基于自适应阈值Canny边缘检测的Shi-Tomasi角点检测方法

doi:10.12068/j.issn.1005-3026.2025.20240067

摘要/Abstract

摘要：

传统的Shi-Tomasi角点检测算法已经广泛应用于许多计算机视觉领域中，效率和精度较低，抗噪性能较差，且容易产生伪角点.本文提出了一种融合自适应阈值Canny边缘检测和改进的Shi-Tomasi角点检测的方法：首先，通过改进的Canny边缘检测对图像进行边缘提取并筛选候选角点，同时采用一维信息熵自适应阈值以适应不同的图像环境，从而提高检测的效率和鲁棒性.其次，利用圆形模板进行非极大值抑制，减少误检角点的数量，以增强算法对真实角点的识别能力.最后，在提取的边缘图像上应用改进的Shi-Tomasi算法进行角点检测，从而实现图像的精准定位.实验结果表明，与传统算法相比，所提出的算法在运行时间和准确度上均有显著提升，且在旋转不变性和抗噪性上有明显的优势.

关键词: 角点检测, 自适应阈值, Canny, Shi-Tomasi

Abstract:

The traditional Shi-Tomasi corner detection algorithm has been widely applied in many fields of computer vision. However， this algorithm has low efficiency and accuracy， poor noise resistance， and is prone to producing false corners. A method that combined adaptive threshold Canny edge detection and improved Shi-Tomasi corner detection was proposed. Firstly， improved Canny edge detection was used to extract image edges and screen candidate corner points， while a one-dimensional information entropy adaptive threshold was used to adapt to different image environments， thereby improving the efficiency and robustness of detection. Secondly， using circular templates for non-maximum suppression reduced the number of false corner points and enhanced the algorithm’s ability to recognize true corners. Finally， the improved Shi-Tomasi algorithm was applied to the extracted edge images for corner extraction， thereby achieving accurate image localization. The experimental results show that compared with the traditional algorithm， the proposed method has significant improvements in runtime and accuracy， and it has significant advantages in rotation invariance and noise resistance.

Key words: corner detection, adaptive threshold, Canny, Shi-Tomasi

中图分类号:

TP 391

张铫, 孙宇, 林清河, 王怀. 基于自适应阈值Canny边缘检测的Shi-Tomasi角点检测方法[J]. 东北大学学报（自然科学版）, 2025, 46(10): 36-43.

Yao ZHANG, Yu SUN, Qing-he LIN, Huai WANG. Shi-Tomasi Corner Detection Method Based on Adaptive Threshold Canny Edge Detection[J]. Journal of Northeastern University(Natural Science), 2025, 46(10): 36-43.

图/表 11

图1 图像预处理流程

Fig.1 Flow chart of image preprocessing

图2 两种滤波效果对比（a）—高斯滤波；（b）—双边滤波.

Fig.2 Comparison of two filtering effects

图3 非极大值抑制二值图

Fig.3 Binary graph of non-maximum suppression

图4 边缘检测预处理效果（a）—传统Canny边缘检测；（b）—改进Canny边缘检测.

Fig.4 Edge detection preprocessing effect

图5 传统算法和圆形模板算法（a）—传统算法矩形窗；（b）—传统算法窗口旋转；（c）—圆形模板窗口；（d）—圆形模板窗口旋转.

Fig.5 Traditional algorithm and circular template algorithm

图6 角点提取结果对比（a）—原图像1；（b）—传统算法处理；（c）—本文算法处理；（d）—原图像2；（e）—传统算法处理；（f）—本文算法处理.

Fig.6 Comparison of corner extraction results

表1 算法运行时间对比结果

Table 1 Algorithm runtime comparison results

检测算法	平均时间/s
传统算法	0.042 498
本文算法	0.038 086

表2 算法精准度对比结果

Table 2 Algorithm accuracy comparison results

算法	正确角点数	伪角点数	漏检角点数	精准度/%
传统算法(q=0.01)	58	35	2	61.05
本文算法(q=0.01)	54	10	6	77.14
传统算法(q=0.02)	57	25	3	67.06
本文算法(q=0.02)	55	9	5	79.71

图7 原图像旋转45°后的对比图

Fig.7 Comparison of original image after

表3 不同角度错准比对比结果 (different angles)

Table 3 Comparison results of misalignment ratio at

旋转角度/（°）	检测算法	正确角点数	伪角点数	漏检角点数	错准比/%
25	传统算法	43	6	17	53.49
25	本文算法	47	2	13	31.91
45	传统算法	46	4	14	39.13
45	本文算法	48	1	12	27.08
70	传统算法	44	8	16	54.55
70	本文算法	47	1	13	29.79
90	传统算法	46	5	14	41.31
90	本文算法	48	2	12	29.17

图8 抗噪性对比结果（a）—传统算法；（b）—本文算法.

Fig.8 Noise resistance comparison results

参考文献 16

[1]	Guan B L， Zhao J， Li Z， et al. Minimal solutions for relative pose with a single affine correspondence［C］// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， 2020： 1929-1938.
[2]	Liu Y X， Mo F， Aleksandrov M， et al. Accurate calibration of standard plenoptic cameras using corner features from raw images［J］. Optics Express， 2021， 29（1）： 158-169.
[3]	Sikka P， Asati A R， Shekhar C. Real time FPGA implementation of a high speed and area optimized Harris corner detection algorithm［J］. Microprocessors and Microsystems， 2021， 80： 103514.
[4]	Gu J F， Liu W Z. Polygon graphic recognition based on improved fast corner detection［J］. Journal of Physics： Conference Series， 2020， 1629（1）： 012014.
[5]	Wang Y F， Li Y， Wang J Q， et al. A target corner detection algorithm based on the fusion of FAST and Harris［J］. Mathematical Problems in Engineering， 2022， 2022（1）： 4611508.
[6]	Kumar T R， Kalaiselvi K， Velu C M， et al. Mammogram image segmentation using SUSAN corner detection［C］// 2021 Second International Conference on Electronics and Sustainable Communication Systems （ICESC）. Coimbatore， 2021： 1190-1194.
[7]	Bansal M， Kumar M， Kumar M， et al. An efficient technique for object recognition using Shi-Tomasi corner detection algorithm［J］. Soft Computing， 2021， 25（6）： 4423-4432.
[8]	Shanker ， O. Defining dimension of a complex network［J］. Modern Physics Letters B， 2011， 21（6）： 321-326.
[9]	Yazdi R， Khotanlou H. Robust corner detector based on local maximum and minimum differences［C］// 2024 10th International Conference on Web Research （ICWR）. Tehran， 2024： 92-98.
[10]	Wang Y H， Wang J M. Fingertip detection based on Freeman chain code analysis［C］// 2022 5th International Conference on Advanced Electronic Materials， Computers and Software Engineering （AEMCSE）. Wuhan， 2022： 651-654.
[11]	Sun X， Zhong B J， Yang J Y， et al. Corner detection via scale-space behavior-guided trajectory tracing［J］. IEEE Signal Processing Letters， 2023， 30： 50-54.
[12]	Wang Z C， Li R， Shao Z H， et al. Adaptive Harris corner detection algorithm based on iterative threshold［J］. Modern Physics Letters B， 2017， 31（15）： 1750181.
[13]	韩松奇，于微波，杨宏涛，等. 改进Harris角点检测算法［J］.长春工业大学学报， 2018， 39（5）：470-474.
	Han Song-qi， Yu Wei-bo， Yang Hong-tao， et al. Improved Harris corner detection algorithm［J］. Journal of Changchun University of Technology， 2018， 39（5）： 470-474.
[14]	汪强，郭来功. 自适应阈值Harris算法遥感图像配准的FPGA实现［J］.无线互联科技， 2023， 20（24）： 110-112.
	Wang Qiang， Guo Lai-gong. FPGA implementation of adaptive threshold Harris algorithm for remote sensing image registration［J］. Wireless Interconnection Technology， 2023， 20（24）： 110-112.
[15]	董立红，彭业勋，符立梅.基于Sobel边缘检测的圆周Harris角点检测算法［J］. 西安科技大学学报， 2019， 39（2）：374-380.
	Dong Li-hong， Peng Ye-xun， Fu Li-mei. Circumference Harris corner detection algorithm based on Sobel edge detection ［J］. Journal of Xi’an University of Science and Technology，2019， 39（2）： 374-380.
[16]	Pham T Q， Viet L J V. Separable bilateral filtering for fast video preprocessing［C］// IEEE International Conference on Multimedia and Expo. Amsterdam， 2005： 115-128.