Learning Two-View Correspondences and Geometry Using Neighbor-Aware Network

Article Geochemistry & Geophysics

Robust Feature Matching for Remote Sensing Image Registration via Guided Hyperplane Fitting

Guobao Xiao et al.

Summary: This article proposes a robust feature matching method called FNRG for remote sensing image registration, which addresses the problem of local distortions in images. The method utilizes the first neighbor relation of feature points between two images to find consistent matches and employs hyperplane fitting and a cost function to improve matching performance. Experimental results demonstrate that the proposed method outperforms several state-of-the-art methods in handling complex remote sensing images.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Add to Collection

Article Geography, Physical

Robust feature matching via neighborhood manifold representation consensus

Jiayi Ma et al.

Summary: The proposed method, named neighborhood manifold representation consensus (NMRC), is efficient for robust feature matching by preserving stable neighborhood topologies within consistent regions. By establishing a mathematical optimization model and iterative filtering strategy, it successfully handles a large number of correspondences and demonstrates significant advantages in various tasks.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2022)

Add to Collection

Article Geochemistry & Geophysics

Metric-Learning-Based Deep Hashing Network for Content-Based Retrieval of Remote Sensing Images

Subhankar Roy et al.

Summary: This letter introduces a metric-learning-based hashing network that improves retrieval performance by using a large pretrained DNN, learning a semantic-based metric space, and generating compact binary hash codes. Experiments demonstrate significant improvement in retrieval performance compared to state-of-the-art hashing methods in RS.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2021)

Add to Collection

Article Geochemistry & Geophysics

A Discriminative Point Matching Algorithm Based on Local Structure Consensus Constraint

Feng Shao et al.

Summary: A discriminative point matching algorithm named local structure consensus constraint is proposed in this study to improve the accuracy of feature matching by removing outliers in remote sensing images. The algorithm is proven to be more accurate and efficient compared to five state of the art point matching methods.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2021)

Add to Collection

Article Geochemistry & Geophysics

Hyperspectral Anomaly Detection via Integration of Feature Extraction and Background Purification

Yong Ma et al.

Summary: This study proposes a new anomaly detection method that extracts features from HSI data using FrFT and combines with LRaSMD, showing superior performance in experimental results.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence