1.School of Computer and Communication Engineering,Northeastern University at Qinhuangdao,Qinhuangdao 066004,China
2.Hebei Key Laboratory of Marine Perception Network and Data Processing,Northeastern University at Qinhuangdao,Qinhuangdao 066004,China. Corresponding author: SUN Yu,E-mail: 2272167@stu. neu. edu. cn
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.
M 是一个实对称矩阵(二阶方阵,其元素都是实数,且转置矩阵和 M 相等),因此无论Ix 和Iy 取值如何,通过累加后矩阵仍然是对称的矩阵.由于实对称矩阵一定可以作相似对角化,即存在正交矩阵 P,使得
.
矩阵 M 的特征值为1,2,可得
.
最终每个像素点的响应函数R被定义为
.
Shi-Tomasi角点检测算法的核心在于判断矩阵 M 的较小特征值与预设阈值的关系.当R(代表较小的特征值)超过了阈值,该像素点便被认定为角点.若 M 的两个特征值都不超过阈值,意味着即便是较小的特征值也未超过阈值,这样的像素点则被归类为平坦区域的一部分.反之,如果一个特征值超过阈值而另一个未达到,此时的像素点则被视为边缘上的点.
GuanB L, ZhaoJ, LiZ, 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]
LiuY X, MoF, AleksandrovM, et al. Accurate calibration of standard plenoptic cameras using corner features from raw images[J]. Optics Express, 2021, 29(1): 158-169.
[3]
SikkaP, AsatiA R, ShekharC. Real time FPGA implementation of a high speed and area optimized Harris corner detection algorithm[J]. Microprocessors and Microsystems, 2021, 80: 103514.
[4]
GuJ F, LiuW Z. Polygon graphic recognition based on improved fast corner detection[J]. Journal of Physics: Conference Series, 2020, 1629(1): 012014.
[5]
WangY F, LiY, WangJ 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]
KumarT R, KalaiselviK, VeluC 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]
BansalM, KumarM, KumarM, 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]
YazdiR, KhotanlouH. Robust corner detector based on local maximum and minimum differences[C]// 2024 10th International Conference on Web Research (ICWR). Tehran, 2024: 92-98.
[10]
WangY H, WangJ 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]
SunX, ZhongB J, YangJ Y, et al. Corner detection via scale-space behavior-guided trajectory tracing[J]. IEEE Signal Processing Letters, 2023, 30: 50-54.
[12]
WangZ C, LiR, ShaoZ H, et al. Adaptive Harris corner detection algorithm based on iterative threshold[J]. Modern Physics Letters B, 2017, 31(15): 1750181.
HanSong-qi, YuWei-bo, YangHong-tao, et al. Improved Harris corner detection algorithm[J]. Journal of Changchun University of Technology, 2018, 39(5): 470-474.
DongLi-hong, PengYe-xun, FuLi-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.
[19]
PhamT Q, VietL J V. Separable bilateral filtering for fast video preprocessing[C]// IEEE International Conference on Multimedia and Expo. Amsterdam, 2005: 115-128.