scholarly journals ROBUST REGISTRATION FOR OPTICAL AND SAR IMAGES BASED ON SPATIAL GEOMETRIC CONSTRAINT AND STRUCTURE FEATURES

2020 ◽  
Vol V-1-2020 ◽  
pp. 117-124
Author(s):  
M. Wang ◽  
Y. Ye ◽  
M. Sun ◽  
X. Tan ◽  
L. Li
Keyword(s):  
Template Matching ◽  
Three Dimensional ◽  
Phase Correlation ◽  
Geometric Constraint ◽  
Feature Descriptor ◽  
Automatic Registration ◽  
Geometric Correction ◽  
Registration Accuracy ◽  
Sar Images ◽  
Registration Method

Abstract. Automatic registration of optical and synthetic aperture radar (SAR) images is a challenging task due to significant geometric deformation and radiometric differences between two images. To address this issue, this paper proposes an automatic registration method for optical and SAR images based on spatial geometric constraint and structure features. Firstly, the Harris detector with a block strategy is used to extract evenly distributed feature points in the images. Subsequently, a local geometric correction is performed by using the Rational Function Model, which eliminates the rotation and scale differences between optical and SAR images. Secondly, orientated gradient information of images is used to construct a geometric structural feature descriptor. Then, the feature descriptor is transformed into the frequency domain, and the three-dimensional (3-D) phase correlation is used as the similarity metric to achieve correspondences by employing a template matching scheme. Finally, mismatches are eliminated based on spatial geometric constraint relationship between images, followed by a process of geometric correction to achieve the image registration. Experimental results with multiple high-resolution optical and SAR images show that the proposed method can achieve reliable registration accuracy, and outperforms the state of the art methods.

scholarly journals A Methodology of Three-Dimensional Medical Image Registration Based on Conformal Geometric Invariant

2014 ◽  
Vol 2014 ◽  
pp. 1-8
Author(s):  
Liang Hua ◽  
Kean Yu ◽  
Lijun Ding ◽  
Juping Gu ◽  
Xinsong Zhang ◽  
...  
Keyword(s):  
Image Registration ◽  
Medical Image ◽  
Subjective Evaluation ◽  
Three Dimensional ◽  
Medical Image Registration ◽  
Geometric Invariant ◽  
Registration Accuracy ◽  
Registration Method ◽  
Cloud Data ◽  
Dual Vector

A three-dimensional multimodality medical image registration method using geometric invariant based on conformal geometric algebra (CGA) theory is put forward for responding to challenges resulting from many free degrees and computational burdens with 3D medical image registration problems. The mathematical model and calculation method of dual-vector projection invariant are established using the distribution characteristics of point cloud data and the point-to-plane distance-based measurement in CGA space. The translation operator and geometric rotation operator during registration operation are built in Clifford algebra (CA) space. The conformal geometrical algebra is used to realize the registration of 3D CT/MR-PD medical image data based on the dual vector geometric invariant. The registration experiment results indicate that the methodology proposed in this paper is of stronger commonality, less computation burden, shorter time consumption, and intuitive geometric meaning. Both subjective evaluation and objective indicators show that the methodology proposed here is of high registration accuracy and suitable for 3D medical image registration.

scholarly journals Exploiting High Geopositioning Accuracy of SAR Data to Obtain Accurate Geometric Orientation of Optical Satellite Images

2021 ◽  
Vol 13 (17) ◽  
pp. 3535
Author(s):  
Zhongli Fan ◽  
Li Zhang ◽  
Yuxuan Liu ◽  
Qingdong Wang ◽  
Sisi Zlatanova
Keyword(s):  
Satellite Imagery ◽  
Image Matching ◽  
Satellite Images ◽  
Three Dimensional ◽  
Phase Correlation ◽  
Feature Descriptor ◽  
Matching Method ◽  
Reference Images ◽  
Sar Data ◽  
Optical Satellite Images

Accurate geopositioning of optical satellite imagery is a fundamental step for many photogrammetric applications. Considering the imaging principle and data processing manner, SAR satellites can achieve high geopositioning accuracy. Therefore, SAR data can be a reliable source for providing control information in the orientation of optical satellite images. This paper proposes a practical solution for an accurate orientation of optical satellite images using SAR reference images to take advantage of the merits of SAR data. Firstly, we propose an accurate and robust multimodal image matching method to match the SAR and optical satellite images. This approach includes the development of a new structural-based multimodal applicable feature descriptor that employs angle-weighted oriented gradients (AWOGs) and the utilization of a three-dimensional phase correlation similarity measure. Secondly, we put forward a general optical satellite imagery orientation framework based on multiple SAR reference images, which uses the matches of the SAR and optical satellite images as virtual control points. A large number of experiments not only demonstrate the superiority of the proposed matching method compared to the state-of-the-art methods but also prove the effectiveness of the proposed orientation framework. In particular, the matching performance is improved by about 17% compared with the latest multimodal image matching method, namely, CFOG, and the geopositioning accuracy of optical satellite images is improved, from more than 200 to around 8 m.

scholarly journals UAV Remote Sensing Image Automatic Registration Based on Deep Residual Features

2021 ◽  
Vol 13 (18) ◽  
pp. 3605
Author(s):  
Xin Luo ◽  
Guangling Lai ◽  
Xiao Wang ◽  
Yuwei Jin ◽  
Xixu He ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Rapid Development ◽  
Image Features ◽  
Automatic Registration ◽  
Remote Sensing Images ◽  
Registration Accuracy ◽  
Registration Method ◽  
Uav Images ◽  
High Level

With the rapid development of unmanned aerial vehicle (UAV) technology, UAV remote sensing images are increasing sharply. However, due to the limitation of the perspective of UAV remote sensing, the UAV images obtained from different viewpoints of a same scene need to be stitched together for further applications. Therefore, an automatic registration method of UAV remote sensing images based on deep residual features is proposed in this work. It needs no additional training and does not depend on image features, such as points, lines and shapes, or on specific image contents. This registration framework is built as follows: Aimed at the problem that most of traditional registration methods only use low-level features for registration, we adopted deep residual neural network features extracted by an excellent deep neural network, ResNet-50. Then, a tensor product was employed to construct feature description vectors through exacted high-level abstract features. At last, the progressive consistency algorithm (PROSAC) was exploited to remove false matches and fit a geometric transform model so as to enhance registration accuracy. The experimental results for different typical scene images with different resolutions acquired by different UAV image sensors indicate that the improved algorithm can achieve higher registration accuracy than a state-of-the-art deep learning registration algorithm and other popular registration algorithms.

scholarly journals FAST AND ROBUST REGISTRATION OF AERIAL IMAGES AND LIDAR DATA BASED ON STRUCTURAL FEATURES AND 3D PHASE CORRELATION

2020 ◽  
Vol V-2-2020 ◽  
pp. 135-141
Author(s):  
B. Zhu ◽  
Y. Ye ◽  
C. Yang ◽  
L. Zhou ◽  
H. Liu ◽  
...  
Keyword(s):  
Structural Features ◽  
Phase Correlation ◽  
Aerial Images ◽  
Aerial Image ◽  
Reference Image ◽  
Feature Descriptor ◽  
Lidar Data ◽  
Three Dimension ◽  
Interest Points ◽  
Registration Method

Abstract. Co-Registration of aerial imagery and Light Detection and Ranging (LiDAR) data is quilt challenging because the different imaging mechanism causes significant geometric and radiometric distortions between such data. To tackle the problem, this paper proposes an automatic registration method based on structural features and three-dimension (3D) phase correlation. In the proposed method, the LiDAR point cloud data is first transformed into the intensity map, which is used as the reference image. Then, we employ the Fast operator to extract uniformly distributed interest points in the aerial image by a partition strategy and perform a local geometric correction by using the collinearity equation to eliminate scale and rotation difference between images. Subsequently, a robust structural feature descriptor is build based on dense gradient features, and the 3D phase correlation is used to detect control points (CPs) between aerial images and LiDAR data in the frequency domain, where the image matching is accelerated by the 3D Fast Fourier Transform (FFT). Finally, the obtained CPs are employed to correct the exterior orientation elements, which is used to achieve co-registration of aerial images and LiDAR data. Experiments with two datasets of aerial images and LiDAR data show that the proposed method is much faster and more robust than state of the art methods.

MAGNETOENCEPHALOGRAPHY–ELECTROENCEPHALOGRAPHY CO-REGISTRATION USING 3D GENERALIZED HOUGH TRANSFORM

2020 ◽  
Vol 32 (03) ◽  
pp. 2050024
Author(s):  
Sheng-Kai Lin ◽  
Rong-Chin Lo ◽  
Ren-Guey Lee
Keyword(s):  
Hough Transform ◽  
Quantum Interference ◽  
Three Dimensional ◽  
Image Data ◽  
Epileptic Activity ◽  
High Temporal Resolution ◽  
Accuracy Evaluation ◽  
Registration Accuracy ◽  
Registration Method ◽  
Generalized Hough Transform

This study proposes an advanced co-registration method for an integrated high temporal resolution electroencephalography (EEG) and magnetoencephalography (MEG) data. The MEG has a higher accuracy for source localization techniques and spatial resolution by sensing magnetic fields generated by the entire brain using multichannel superconducting quantum interference devices, whereas EEG can record electrical activities from larger cortical surface to detect epilepsy. However, by integrating the two modality tools, we can accurately localize the epileptic activity compared to other non-invasive modalities. Integrating the two modality tools is challenging and important. This study proposes a new algorithm using an extended three-dimensional generalized Hough transform (3D GHT) to co-register the two modality data. The pre-process steps require the locations of EEG electrodes, MEG sensors, head-shape points of subjects and fiducial landmarks. The conventional GHT algorithm is a well-known method used for identifying or locating two 2D images. This study proposes a new co-registration method that extends the 2D GHT algorithm to a 3D GHT algorithm that can automatically co-register 3D image data. It is important to study the prospective brain source activity in bio-signal analysis. Furthermore, the study examines the registration accuracy evaluation by calculating the root mean square of the Euclidean distance of MEG–EEG co-registration data. Several experimental results are used to show that the proposed method for co-registering the two modality data is accurate and efficient. The results demonstrate that the proposed method is feasible, sufficiently automatic, and fast for investigating brain source images.

scholarly journals Improving Co-Registration for Sentinel-1 SAR and Sentinel-2 Optical Images

2021 ◽  
Vol 13 (5) ◽  
pp. 928
Author(s):  
Yuanxin Ye ◽  
Chao Yang ◽  
Bai Zhu ◽  
Liang Zhou ◽  
Youquan He ◽  
...  
Keyword(s):  
European Space Agency ◽  
Phase Correlation ◽  
Optical Data ◽  
Geometric Transformation ◽  
Interest Points ◽  
Registration Accuracy ◽  
Registration Method ◽  
Sensing Applications ◽  
Optical Images ◽  
Sentinel 2

Co-registering the Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical data of the European Space Agency (ESA) is of great importance for many remote sensing applications. However, we find that there are evident misregistration shifts between the Sentinel-1 SAR and Sentinel-2 optical images that are directly downloaded from the official website. To address that, this paper presents a fast and effective registration method for the two types of images. In the proposed method, a block-based scheme is first designed to extract evenly distributed interest points. Then, the correspondences are detected by using the similarity of structural features between the SAR and optical images, where the three-dimensional (3D) phase correlation (PC) is used as the similarity measure for accelerating image matching. Lastly, the obtained correspondences are employed to measure the misregistration shifts between the images. Moreover, to eliminate the misregistration, we use some representative geometric transformation models such as polynomial models, projective models, and rational function models for the co-registration of the two types of images, and we compare and analyze their registration accuracy under different numbers of control points and different terrains. Six pairs of the Sentinel-1 SAR L1 and Sentinel-2 optical L1C images covering three different terrains are tested in our experiments. Experimental results show that the proposed method can achieve precise correspondences between the images, and the third-order polynomial achieves the most satisfactory registration results. Its registration accuracy of the flat areas is less than 1.0 10 m pixel, that of the hilly areas is about 1.5 10 m pixels, and that of the mountainous areas is between 1.7 and 2.3 10 m pixels, which significantly improves the co-registration accuracy of the Sentinel-1 SAR and Sentinel-2 optical images.

scholarly journals An Infrared-Visible Image Registration Method Based on the Constrained Point Feature

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1188
Author(s):  
Qingqing Li ◽  
Guangliang Han ◽  
Peixun Liu ◽  
Hang Yang ◽  
Huiyuan Luo ◽  
...  
Keyword(s):  
Image Registration ◽  
Evaluation Method ◽  
Detection Algorithm ◽  
Feature Descriptor ◽  
Registration Accuracy ◽  
Visible Image ◽  
Registration Method ◽  
Visible Images ◽  
Image Pairs ◽  
Point Feature

It is difficult to find correct correspondences for infrared and visible image registration because of different imaging principles. Traditional registration methods based on the point feature require designing the complicated feature descriptor and eliminate mismatched points, which results in unsatisfactory precision and much calculation time. To tackle these problems, this paper presents an artful method based on constrained point features to align infrared and visible images. The proposed method principally contains three steps. First, constrained point features are extracted by employing an object detection algorithm, which avoids constructing the complex feature descriptor and introduces the senior semantic information to improve the registration accuracy. Then, the left value rule (LV-rule) is designed to match constrained points strictly without the deletion of mismatched and redundant points. Finally, the affine transformation matrix is calculated according to matched point pairs. Moreover, this paper presents an evaluation method to automatically estimate registration accuracy. The proposed method is tested on a public dataset. Among all tested infrared-visible image pairs, registration results demonstrate that the proposed framework outperforms five state-of-the-art registration algorithms in terms of accuracy, speed, and robustness.

scholarly journals Automatic Registration Of SAR And Optical Image Based On Line And Graph Spectral Theory

2014 ◽  
Vol XL-4 ◽  
pp. 377-382 ◽  
Author(s):  
J. Zhao ◽  
S. Gao ◽  
H. Sui ◽  
Y. Li ◽  
L. Li
Keyword(s):  
Spectral Theory ◽  
Voronoi Diagrams ◽  
Automatic Registration ◽  
Point Sets ◽  
Sar Images ◽  
Registration Method ◽  
On Line ◽  
Line Features ◽  
Reliability And Robustness ◽  
Relationship Of

In this paper, a novel registration method is proposed by integrating the graph spectral theory and line features. The principal steps of our algorithm are as follows. Firstly, the images are filtered to enhance the reliability and robustness of registration, and line features are acquired by Hough Transform. Secondly, the original point features can be obtained by calculating the line intersections. The points are normalized to reduce computational complexity. Thirdly, voronoi diagrams of two point sets are extracted respectively. The original corresponding point sets are determined by corresponding voronoi diagrams, which can be obtained by Graph Spectral Theory. At last, RANSAC is used to remove the wrong corresponding points. The transform relationship of the two input images can be achieved using the corresponding point sets. The experimental results show that the proposed method can achieve high accuracy for the registration between optical and SAR images.

scholarly journals FAST AND ROBUST REGISTRATION OF MULTIMODAL REMOTE SENSING IMAGES VIA DENSE ORIENTATED GRADIENT FEATURE

2017 ◽  
Vol XLII-2/W7 ◽  
pp. 1009-1015 ◽  
Author(s):  
Y. Ye
Keyword(s):  
Remote Sensing ◽  
Computational Efficiency ◽  
Template Matching ◽  
Remote Sensing Data ◽  
Experimental Results ◽  
Feature Descriptor ◽  
Remote Sensing Images ◽  
Registration Accuracy ◽  
Registration System ◽  
Similarity Metric

This paper presents a fast and robust method for the registration of multimodal remote sensing data (e.g., optical, LiDAR, SAR and map). The proposed method is based on the hypothesis that structural similarity between images is preserved across different modalities. In the definition of the proposed method, we first develop a pixel-wise feature descriptor named Dense Orientated Gradient Histogram (DOGH), which can be computed effectively at every pixel and is robust to non-linear intensity differences between images. Then a fast similarity metric based on DOGH is built in frequency domain using the Fast Fourier Transform (FFT) technique. Finally, a template matching scheme is applied to detect tie points between images. Experimental results on different types of multimodal remote sensing images show that the proposed similarity metric has the superior matching performance and computational efficiency than the state-of-the-art methods. Moreover, based on the proposed similarity metric, we also design a fast and robust automatic registration system for multimodal images. This system has been evaluated using a pair of very large SAR and optical images (more than 20000 × 20000 pixels). Experimental results show that our system outperforms the two popular commercial software systems (i.e. ENVI and ERDAS) in both registration accuracy and computational efficiency.

The Study of a Fast Sub-Pixel Registration Method for Remote Sensing Image

2014 ◽  
Vol 989-994 ◽  
pp. 3877-3880 ◽  
Author(s):  
Cui Zhou ◽  
Jing Hong Zhou ◽  
Dong Hao Fan
Keyword(s):  
Remote Sensing ◽  
Fourier Transform ◽  
Remote Sensing Image ◽  
Phase Correlation ◽  
Engineering Practice ◽  
Improved Method ◽  
Registration Accuracy ◽  
Total Size ◽  
Transform Method ◽  
Registration Method

We put forward a fast and efficiently sub-pixel registration method for solving the classical methods’ problems of low efficiency, and use efficiently sub-images instead of original image to sub-pixel registration based on the Fourier transform phase correlation and matrix Fourier transform method. Effective sub-images are selected from the total size of the high-frequency energy after two-dimensional wavelet decomposition, then we use the phase correlation to calculate the pixel displacement and matrix Fourier transform to calculate the sub-pixel displacement. Not only the improved method is inherited the advantage of matrix Fourier transform sub-pixel registration, but also the registration speed is greatly improved. This is more applicable to massive remote sensing data. Through simulation and engineering practice, composited registration accuracy and speed, proved that the improved method is more efficient compared with the classical methods, and it’s more suitable for real remote sensing image registration.

Sign in / Sign up

Export Citation Format

Share Document