Rotation-Invariant Siamese Network for Low-Altitude Remote-Sensing Image Registration

Liu, Yuyan; Gong, Xiaoying; Chen, Jiaxuan; Chen, Shuang; Yang, Yang

doi:10.1109/jstars.2020.3024776

Cited by 24 publications

(4 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, convolutional neural networks (CNNs) are becoming the mainstream for image registration owing to the strong nonlinear learning capabilities [11]. The CNNsbased registration methods are basically divided into three categories: model parameter methods [10], corner matching methods [11], [12], [13] and unsupervised methods [14]. The model parameter methods utilize a trained DNN (deep neural networks) predicts matching labels of patch-pairs from the sensed and reference images.…”

Section: Related Work a Registration Methodsmentioning

confidence: 99%

R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images

Chen,

Zheng,

Leng

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In the detection of building changes in high spatialresolution remote sensing images, both the distribution position and surface characteristics of the same objects are probably different under different imaging phases, which potentially causes high false positives. In order to improve the detection accuracy of building changes, an integration network, named R&D net is proposed in this paper, which comprises a registration network (R-net) followed by a change detection network (D-net). In Rnet, two different phase images are accepted as inputs, corner points and their descriptors are generated to spatially align those images. After that, the spatially aligned images are fed into the Dnet, and building images are detected accordingly. In this paper, a multi-view automatic labeling method is proposed to obtain labeling corner points. A new dataset containing 5,104 image pairs is established. Experimental results demonstrate that the R-net can extract robust invariant features, and then improve registration accuracy under circumstances with obvious changes of surface feature, which is a base of D-net. Uniting pyramid pooling structure with a focal loss function in D-net, both leaky and wrong segmentations can be dramatically improved under complex scenes with many interferences. When compared with baseline methods on different high-resolution remote sensing scenes, the proposed method achieves better performance and more accurate detection results of building changes.

show abstract

Section: Related Work a Registration Methodsmentioning

confidence: 99%

R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images

Chen,

Zheng,

Leng

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In essence, the existing remote sensing image registration methods based on deep learning belongs to strongly supervised learning. They need the corresponding feature point pairs as supervised signal [32][33][34]. However, because a large number of feature point pairs are required to used as training data and manual selection is time-consuming, the commonly used method is extracting feature point pairs by using existing mature methods, such as SIFT [6].…”

Section: Image Registration Of Remote Sensing Imagesmentioning

confidence: 99%

A Coarse-to-Fine Feature Match Network Using Transformers for Remote Sensing Image Registration

et al. 2023

View full text Add to dashboard Cite

Feature matching is a core step in multi-source remote sensing image registration approaches based on feature. However, for existing methods, whether traditional classical SIFT algorithm or deep learning-based methods, they essentially rely on generating descriptors from local regions of feature points, which can lead to low matching success rates due to various challenges, including gray-scale changes, content changes, local similarity, and occlusions between images. Inspired by the human approach of finding rough corresponding regions globally and then carefully comparing local regions, and the excellent global attention property of transformers, the proposed feature matching network adopts a coarse-to-fine matching strategy that utilizes both global and local information between images to predict corresponding feature points. Importantly, the network has great flexibility of matching corresponding points for any feature points and can be effectively trained without strong supervised signals of corresponding feature points and only require the true geometric transformation between images. The qualitative experiment illustrate the effectiveness of the proposed network by matching feature points extracted by SIFT or sampled uniformly. In the quantitative experiments, we used feature points extracted by SIFT, SuperPoint, and LoFTR as the keypoints to be matched. We then calculated the mean match success ratio (MSR) and mean reprojection error (MRE) of each method at different thresholds in the test dataset. Additionally, boxplot graphs were plotted to visualize the distributions. By comparing the MSR and MRE values as well as their distributions with other methods, we can conclude that the proposed method consistently outperforms the comparison methods in terms of MSR at different thresholds. Moreover, the MSR of the proposed method remains within a reasonable range compared to the MRE of other methods.

show abstract

“…For example, in [33] the authors presented a transfer learning approach and local features estimation to register multi-modal remote sensing images. The authors in [34] presented a siamese network to deal with the complexity registration of low-altitude remote-sensing images. Although approaches based on deep learning show improvements, the main disadvantage is the high computational cost and the significant number of examples required to train them.…”

Section: Revisited Literaturementioning

confidence: 99%

Coregistration of Remote Sensing Image Based on Histogram Kernel Predictability

Hugo¹,

Aranda²,

Mejia-Zuluaga³

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Registration of remote sensing images has been approached using different strategies; one of the most popular is based on similarity measures. There are different measures of similarity in the literature: Normalized Cross-Correlation (NCC), Mutual Information (MI), etc. Normalized Mutual Information (NMI) has received the most attention in image processing; among the most important limitations are its high computational cost and lack of robustness to strong radiometric changes. For this reason, in this work, we introduce a co-registration approach based on the Histogram Kernel Predictability (HKP). This formulation reduces numerical errors and requires less computing time in comparison to NMI. To the best of our knowledge, this is the first work for registering any remote sensing images by using HKP. Additionally, we propose to use an algorithm based on meta-heuristics called Evolutionary Centers Algorithm (ECA), which allows having fewer iterations to solve the registration problem. In addition, we incorporate a parallelization scheme that permits reducing processing times. The results show that our proposal can solve co-registration problems that the NMI cannot solve while obtaining competitive computational times and registration errors comparable with other existing works in the literature. The HKP approach solves most of all the transformations of a set of simulated registration problems, while the NMI, in some cases, only solves half of the registration problems. Moreover, we compare our approach with feature-based methods in real datasets. This research presents an alternative to remote sensing problems where MI has traditionally been used.

show abstract

Rotation-Invariant Siamese Network for Low-Altitude Remote-Sensing Image Registration

Cited by 24 publications

References 58 publications

R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images

R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images

A Coarse-to-Fine Feature Match Network Using Transformers for Remote Sensing Image Registration

Coregistration of Remote Sensing Image Based on Histogram Kernel Predictability

Contact Info

Product

Resources

About