Remote Sensing Image Registration Using Multiple Image Features

Yang, Kun; Pan, Anning; Yang, Yang; Zhang, Su; Ong, Sim Heng; Tang, Haolin

doi:10.20944/preprints201705.0027.v2

Cited by 21 publications

(24 citation statements)

References 22 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The TPS as the non-rigid transformation model is used widely in image warping corrections [31,33,34], as shown in Figure 7. Thus, it is adopted in this study.…”

Section: Position Correction Of Sss Images Using Thin-plate Splinesmentioning

confidence: 99%

A New Method for Acquisition of High-Resolution Seabed Topography by Matching Seabed Classification Images

et al. 2017

View full text Add to dashboard Cite

Abstract:The multibeam echo sounders (MBES) can acquire accurate positional but low-resolution seabed terrain and images, whereas side scan sonars (SSS) can only acquire inaccurate positional but high-resolution seabed images. In this study, a new method for superimposing corrected-positional SSS images on multibeam bathymetric terrain is proposed to obtain high-resolution and accurate-positional seabed topography using traditional MBES and SSS. Three steps, including the normalization by the z-score, sediment classification by the k-means++ algorithm, and denoising processing using morphological operations, are processed for both MBES and SSS images to obtain the corresponding sediment images. Next, a segmented matching method is given based on the common sediment distributions and features of MBES and SSS sediment images. The two kinds of sediment images are matched segmentally using the speeded up robust features algorithm and random sample consensus algorithm. Then, the positions of SSS images are corrected segmentally using thin plate splines based on matching points. Finally, the corrected SSS image is superimposed on MBES bathymetric terrain, based on positional relationship. The proposed method was verified through experiments, and high image resolution and high position accuracy seabed topography were obtained. Moreover, the performances of the method are discussed, and some conclusions are drawn according to the experiments and discussions.

show abstract

“…The TPS as the non-rigid transformation model is used widely in image warping corrections [31,33,34], as shown in Figure 7. Thus, it is adopted in this study.…”

Section: Position Correction Of Sss Images Using Thin-plate Splinesmentioning

confidence: 99%

A New Method for Acquisition of High-Resolution Seabed Topography by Matching Seabed Classification Images

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The second group is more popular than the first one due to the robustness and reliability of those methods against image geometric distortion and radiometric difference [6,7]. Feature-based methods generally consist of three steps: feature detection, description, and matching.…”

Section: Introductionmentioning

confidence: 99%

“…Many improved descriptors, such as principal component analysis-SIFT [11], gradient location and orientation histogram [12], and Affine-SIFT [13], have been investigated to make the SIFT features distinctive in image deformation. Feature descriptors are combined with several similarity metrics or constraints, such as scale-orientation joint restriction criteria [14], weight-based topological map-matching algorithm [15], normalized cross correlation and least square matching [16], perspective scale invariant feature [17], l q -estimator [18], and L 2 -minimizing estimation [6], to match remote sensing images. Despite significant improvements to the feature-based matching method, the manually designed methods (e.g., SIFT) cannot fully obtain the invariant descriptors with the appearance of nonlinear illumination changes, shadows, and occlusions [19].…”

Section: Introductionmentioning

confidence: 99%

Matching of Remote Sensing Images with Complex Background Variations via Siamese Convolutional Neural Network

Chen

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:Feature-based matching methods have been widely used in remote sensing image matching given their capability to achieve excellent performance despite image geometric and radiometric distortions. However, most of the feature-based methods are unreliable for complex background variations, because the gradient or other image grayscale information used to construct the feature descriptor is sensitive to image background variations. Recently, deep learning-based methods have been proven suitable for high-level feature representation and comparison in image matching. Inspired by the progresses made in deep learning, a new technical framework for remote sensing image matching based on the Siamese convolutional neural network is presented in this paper. First, a Siamese-type network architecture is designed to simultaneously learn the features and the corresponding similarity metric from labeled training examples of matching and non-matching true-color patch pairs. In the proposed network, two streams of convolutional and pooling layers sharing identical weights are arranged without the manually designed features. The number of convolutional layers is determined based on the factors that affect image matching. The sigmoid function is employed to compute the matching and non-matching probabilities in the output layer. Second, a gridding sub-pixel Harris algorithm is used to obtain the accurate localization of candidate matches. Third, a Gaussian pyramid coupling quadtree is adopted to gradually narrow down the searching space of the candidate matches, and multiscale patches are compared synchronously. Subsequently, a similarity measure based on the output of the sigmoid is adopted to find the initial matches. Finally, the random sample consensus algorithm and the whole-to-local quadratic polynomial constraints are used to remove false matches. In the experiments, different types of satellite datasets, such as ZY3, GF1, IKONOS, and Google Earth images, with complex background variations are used to evaluate the performance of the proposed method. The experimental results demonstrate that the proposed method, which can significantly improve the matching performance of multi-temporal remote sensing images with complex background variations, is better than the state-of-the-art matching methods. In our experiments, the proposed method obtained a large number of evenly distributed matches (at least 10 times more than other methods) and achieved a high accuracy (less than 1 pixel in terms of root mean square error).

show abstract

“…For example, in the tasks of image or point cloud registration [1][2][3][4], change detection [5], large scale 3D reconstruction, and image stitching [6], data that acquired from different sensors, different time, and different angles should be transformed to a unified coordinate system. Therefore, the performance of these systems are rely on the accuracy of the estimated transformations.…”

Section: Introductionmentioning

confidence: 99%

A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images

Cai

Leng

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:Estimating the transformation between two images from the same scene is a fundamental step for image registration, image stitching and 3D reconstruction. State-of-the-art methods are mainly based on sorted residual for generating hypotheses. This scheme has acquired encouraging results in many remote sensing applications. Unfortunately, mainstream residual based methods may fail in estimating the transform between Unmanned Aerial Vehicle (UAV) low altitude remote sensing images, due to the fact that UAV images always have repetitive patterns and severe viewpoint changes, which produce lower inlier rate and higher pseudo outlier rate than other tasks. We performed extensive experiments and found the main reason is that these methods compute feature pair similarity within a fixed window, making them sensitive to the size of residual window. To solve this problem, three schemes that based on the distribution of residuals are proposed, which are called Relational Window (RW), Sliding Window (SW), Reverse Residual Order (RRO), respectively. Specially, RW employs a relaxation residual window size to evaluate the highest similarity within a relaxation model length. SW fixes the number of overlap models while varying the length of window size. RRO takes the permutation of residual values into consideration to measure similarity, not only including the number of overlap structures, but also giving penalty to reverse number within the overlap structures. Experimental results conducted on our own built UAV high resolution remote sensing images show that the proposed three strategies all outperform traditional methods in the presence of severe perspective distortion due to viewpoint change.

show abstract

Remote Sensing Image Registration Using Multiple Image Features

Cited by 21 publications

References 22 publications

A New Method for Acquisition of High-Resolution Seabed Topography by Matching Seabed Classification Images

A New Method for Acquisition of High-Resolution Seabed Topography by Matching Seabed Classification Images

Matching of Remote Sensing Images with Complex Background Variations via Siamese Convolutional Neural Network

A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images

Contact Info

Product

Resources

About