:10.19950/j.cnki.cn61-1121/th.2022.05.019]
[5]王志波,王继柱.基于光纤光栅传感技术和卷积神经网络的铁路信号调节方法研究[J].工业仪表与自动化装置,2023,(01):91.[doi:10.19950/j.cnki.cn61-1121/th.2023.01.018]
　WANG Zhibo,WANG Jizhu.Research on railway signal regulation based on fiber grating sensing technology and convolutional neural network[J].Industrial Instrumentation & Automation,2023,(04):91.[doi:10.19950/j.cnki.cn61-1121/th.2023.01.018]
[6]徐晓强,丁 峰,毕淑敏.基于高速通信的港口设备远程检测与控制技术研究[J].工业仪表与自动化装置,2024,(05):83.[doi:DOI:10.19950/j.cnki.cn61-1121/th.2024.05.016]
　XU Xiaoqiang,DING Feng,BI Shumin.Design of remote detection and control technology for port equipment based on high-speed mobile communication[J].Industrial Instrumentation & Automation,2024,(04):83.[doi:DOI:10.19950/j.cnki.cn61-1121/th.2024.05.016]
[7]周旭涛,杨泽昀,吴文开.基于多通道并行LSTM-CNN的旋转机械故障诊断[J].工业仪表与自动化装置,2025,(02):92.[doi:10.19950/j.cnki.CN61-1121/TH.2025.02.017]
　ZHUO Xutao,YANG Zeyun,WU Wenkai.Fault diagnosis of rotating machinery based on multi-channel parallel LSTM-CNN[J].Industrial Instrumentation & Automation,2025,(04):92.[doi:10.19950/j.cnki.CN61-1121/TH.2025.02.017]

备注/Memo

备注/Memo:
收稿日期：2021-01-05

基金项目：
国家自然科学基金(51574087)
东北石油大学研究生创新科研项目（JYCX_CX09_2018）

作者简介：
牟海维（1963），男，黑龙江省绥化市，博士，教授，主要研究方向为油气田地质勘探与开发、储层评价与表征。
更新日期/Last Update: 1900-01-01