2023
DOI: 10.1016/j.isprsjprs.2023.01.016
|View full text |Cite
|
Sign up to set email alerts
|

Robust feature matching via progressive smoothness consensus

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 8 publications
(3 citation statements)
references
References 55 publications
0
3
0
Order By: Relevance
“…Homography matrix estimation tasks are conducted on humanoid-eye binocular images. For these tasks, following Xia’s work [ 35 ], homography error is considered, which adopts RANSAC as the estimator to derive the geometric model. In this case, a corresponding estimated homography is identified as accurate when its homography error is less than three pixels, and the accuracy (Acc.)…”
Section: Experiments and Discussionmentioning
confidence: 99%
“…Homography matrix estimation tasks are conducted on humanoid-eye binocular images. For these tasks, following Xia’s work [ 35 ], homography error is considered, which adopts RANSAC as the estimator to derive the geometric model. In this case, a corresponding estimated homography is identified as accurate when its homography error is less than three pixels, and the accuracy (Acc.)…”
Section: Experiments and Discussionmentioning
confidence: 99%
“…For real data, SARBuD (SAR Building Dataset) dataset [43] is tested, and we also collected several satellite images with different deformations, e.g., multiview changes, multiple modes and outliers. Several typical methods are selected to make comparisons, i.e., RANSAC [44], CPD [24], RPM-L2E [45], PR-GLS [28], GCPD [46], DFM [47], LAF [48], and PSC [49]. All the experiments are implemented in MATLAB and Python running on a platform with Intel Core i7 CPU and 16 GB RAM.…”
Section: Methodsmentioning
confidence: 99%
“…On the other hand, local transformations provide a more generalized approach and can describe complex geometric relationships between image pairs. These complex relationships can arise due to various factors, including nonrigid transformations [18][19][20][21][22][23][24][25][26], occlusion and repetitive patterns [27][28][29][30][31], and sensor distortions [32][33][34][35][36][37]. Both global and local transformations offer unique advantages in handling image geometry.…”
Section: Introductionmentioning
confidence: 99%