Adaptively feature matching via joint transformational-spatial clustering

被引:2
|
作者
Wang, Linbo [1 ]
Tan, Li [1 ]
Fang, Xianyong [1 ]
Guo, Yanwen [2 ]
Wan, Shaohua [3 ]
机构
[1] Anhui Univ, Sch Comp Sci & Technol, MOE Key Lab Intelligent Comp & Signal Proc, Hefei, Peoples R China
[2] Nanjing Univ, Natl Key Lab Novel Software Technol, Nanjing, Peoples R China
[3] Zhongnan Univ Econ & Law, Sch Informat & Safety Engn, Wuhan, Peoples R China
基金
中国国家自然科学基金;
关键词
Clustering; Density estimation; Feature matching; Mode-seeking; GRAPHS; SCALE;
D O I
10.1007/s00530-021-00792-8
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The transformational and spatial proximities are important cues for identifying inliers from an appearance based match set because correct matches generally stay close in input images and share similar local transformations. However, most existing approaches only check one type of them or both types consecutively with manually set thresholds, and thus their matching accuracy and flexibility in handling large-scale images are limited. In this paper, we present an efficient clustering based approach to identify match inliers with both proximities simultaneously. It first projects the putative matches into a joint transformational-spatial space, where mismatches tend to scatter all around while correct matches gather together. A mode-seeking process based on joint kernel density estimation is then proposed to obtain significant clusters in the joint space, where each cluster contains matches mapping the same object across images with high accuracy. Moreover, kernel bandwidths for measuring match proximities are adaptively set during density estimation, which enhances its applicability for matching different images. Experiments on three standard datasets show that the proposed approach delivers superior performance on a variety of feature matching tasks, including multi-object matching, duplicate object matching and object retrieval.
引用
收藏
页码:1717 / 1727
页数:11
相关论文
共 50 条
  • [21] Robust Feature Matching via Multi-scale Grid Structure
    Li, Yanping
    Huang, Qian
    Liu, Yizhang
    Huang, Yuan
    Sun, Xiaoqing
    2019 IEEE INTL CONF ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, BIG DATA & CLOUD COMPUTING, SUSTAINABLE COMPUTING & COMMUNICATIONS, SOCIAL COMPUTING & NETWORKING (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2019), 2019, : 1187 - 1193
  • [22] Filter pruning via feature map clustering
    Li, Wei
    He, Yongxing
    Zhang, Xiaoyu
    Tang, Yongchuan
    INTELLIGENT DATA ANALYSIS, 2023, 27 (04) : 911 - 933
  • [23] Hierarchical Clustering with Simple Matching and Joint Entropy Dissimilarity Measure
    Cilingirturk, A. Mete
    Ergut, Ozlem
    JOURNAL OF MODERN APPLIED STATISTICAL METHODS, 2014, 13 (01) : 329 - 338
  • [24] Transfer Learning Based on Joint Feature Matching and Adversarial Networks
    钟昊文
    王超
    庹红娅
    胡健
    乔凌峰
    敬忠良
    JournalofShanghaiJiaotongUniversity(Science), 2019, 24 (06) : 699 - 705
  • [25] Transfer Learning Based on Joint Feature Matching and Adversarial Networks
    Zhong H.
    Wang C.
    Tuo H.
    Hu J.
    Qiao L.
    Jing Z.
    Journal of Shanghai Jiaotong University (Science), 2019, 24 (06) : 699 - 705
  • [26] A Fast Video Stabilization Method Based on Feature Matching and Histogram Clustering
    Li, Baotong
    Chen, Yangzhou
    Ren, Jianqiang
    Cheng, Lan
    INFORMATION TECHNOLOGY AND INTELLIGENT TRANSPORTATION SYSTEMS, VOL 2, 2017, 455 : 315 - 325
  • [27] Joint Spectral Clustering based on Optimal Graph and Feature Selection
    Zhu, Jinting
    Jang-Jaccard, Julian
    Liu, Tong
    Zhou, Jukai
    NEURAL PROCESSING LETTERS, 2021, 53 (01) : 257 - 273
  • [28] Joint Spectral Clustering based on Optimal Graph and Feature Selection
    Jinting Zhu
    Julian Jang-Jaccard
    Tong Liu
    Jukai Zhou
    Neural Processing Letters, 2021, 53 : 257 - 273
  • [29] Efficient Feature Matching via Nonnegative Orthogonal Relaxation
    Bo Jiang
    Jin Tang
    Bin Luo
    International Journal of Computer Vision, 2019, 127 : 1345 - 1360
  • [30] Robust feature matching via progressive smoothness consensus
    Xia, Yifan
    Jiang, Jie
    Lu, Yifan
    Liu, Wei
    Ma, Jiayi
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2023, 196 : 502 - 513