.png){kind=icon}
返回
A Two-Step Descriptor-Based Keypoint Filtering Algorithm for Robust Image Matching
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2022.3188931.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Finding robust and correct keypoints in images remains a challenge, especially when repetitive patterns are present. In this article, we propose a universal two-step filtering method to solve the mismatch problem in repetitive patterns. Having applied a mean-shift clustering algorithm to remove obvious mismatches, the proposed confusion reduction (CR) method uses a novel confusion index (CI) in a gridding schema to identify and filter out the remaining confusing keypoints. In both steps, the descriptors' statistical properties are evaluated using kernel density estimation. Various synthetic and real stereo pairs, along with multiview image blocks, were used to assess the performance of the presented algorithm. The results were also compared with those obtained by several state-of-the-art mismatch removal methods. The experiments showed that, on average, the proposed strategy improves the accuracy of matching by 10% and the accuracy of photogrammetric blocks by 20%-30%.
Keyword:
Indexes
Feature extraction
Estimation
Clustering algorithms
Kernel
Filtering algorithms
Detectors
Descriptor
image matching
kernel density estimation
keypoint filtering
mean shift
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
分享收藏AutoMorph: Automated Retinal Vascular Morphology Quantification Via a Deep Learning PipelineAutoMorph: 通过深度学习管道自动量化视网膜血管形态
OAAI
OAAI分享收藏Robust feature matching using guided local outlier factor基于引导局部离群因子的鲁棒特征匹配.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Regularized vector field learning with sparse approximation for mismatch removalPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容