Knowledge Commons of Institute of Automation,CAS
An occlusion-resistant circle detector using inscribed triangles | |
Zhao, Mingyang1,3; Jia, Xiaohong1,3; Yan, Dong-Ming2,3 | |
发表期刊 | PATTERN RECOGNITION |
ISSN | 0031-3203 |
2021 | |
卷号 | 109页码:15 |
通讯作者 | Jia, Xiaohong(xhjia@amss.ac.cn) |
摘要 | Circle detection is a critical issue in pattern recognition and image analysis. Conventional geometry-based methods such as tangent or symmetry are sensitive to noise or occlusion. Area computation is more robust against noise, because it avoids differential calculations. Inspired by this characteristic, we present a novel method for fast circle detection using inscribed triangles. The proposed algorithm, which is robust to noise and resistant to occlusion, first extracts circular arcs by approximating line segments and identifying inflection points and sharp corners. To speed up the computation, irrelevant segments are filtered out through the triangle inequality. Arcs that belong to the same circle are then combined according to the position constraint and the inscribed triangle constraint. The circle parameters are further estimated by inscribed triangles based upon the Theil-Sen estimator and linear error refinement without the dependence of least-square fitting but still with the equivalent accuracy. Finally, candidate circles are verified to prune false positives through an inlier ratio rule, which jointly considers both distance and angle deviations. Extensive experiments are conducted on synthetic images including overlapping circles, and real images from four diverse datasets (three publicly available and one we built). Results are compared with those of representative state-of-the-art methods, and the proposed method is demonstrated to embraces several advantages: resistant to occlusion, more robust to noise, and better performance and efficiency. (C) 2020 Elsevier Ltd. All rights reserved. |
关键词 | Circle detection Inscribed triangle Parameter estimation Hough transform |
DOI | 10.1016/j.patcog.2020.107588 |
关键词[WOS] | HOUGH-TRANSFORM ; DETECTION ALGORITHM ; ELLIPSE DETECTOR |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61872354] ; National Natural Science Foundation of China[61772523] ; National Key R&D Program of China[2019YFB2204104] ; Beijing Natural Science Foundation[L182059] ; Beijing Natural Science Foundation[Z190004] ; Intelligent Science and Technology Advanced subject project of University of Chinese Academy of Sciences[115200S001] ; Open Research Fund Program of State key Laboratory of Hydroscience and Engineering, Tsinghua University[sklhse-2020-D-07] ; Alibaba Group through Alibaba Innovative Research Program |
项目资助者 | National Natural Science Foundation of China ; National Key R&D Program of China ; Beijing Natural Science Foundation ; Intelligent Science and Technology Advanced subject project of University of Chinese Academy of Sciences ; Open Research Fund Program of State key Laboratory of Hydroscience and Engineering, Tsinghua University ; Alibaba Group through Alibaba Innovative Research Program |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000573025400001 |
出版者 | ELSEVIER SCI LTD |
七大方向——子方向分类 | 模式识别基础 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/41993 |
专题 | 多模态人工智能系统全国重点实验室_三维可视计算 |
通讯作者 | Jia, Xiaohong |
作者单位 | 1.Chinese Acad Sci, Acad Math & Syst Sci, NCMIS, KLMM, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Zhao, Mingyang,Jia, Xiaohong,Yan, Dong-Ming. An occlusion-resistant circle detector using inscribed triangles[J]. PATTERN RECOGNITION,2021,109:15. |
APA | Zhao, Mingyang,Jia, Xiaohong,&Yan, Dong-Ming.(2021).An occlusion-resistant circle detector using inscribed triangles.PATTERN RECOGNITION,109,15. |
MLA | Zhao, Mingyang,et al."An occlusion-resistant circle detector using inscribed triangles".PATTERN RECOGNITION 109(2021):15. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论