基于自适应阈值的型钢精确角点FAST检测算法

doi:10.16183/j.cnki.jsjtu.2023.276

摘要/Abstract

摘要：

基于机器视觉的在线型钢平直度检测中,对型钢图像关键角点快速、准确地提取是实现精确检测的关键技术问题.针对加速分割检验特征提取(FAST)算法需要人工设定角点筛选阈值和角点提取存在大量伪角点的问题,提出一种自适应阈值生成及校正策略,能够在自动获取初始阈值的基础上,根据角点数是否达到初始角点集要求对阈值实时校正直至达到适当值,以减少关键角点遗漏.在采用FAST提取角点的基础上,利用最小核心值相似区域(SUSAN)算法剔除伪角点,以保证关键角点提取的有效性.试验证明,这种基于自适应阈值的FAST角点检测算法(FAST-A),在检测环境和对象特性发生变化时,仍然可以准确、快速地检测到型钢关键角点,在为型钢平直度检测实时提供精确角点的基础上,提高角点提取的自适应性.

关键词: 型钢, 角点检测, 加速分割检验特征提取算法, 最小核心值相似区域算法, 自适应阈值

Abstract:

The on-line flatness detection of section steel based on machine vision is a key technical problem for quickly and accurately extracting key corner points from section steel images to enable accurate detection. Aiming at the problem that the features from accelerated segment test (FAST) algorithm needs to manually set the corner points screening threshold and there are numerous false corner points in corner point extraction, this paper proposes an adaptive threshold generation and correction strategy. Based on the automatic determination of the initial threshold, this strategy can adjust the threshold in real time until an appropriate value is reached according to the requirements of the initial corner points set, thereby to reduce the risk of missing key corner points. In addition to using FAST algorithm to extract corner points, the smallest univalue segment assimilating nucleus (SUSAN) algorithm is employed to eliminate false corner points ensuring the effectiveness of key corner points extraction. The experiments prove that the FAST corner detection algorithm based on adaptive threshold (FAST-A) can still accurately and quickly detect key corner points even when the detection environment and object characteristics change. Furthermore, the algorithm proposed provides accurate corner points for real-time section steel flatness detection, and improves the adaptability of corner points extraction.

Key words: section steel, corner points detection, features from accelerated segment test (FAST) algorithm, smallest univalue segment assimilating nucleus (SUSAN) algorithm, adaptive threshold

中图分类号:

TP391.4

包家汉, 孙德尚, 黄建中, 胡政. 基于自适应阈值的型钢精确角点FAST检测算法[J]. 上海交通大学学报, 2025, 59(5): 691-702.

BAO Jiahan, SUN Deshang, HUANG Jianzhong, HU Zheng. FAST Algorithm for Accurate Corner Points Detection of Section Steel Based on Adaptive Threshold[J]. Journal of Shanghai Jiao Tong University, 2025, 59(5): 691-702.

图/表 20

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

图10

图11

图12

图13

图14

图15

图16

图17

图18

表2

参考文献 32

[1]	段永强, 王琨, 刘宏波. H型钢矫裂缺陷的原因分析及对策[J]. 包钢科技, 2017, 43(6): 23-25.
	DUAN Yongqiang, WANG Kun, LIU Hongbo. Cause analysis and countermeasures for straightening crack defects of H-beam[J]. Science and Technology of Baotou Steel, 2017, 43(6): 23-25.
[2]	杨海马, 江斌, 钱隆平, 等. 基于轨型重建的平直度提取算法研究[J]. 电子测量与仪器学报, 2022, 36(9): 1-11.
	YANG Haima, JIANG Bin, QIAN Longping, et al. Research on flatness extraction algorithm based on rail type reconstruction[J]. Journal of Electronic Measurement and Instrument, 2022, 36(9): 1-11.
[3]	肖尧, 刘瑾, 杨海马, 等. 非接触式钢轨类大构件平直度检测算法研究[J]. 传感器与微系统, 2020, 39(9): 56-59.
	XIAO Yao, LIU Jin, YANG Haima, et al. Study on flatness and straightness measurement algorithm of non-contact rail type large components[J]. Transducer and Microsystem Technologies, 2020, 39(9): 56-59.
[4]	刘庆纲, 樊志国, 刘超, 等. H型钢端面尺寸的精密视觉检测方法[J]. 光电工程, 2013, 40(11): 1-7.
	LIU Qinggang, FAN Zhiguo, LIU Chao, et al. Precision visual inspection method for the end face dimension of H-shaped steel[J]. Opto-Electronic Engineering, 2013, 40(11): 1-7.
[5]	张伟, 韩宗旺, 程祥, 等. 基于机器视觉零件轴线直线度误差测量的研究[J]. 光学精密工程, 2021, 29(9): 2168-2177.
	ZHANG Wei, HAN Zongwang, CHENG Xiang, et al. Research on straightness error measurement of part axis based on machine vision[J]. Optical Precision Engineering, 2021, 29(9): 2168-2177.
[6]	章为川, 孔祥楠, 宋文. 图像的角点检测研究综述[J]. 电子学报, 2015, 43(11): 2315-2321. doi: 10.3969/j.issn.0372-2112.2015.11.026
	ZHANG Weichuan, KONG Xiangnan, SONG Wen. Review of image corner detection algorithms[J]. Acta Electronica Sinica, 2015, 43(11): 2315-2321. doi: 10.3969/j.issn.0372-2112.2015.11.026
[7]	崔建国, 孙长库, 李玉鹏, 等. 基于SURF的快速图像匹配改进算法[J]. 仪器仪表学报, 2022, 43(8): 47-53.
	CUI Jianguo, SUN Changku, LI Yupeng, et al. An improved algorithm for fast image matching based on SURF[J]. Chinese Journal of Scientific Instrument, 2022, 43(8): 47-53.
[8]	赵斌, 周军. 基于改进棋盘的角点自动检测与排序[J]. 光学精密工程, 2015, 23(1): 237-244.
	ZHAO Bin, ZHOU Jun. Automatic detection and sorting of corners by improved chessboard pattern[J]. Optical Precision Engineering, 2015, 23(1): 237-244.
[9]	薛梦霞, 刘士荣, 王坚. 基于机器视觉的动态多目标识别[J]. 上海交通大学学报, 2017, 51(6): 727-733.
	XUE Mengxia, LIU Shirong, WANG Jian. Dynamic multi-target recognition based on machine vision[J]. Journal of Shanghai Jiao Tong University, 2017, 51(6): 727-733.
[10]	周志艳, 闫梦璐, 陈盛德, 等. Harris角点自适应检测的水稻低空遥感图像配准与拼接算法[J]. 农业工程学报, 2015, 31(14): 186-193.
	ZHOU Zhiyan, YAN Menglu, CHEN Shengde, et al. Image registration and stitching algorithm of rice low-altitude remote sensing based on Harris corner self-adaptive detection[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(14): 186-193.
[11]	牛牧, 许黎明, 赵达, 等. 基于工件轮廓图像的砂轮磨损在线检测方法[J]. 上海交通大学学报, 2021, 55(3): 221-228. doi: 10.16183/j.cnki.jsjtu.2019.285
	NIU Mu, XU Liming, ZHAO Da, et al. Workpiece-contour-image based wheel wear online detection methodology[J]. Journal of Shanghai Jiao Tong University, 2021, 55(3): 221-228.
[12]	王巍, 赵红蕊. 面向影像匹配的SUSAN角点检测[J]. 遥感学报, 2011, 15(5): 940-956.
	WANG Wei, ZHAO Hongrui. The improvement of SUSAN for image matching[J]. National Remote Sensing Bulletin, 2011, 15(5): 940-956.
[13]	SMITH S M, BRADY J M. SUSAN—A new approach to low level image processing[J]. International Journal of Computer Vision, 1997, 23(1): 45-78.
[14]	ROSTEN E, DRUMMOND T. Machine learning for high-speed corner detection[C]// Computer Vision-ECCV 2006: 9th European Conference on Computer Vision. Graz, Austria: Springer Berlin Heidelberg, 2006: 430-443.
[15]	HARRIS C, STEPHENS M. A combined corner and edge detector[C]// Proceedings of the Alvey Vision Conference. Manchester, UK: Alvety Vision Club, 1988: 147-152.
[16]	BAY H, TUYTELAARS T, VAN GOOL L. SURF: Speeded up robust features[J]. Lecture Notes in Computer Science, 2006, 3951: 404-417.
[17]	JIANG M, WU Y, ZHAO T, et al. Pointsift:A sift-like network module for 3d point cloud semantic segmentation[DB/OL]. (2018-11-24) [2023-09-26]. https://doi.org/10.48550/arXiv.1807.00652.
[18]	高礼圳, 刘书桂, 韩振华. 零件的角点提取及匹配定位[J]. 中国光学, 2016, 9(4): 397-404.
	GAO Lizhen, LIU Shugui, HAN Zhenhua. Corner extraction and matching location of parts[J]. China Optics, 2016, 9(4): 397-404.
[19]	张立亭, 黄晓浪, 鹿琳琳, 等. 基于灰度差分与模板的Harris角点检测快速算法[J]. 仪器仪表学报, 2018, 39(2): 218-224.
	ZHANG Liting, HUANG Xiaolang, LU Linlin, et al. Fast Harris corner detection based on gray difference and template[J]. Chinese Journal of Scientific Instrument, 2018, 39(2): 218-224.
[20]	邓淇元, 曲长文, 江源. 基于圆环模板的改进Harris角点检测算法[J]. 系统工程与电子技术, 2016, 38(4): 949-954.
	DENG Qiyuan, QU Changwen, JIANG Yuan. Improved corner detection algorithm based on circle mask via Harris[J]. Systems Engineering and Electronics, 2016, 38(4): 949-954. doi: 10.3969/j.issn.1001-506X.2016.04.32
[21]	CHEN X, LIU L, SONG J, et al. Corner detection and matching for infrared image based on double ring mask and adaptive SUSAN algorithm[J]. Optical and Quantum Electronics, 2018, 50: 1-10.
[22]	WANG Y, TANG X, XIA M, et al. An improved self-adapting corner detection algorithm for low-contrast images[C]// 2022 5th International Symposium on Autonomous Systems. Hangzhou, China: IEEE, 2022: 1-4.
[23]	WANG M Y, ZHANG W, SUN C, et al. Corner detection based on shearlet transform and multi-directional structure tensor[J]. Pattern Recognition, 2020, 103: 107299.
[24]	WANG Y, LI Y, WANG J, et al. A target corner detection algorithm based on the fusion of FAST and Harris[J]. Mathematical Problems in Engineering, 2022, 2022: 1-16.
[25]	XIONG W, TIAN W, YANG Z, et al. Improved FAST corner-detection method[J]. The Journal of Engineering, 2019, 2019(19): 5493-5497.
[26]	ZHANG H, XIAO L, XU G. A novel tracking method based on improved FAST corner detection and pyramid LK optical flow[C]// 2020 Chinese Control and Decision Conference. Hefei, China: IEEE, 2020: 1871-1876.
[27]	刘国华, 李亮玉. 基于机器视觉的分钢机械手定位及运动轨迹分析[J]. 机械设计, 2015, 32(4): 40-45.
	LIU Guohua, LI Liangyu. Positioning and trajectory planning of steel-bar-splitting manipulator based on machine vision[J]. Journal of Machine Design, 2015, 32(4): 40-45.
[28]	张懿, 刘艺. 基于FAST特征的快速图像拼接系统研究[J]. 计算机工程与应用, 2016, 52(10): 167-170.
	ZHANG Yi, LIU Yi. Study of image registration system based on FAST feature[J]. Computer Engineering and Applications, 2016, 52(10): 167-170.
[29]	刘丹, 王运宏. 限制型自适应SUSAN边缘检测算法[J]. 计算机辅助设计与图形学学报, 2020, 32(6): 971-978.
	LIU Dan, WANG Yunhong. Constraint self-adaptive SUSAN algorithm for edge detection[J]. Journal of Computer-Aided Design & Computer Graphics, 2020, 32(6): 971-978.
[30]	朱思聪, 周德龙. 角点检测技术综述[J]. 计算机系统应用, 2020, 29(1): 22-28.
	ZHU Sicong, ZHOU Delong. Review on image corner detection[J]. Computer Systems & Applications, 2020, 29(1): 22-28.
[31]	杨幸芳, 黄玉美, 李艳, 等. 一种基于USAN的特征点检测算法[J]. 机械科学与技术, 2011, 30(7): 1120-1123.
	YANG Xingfang, HUANG Yumei, LI Yan, et al. An algorithm for feature points detection based on univalue segment assimilating nucleus[J]. Mechanical Science and Technology for Aerospace Engineering, 2011, 30(7): 1120-1123.
[32]	王民, 周兆镇, 李昌华, 等. 基于像素点灰度差的Harris角点检测算法[J]. 计算机工程, 2015, 41(6): 227-230. doi: 10.3969/j.issn.1000-3428.2015.06.041
	WANG Min, ZHOU Zhaozhen, LI Changhua, et al. Harris corner detection algorithm based on pixel point gray difference[J]. Computer Engineering, 2015, 41(6): 227-230. doi: 10.3969/j.issn.1000-3428.2015.06.041

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	0	55	0	27

来源	本网站	其他网站

次数	28	54
比例	34%	66%

摘要

1262

最新录用	在线预览	正式出版

99	0	1163

来源	本网站	其他网站

次数	47	1215
比例	4%	96%

阈值变化	M_n_-1变化	状态判断
增大	减少	正常
减少	增大	正常
增大	增大	异常
减少	减少	异常
增大或减少	M≫b	异常