Screening Method for Feature Matching Based on Dynamic Window Motion Statistics

被引：0
|
作者：
Xiang H. [1 ,2 ]
Zhou L. [1 ]
Ba X. [1 ,3 ]
Chen J. [1 ]
机构：
[1] Institute of Microelectronics of the Chinese Academy of Sciences, Beijing
[2] School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing
[3] School of Microelectronics, University of Chinese Academy of Sciences, Beijing
来源：
Huanan Ligong Daxue Xuebao/Journal of South China University of Technology (Natural Science) | 2020年 / 48卷 / 06期
基金：
中国国家自然科学基金;
关键词：
Dynamic window; Fast approximate nearest neighbor; Feature matching; Motion statistics;
D O I：
10.12141/j.issn.1000-565X.190769
中图分类号：
学科分类号：
摘要：
During the image local feature matching process, error matches will be eliminated effectively by conside-ring the motion statistics of features. However, the current grid-based method of motion statistics works poorly with zoom and rotation. To solve this problem, a screening method for feature matching based on dynamic window motion statistics was proposed. Firstly, the algorithm builds a fast approximate nearest neighbor index structure based on the location of image feature points. Then it sets up the dynamic window and computes motion statistics. Fina-lly, it eliminates error matches with the score of motion statistics. The experimental results show that, compared with other methods, the proposed method has a significant advantage over the algorithm based on grid in predicating precision and recall rate when the scale and angle change greatly. And in more general scenarios, the overall matching effect of this algorithm is better than other real-time matching methods. Meanwhile, this algorithm has good time performance and can be applied to real-time tasks. © 2020, Editorial Department, Journal of South China University of Technology. All right reserved.
引用
收藏
页码：114 / 122
页数：8
相关论文
共 21 条
  • [1] HOSSEIN-NEJAD Z, NASRI M., An adaptive image registration method based on SIFT features and RANSAC transform [J], Computers & Electrical Engineering, 62, pp. 524-537, (2017)
  • [2] BIAN J W, LIN W Y, MATSUSHITA Y, Et al., GMS:grid-based motion statistics for fast,ultra-robust feature correspondence [C], Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2828-2837, (2017)
  • [3] MA J, ZHAO J, JIANG J, Et al., Locality preserving matching [C], Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, pp. 4492-4498, (2017)
  • [4] MA J, JIANG J, ZHOU H, Et al., Guided locality preserving feature matching for remote sensing image registration [J], IEEE Transactions on Geoscience and Remote Sensing, 56, 8, pp. 4435-4447, (2018)
  • [5] MA J, ZHAO J, JIANG J, Et al., Visual homing via guided locality preserving matching [C], Proceedings of 2018 IEEE International Conference on Robotics and Automation(ICRA), pp. 7254-7261, (2018)
  • [6] LOWE D G., Distinctive image features from scale-invariant keypoints [J], International Journal of Computer Vision, 60, 2, pp. 91-110, (2004)
  • [7] JIANG D G, SUN H J, JUNKAI A., Approximate nearest neighbor searching algorithm based on distance [J], Journal of Beijing University of Chemical Techno-logy, 44, 5, pp. 94-98, (2017)
  • [8] WESS S, ALTHOFF K, DERWAND G., Using k-d trees to improve the retrieval step in case-based reasoning [C], Proceedings of Selected Papers from the First European Workshop on Topics in Case-based Reasoning, pp. 167-181, (1993)
  • [9] BAY H, TUYTELAARS T, VAN GOOL L., Surf:speeded up robust features [C], Proceedings of Computer Vision-ECCV 2006, pp. 404-417, (2006)
  • [10] ALCANTARILLA P, BARTOLI A, Davison A., KAZE features [C], Proceedings of Computer Vision-ECCV 2012, pp. 214-227, (2012)
123