ACCURATE IMAGE REGISTRATION BY COMBINING FEATURE-BASED MATCHING AND GLS-BASED MOTION ESTIMATION

2007 ◽  
Keyword(s):  
Image Registration ◽  
Motion Estimation ◽  
Feature Based

scholarly journals Non-rigid image registration using a modified fuzzy feature-based inference system for 3D cardiac motion estimation

2021 ◽  
Vol 205 ◽  
pp. 106085
Author(s):  
Monire Sheikh Hosseini ◽  
Mahammad Hassan Moradi ◽  
Mahdi Tabassian ◽  
Jan D'hooge
Keyword(s):  
Image Registration ◽  
Motion Estimation ◽  
Cardiac Motion ◽  
Inference System ◽  
Feature Based

scholarly journals Efficient feature-based motion estimation in neurosurgery using non-maximum suppression

2018 ◽  
Vol 4 (1) ◽  
pp. 555-558 ◽  
Author(s):  
Fang Chen ◽  
Jan Müller ◽  
Jens Müller ◽  
Ronald Tetzlaff
Keyword(s):  
Motion Estimation ◽  
Thermal Imaging ◽  
Motion Correction ◽  
Processing Time ◽  
Feature Detection ◽  
Detection Efficiency ◽  
Adaptive Method ◽  
Time Performance ◽  
Key Points ◽  
Feature Based

AbstractIn this contribution we propose a feature-based method for motion estimation and correction in intraoperative thermal imaging during brain surgery. The motion is estimated from co-registered white-light images in order to perform a robust motion correction on the thermographic data. To ensure real-time performance of an intraoperative application, we optimise the processing time which essentially depends on the number of key points found by our algorithm. For this purpose we evaluate the effect of applying an non-maximum suppression (NMS) to improve the feature detection efficiency. Furthermore we propose an adaptive method to determine the size of the suppression area, resulting in a trade-off between accuracy and processing time.

Spatiotemporal non-rigid image registration for 3D ultrasound cardiac motion estimation

2007 ◽  
Author(s):  
D. Loeckx ◽  
J. Ector ◽  
F. Maes ◽  
J. D'hooge ◽  
D. Vandermeulen ◽  
...  
Keyword(s):  
Image Registration ◽  
Motion Estimation ◽  
3D Ultrasound ◽  
Cardiac Motion

A Comparison of Image Registration Methods Used for Printed Circuit Board Inspection

2008 ◽  
Vol 381-382 ◽  
pp. 295-298
Author(s):  
Shin Chieh Lin ◽  
C.T. Chen ◽  
C.H. Chou
Keyword(s):  
Image Registration ◽  
Printed Circuit Board ◽  
Circuit Board ◽  
Loading Test ◽  
Area Method ◽  
Printed Circuit ◽  
Feature Based ◽  
Position And Orientation ◽  
Inspection Machine

In this study, registration methods used to estimate both position and orientation differences between two images had been evaluated. This is an important issue since that there are always some position and orientation differences when loading test samples on the inspection machine. These differences should be calculated and compensated before further analysis. Registration methods tested including one area method and three feature based method. It was shown that the area method had better performance than other feature based method in these cases studied. And it is shown that it is much easy to detect defect by analyzing the subtracted image with position and orientation compensation instead of those without compensation.

scholarly journals Efficient feature-based image registration by mapping sparsified surfaces

2018 ◽  
Vol 55 ◽  
pp. 561-571 ◽  
Author(s):  
Chun Pang Yung ◽  
Gary P.T. Choi ◽  
Ke Chen ◽  
Lok Ming Lui
Keyword(s):  
Image Registration ◽  
Feature Based

scholarly journals Implementation of RANSAC Algorithm for Feature-Based Image Registration

2013 ◽  
Vol 01 (06) ◽  
pp. 46-50 ◽  
Author(s):  
Lan-Rong Dung ◽  
Chang-Min Huang ◽  
Yin-Yi Wu
Keyword(s):  
Image Registration ◽  
Feature Based ◽  
Ransac Algorithm

scholarly journals An Image Registration Method Using Deep Residual Network Features for Multisource High-Resolution Remote Sensing Images

2021 ◽  
Vol 13 (17) ◽  
pp. 3425
Author(s):  
Xin Zhao ◽  
Hui Li ◽  
Ping Wang ◽  
Linhai Jing
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Image Registration ◽  
Feature Descriptor ◽  
Remote Sensing Images ◽  
Residual Network ◽  
Scale Invariant ◽  
Registration Method ◽  
Sensing Applications ◽  
Feature Based

Accurate registration for multisource high-resolution remote sensing images is an essential step for various remote sensing applications. Due to the complexity of the feature and texture information of high-resolution remote sensing images, especially for images covering earthquake disasters, feature-based image registration methods need a more helpful feature descriptor to improve the accuracy. However, traditional image registration methods that only use local features at low levels have difficulty representing the features of the matching points. To improve the accuracy of matching features for multisource high-resolution remote sensing images, an image registration method based on a deep residual network (ResNet) and scale-invariant feature transform (SIFT) was proposed. It used the fusion of SIFT features and ResNet features on the basis of the traditional algorithm to achieve image registration. The proposed method consists of two parts: model construction and training and image registration using a combination of SIFT and ResNet34 features. First, a registration sample set constructed from high-resolution satellite remote sensing images was used to fine-tune the network to obtain the ResNet model. Then, for the image to be registered, the Shi_Tomas algorithm and the combination of SIFT and ResNet features were used for feature extraction to complete the image registration. Considering the difference in image sizes and scenes, five pairs of images were used to conduct experiments to verify the effectiveness of the method in different practical applications. The experimental results showed that the proposed method can achieve higher accuracies and more tie points than traditional feature-based methods.

Sign in / Sign up

Export Citation Format

Share Document