Endoscopic image feature matching via motion consensus and global bilateral regression

被引:11
|
作者
Chu, Yakui [1 ]
Li, Heng [1 ]
Li, Xu [1 ]
Ding, Yuan [1 ]
Yang, Xilin [1 ]
Ai, Danni [1 ]
Chen, Xiaohong [2 ]
Wang, Yongtian [1 ]
Yang, Jian [1 ]
机构
[1] Beijing Inst Technol, Sch Opt & Elect, Beijing Engn Res Ctr Mixed Real & Adv Display, Beijing 100081, Peoples R China
[2] Beijing Tongren Hosp, Dept Otolaryngol Head & Neck Surg, Beijing 100730, Peoples R China
基金
美国国家科学基金会;
关键词
SURFACE RECONSTRUCTION; REGISTRATION; PERCEPTION; EXTRACTION; NAVIGATION; ALGORITHM; SLAM;
D O I
10.1016/j.cmpb.2020.105370
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Background and objective: Feature matching of endoscopic images is of crucial importance in many clinical applications, such as object tracking and surface reconstruction. However, with the presence of low texture, specular reflections and deformations, the feature matching methods of natural scene are facing great challenges in minimally invasive surgery (MIS) scenarios. We propose a novel motion consensus-based method for endoscopic image feature matching to address these problems. Methods: Our method starts by correcting the radial distortion with the spherical projection model and removing the specular reflection regions with an adaptive detection method, which helps to eliminate the image distortion and to reduce the quantity of outliers. We solve the matching problem with a two-stage strategy that progressively estimates a consensus of inliers; the result is a precisely smoothed motion field. First, we construct a spatial motion field from candidate feature matches and estimate its maximum posterior with expectation maximization algorithm, which is computationally efficient and able to obtain smoothed motion field quickly. Second, we extend the smoothed motion field to the affine domain and refine it with bilateral regression to preserve locally subtle motions. The true matches can be identified by checking the difference of feature motion against the estimated field. Results: Evaluations are implemented on two simulation datasets of deformation (218 images) and four different types of endoscopic datasets (1032 images). Our method is compared with three other state-of-the-art methods and achieves the best performance on affine transformation and nonrigid deformation simulations, with inlier ratio of 86.7% and 94.3%, sensitivity of 90.0% and 96.2%, precision of 88.2% and 93.9%, and F1-Score of 89.1% and 95.0%, respectively. On clinical datasets evaluations, the proposed method achieves an average reprojection error of 3.7 pixels and a consistent performance in multi-image correspondence of sequential images. Furthermore, we also present a surface reconstruction result from rhinoscopic images to validate the reliability of our method, which shows high-quality feature matching results. Conclusions: The proposed motion consensus-based feature matching method is proved effective and robust for endoscopic images correspondence. This demonstrates its capability to generate reliable feature matches for surface reconstruction and other meaningful applications in MIS scenarios. © 2020 Elsevier B.V.
引用
收藏
页数:13
相关论文
共 50 条
  • [31] Heterogeneous Image Matching via a Novel Feature Describing Model
    Zhou, Bin
    Duan, Xuemei
    Ye, Dongjun
    Wei, Wei
    Wozniak, Marcin
    Damasevicius, Robertas
    APPLIED SCIENCES-BASEL, 2019, 9 (22):
  • [32] Loop Closure Detection via Locality Preserving Matching With Global Consensus
    Jiayi Ma
    Kaining Zhang
    Junjun Jiang
    IEEE/CAA Journal of Automatica Sinica, 2023, 10 (02) : 411 - 426
  • [33] Loop Closure Detection via Locality Preserving Matching With Global Consensus
    Ma, Jiayi
    Zhang, Kaining
    Jiang, Junjun
    IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2023, 10 (02) : 411 - 426
  • [34] Reliable Cosine Matching via Neighborhood Consensus for Fundus Image Registration
    Tang, Kexian
    Wang, Shuyu
    Yang, Hao
    Lai, Huilin
    Sun, Jingyi
    Luo, Ye
    PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 2478 - 2483
  • [35] Infrared and visible image fusion via global variable consensus
    Shen, Donghao
    Zareapoor, Masoumeh
    Yang, Jie
    IMAGE AND VISION COMPUTING, 2020, 104
  • [36] A Cloud Motion Estimation Method Based on Cloud Image Depth Feature Matching
    Zou, Lianglin
    Tang, Ping
    Niu, Yisen
    Yan, Zixuan
    Lin, Xilong
    Song, Jifeng
    Wang, Qian
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2025, 22
  • [37] Motion Artifact Correction for OCT Microvascular Images Based on Image Feature Matching
    Chen, Xudong
    Ma, Zongqing
    Wang, Chongyang
    Cui, Jiaqi
    Fan, Fan
    Gao, Xinxiao
    Zhu, Jiang
    JOURNAL OF BIOPHOTONICS, 2024,
  • [38] Hyperspectral Image Classification via Elastic Net Regression and Bilateral Filtering
    Soomro, Shahzad Hyder
    Xiao, Liang
    Soomro, Bushra Naz
    PROCEEDINGS OF 2015 IEEE INTERNATIONAL CONFERENCE ON PROGRESS IN INFORMATCS AND COMPUTING (IEEE PIC), 2015, : 56 - 60
  • [39] Distributed and consistent multi-image feature matching via QuickMatch
    Serlin, Zachary
    Yang, Guang
    Sookraj, Brandon
    Belta, Calin
    Tron, Roberto
    INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2020, 39 (10-11): : 1222 - 1238
  • [40] Robust image matching via ORB feature and VFC for mismatch removal
    Ma, Tao
    Fu, Wenxing
    Fang, Bin
    Hu, Fangyu
    Quan, Siwen
    Ma, Jie
    MIPPR 2017: PATTERN RECOGNITION AND COMPUTER VISION, 2017, 10609