Article
Chemistry, Multidisciplinary
Wannan Zhang, Yuqian Zhao
Summary: This paper presents a novel method for SAR and optical image registration. The method combines phase consistency intensity screening and scale space grid division to extract stable and uniform feature points from the image. It also employs the extended phase consistency method to calculate the gradient amplitude and direction of the image, improving the correctness of the main direction calculation and descriptor construction. Experimental results demonstrate its superior matching performance compared to the state-of-the-art methods.
APPLIED SCIENCES-BASEL
(2023)
Article
Mathematics
Erbing Yang, Fei Chen, Meiqing Wang, Hang Cheng, Rong Liu
Summary: In this paper, it is proven that traditional methods of feature extraction in image registration or image matching do not include depth information, which may result in keypoint mismatch. Based on the theory that the ratio of depth difference between a keypoint and its neighbor pixel approximates a constant when the camera moves, a local depth-based feature is proposed as a supplement to the traditional feature. The combination of the local depth-based feature and the SIFT feature descriptor forms a new feature descriptor, which has been experimentally proven to be feasible and effective.
Article
Engineering, Biomedical
Vinicius Pavanelli Vianna, Luiz Otavio Murta
Summary: The study introduces Generalized MI (GMI) using Tsallis entropy to improve affine registration, resulting in significantly prolonged registration ranges in the metric space.
PHYSICS IN MEDICINE AND BIOLOGY
(2022)
Article
Environmental Sciences
Xin Zhao, Hui Li, Ping Wang, Linhai Jing
Summary: The proposed method improves the accuracy of matching features for multisource high-resolution remote sensing images by combining SIFT and ResNet features, demonstrating higher accuracies and more tie points compared to traditional feature-based methods.
Article
Computer Science, Software Engineering
Zahra Hossein-Nejad, Mehdi Nasri
Summary: This paper introduces a new method for image mosaicing based on SIFT, which improves image mosaicing quality and registration performance by enhancing RKEM and proposing a new blending algorithm. Experimental results show the superiority of the proposed method over classical methods in image mosaicing and image registration.
Article
Optics
Pei-Ju Chiang, Chang-Hao Lin
Summary: This study proposes an active stereo vision system to improve the spatial resolution of scanning large objects. By projecting stripe patterns onto the object surface with different rotation angles, the system can accurately and completely detect matching points. The system also uses a two-step method to remove incorrect matching points and improve reconstruction results. Experimental results show that this system provides a low-cost, convenient, and effective approach for high spatial resolution 3D object reconstruction.
OPTICS AND LASERS IN ENGINEERING
(2022)
Article
Environmental Sciences
Biao Xiong, Dengke Li, Zhize Zhou, Fashuai Li
Summary: In this paper, an automatic point cloud registration method based on Gaussian-weighting projected image matching is proposed. It can quickly and robustly register multi-station terrestrial point clouds. The method involves regularizing the point cloud into a 2D grid, performing image matching using the scale-invariant features (SIFT) algorithm, and conducting a global least-square optimization to align the point clouds from different stations.
Article
Automation & Control Systems
Linfeng Tang, Yuxin Deng, Yong Ma, Jun Huang, Jiayi Ma
Summary: This study proposes a novel image registration and fusion method called SuperFusion, which integrates image registration, image fusion, and semantic requirements of high-level vision tasks into a single framework. By utilizing registration network, fusion network, and semantic constraint, SuperFusion overcomes the artifacts caused by slight shifts or deformations in input images and achieves superior performance in high-level vision tasks.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Computer Science, Information Systems
Jin Zheng, Wei Peng, Yue Wang, Bo Zhai
Summary: This article introduces an image registration method, PSSC-RANSAC, for aerial videos. By incorporating prior sampling and sample check, it improves the accuracy and speed of image registration. Experimental results show promising performance with reduced computational cost and improved re-projection error compared to existing methods.
Article
Engineering, Biomedical
Jian-Qing Zheng, Ngee Han Lim, Bartlomiej W. Papiez
Summary: Damage to cartilage is an important indicator of osteoarthritis progression. To address the time-consuming and error-prone manual extraction of cartilage morphology, the authors propose a novel annotation-free deep learning method called D-net for accurate and automatic alignment of pre-and post-contrasted cartilage CT volumes. D-net outperforms other state-of-the-art deep learning models and achieves a Dice coefficient of 0.87 in real-world alignment of 50 pairs of pre-and post-contrasted CT volumes.
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
(2023)
Article
Environmental Sciences
Yameng Hong, Chengcai Leng, Xinyue Zhang, Zhao Pei, Irene Cheng, Anup Basu
Summary: This paper introduces a new method called HOLBP for image registration, which improves traditional methods by redefining gradient and angle calculation and adding gradient direction information to form a 138-dimension descriptor vector. The experimental results demonstrate the stability and efficiency of this method for different test images.
Article
Optics
Pan Zhang, Kai Zhong, Zhongwei Li, Baohui Zhang
Summary: This paper proposes a hybrid-quality-guided phase fusion (HPF) model to solve the problem of measuring the 3D shape of a high dynamic range (HDR) surface using structured light. By evaluating the phase quality comprehensively and weighting and fusing all initial phases under the guidance of the hybrid-quality measure, a more accurate final phase can be obtained, enabling the reconstruction of a more complete and accurate 3D shape of the HDR surface.
Article
Optics
Luyao Ma, Linghui Yang, Ruiying Liao, Haoyue Liu, Shuo Yang, Jigui Zhu
Summary: This paper proposes a method for efficient and refined in-motion 3D shape measurements using RGB line-scan cameras with RGB channel fusion. The method can handle the challenge of high dynamic range surfaces with large reflectivity variations and achieve accurate and reliable reconstruction.
Article
Optics
Shu-Feng Lin, Philippe Gentet, Di Wang, Seung-Hyun Lee, Eun-Soo Kim, Qiong-Hua Wang
Summary: The proposed full-color holographic three-dimensional display system utilizes an angular-compensating holographic optical element to achieve a simple structure for full-color display. This system eliminates the need for additional optical elements for synthesizing full-color reconstruction, leading to enhanced system integration and miniaturization.
OPTICS AND LASERS IN ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Debapriya Sengupta, Phalguni Gupta, Arindam Biswas
Summary: Image registration, the process of aligning one image in the coordinate system of another, plays a vital role in the medical field. Mutual information-based algorithms have significantly advanced medical image registration, and new developments, including deep neural network-based algorithms, continue to emerge. This paper provides a survey of these algorithms, discussing their development, major works, comparative studies, and the post-mutual information era in medical image registration.
Article
Mathematics, Interdisciplinary Applications
Patrick Erik Bradley
JOURNAL OF CLASSIFICATION
(2017)
Article
Computer Science, Hardware & Architecture
Patrick Erik Bradley
Article
Computer Science, Information Systems
Patrick Erik Bradley, Norbert Paul
Article
Computer Science, Information Systems
Anna Giovanella, Patrick Erik Bradley, Sven Wursthorn
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2019)
Review
Computer Science, Information Systems
Martin Breunig, Patrick Erik Bradley, Markus Jahn, Paul Kuper, Nima Mazroob, Norbert Roesch, Mulhim Al-Doori, Emmanuel Stefanakis, Mojgan Jadidi
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2020)
Article
Computer Science, Information Systems
Markus Wilhelm Jahn, Patrick Erik Bradley
Summary: This article calculates geometrically induced topology useful for applications such as simulations and navigation by presenting unpublished algorithms. It also analyzes the robustness of the implementations and presents the results. The findings show that most volumes can be extracted, but there are failures and various outcomes in computational geometry.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Article
Computer Science, Information Systems
Markus Wilhelm Jahn, Patrick Erik Bradley
Summary: This study develops a topological access method (TOAM) based on the concept of Property Graph to perform topological queries on geographic data. The experimental test shows that the Euler characteristic is helpful for data validation. This research is important for future innovative applications.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Article
Mathematics, Applied
Patrick Erik Bradley
Summary: This article develops a class of heat operators acting on L-2-function spaces over non-archimedean local fields on holed discs. These operators are seen as previous operators introduced by Zúñiga-Galindo and are associated with certain finite Kronecker product graphs when the underlying trees are regular. The study also examines L-2-spaces and integral operators invariant under the action of a finite group on a holed disc, and applies them to Mumford curves. It is found that the spectral gap in families of Mumford curves can become arbitrarily small.
JOURNAL OF FOURIER ANALYSIS AND APPLICATIONS
(2023)
Article
Environmental Studies
Patrick Erik Bradley, Martin Behnisch
ENVIRONMENT AND PLANNING B-URBAN ANALYTICS AND CITY SCIENCE
(2019)
Article
Construction & Building Technology
Patrick E. Bradley
BUILDING RESEARCH AND INFORMATION
(2019)
Article
Environmental Sciences
Patrick Erik Bradley, Sina Keller, Martin Weinmann
Article
Mathematics, Interdisciplinary Applications
P. E. Bradley
P-ADIC NUMBERS ULTRAMETRIC ANALYSIS AND APPLICATIONS
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Patrick E. Bradley
STATISTICAL LEARNING AND DATA SCIENCES
(2015)
Article
Mathematics, Interdisciplinary Applications
Patrick Erik Bradley
P-ADIC NUMBERS ULTRAMETRIC ANALYSIS AND APPLICATIONS
(2010)