Multi-Neighborhood Guided Kendall Rank Correlation Coefficient for Feature Matching

Chen, Jun; Yang, Meng; Gong, Wenping; Yu, Yang

doi:10.1109/tmm.2022.3217410

Cited by 4 publications

(3 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-scale locality and rank preservation (mTopKRP) [37] defines rank list distance measurements based on multi-scale neighborhoods to more strictly and generally preserve local topological structure. The multi-neighborhood guided Kendall rank correlation coefficient (mGKRCC) [38] proposes that the neighborhood points of feature points have rank consistency and uses the Kendall correlation coefficient to measure the error in the rank order of neighborhood points. Neighborhood manifold representation consensus (NMRC) [39] proposes iterative filtering of neighborhood construction to obtain more reliable neighborhood points and uses manifold learning to preserve inliers with consistent neighborhood topology.…”

Section: Local Geometric Constraint-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Homography Matrix-Based Local Motion Consistent Matching for Remote Sensing Images

Liu

Zhao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Feature matching is a fundamental task in the field of image processing, aimed at ensuring correct correspondence between two sets of features. Putative matches constructed based on the similarity of descriptors always contain a large number of false matches. To eliminate these false matches, we propose a remote sensing image feature matching method called LMC (local motion consistency), where local motion consistency refers to the property that adjacent correct matches have the same motion. The core idea of LMC is to find neighborhoods with correct motion trends and retain matches with the same motion. To achieve this, we design a local geometric constraint using a homography matrix to represent local motion consistency. This constraint has projective invariance and is applicable to various types of transformations. To avoid outliers affecting the search for neighborhoods with correct motion, we introduce a resampling method to construct neighborhoods. Moreover, we design a jump-out mechanism to exit the loop without searching all possible cases, thereby reducing runtime. LMC can process over 1000 putative matches within 100 ms. Experimental evaluations on diverse image datasets, including SUIRD, RS, and DTU, demonstrate that LMC achieves a higher F-score and superior overall matching performance compared to state-of-the-art methods.

show abstract

Section: Local Geometric Constraint-based Methodsmentioning

confidence: 99%

“…We summarized two consensus points from multiple methods [20,25,26,[34][35][36][37][38][39][40][41] for removing false matches.…”

Section: Problem Formulationmentioning

confidence: 99%

Homography Matrix-Based Local Motion Consistent Matching for Remote Sensing Images

Liu

Zhao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Second, each sequential feature x is scored by formula (1). The closer scores are to 1, the higher the occurrence probability of infrastructure project delay will be (Chen et al, 2022). Finally, the threshold Q α can be obtained based on the significance level and the number of infrastructure projects.…”

Section: Feature Extraction Of Infrastructure Project Schedulesmentioning

confidence: 99%