摘 要:针对传统 Canny 算子存在梯度算子简单、阈值选取缺乏自适应性等问题,提出一种改进的高低阈值选取算法。首先将卷积模版扩大到 3×3,并对 45°和 135°方向上的权值进行优化;然后利用改进的 Otsu 法自适应地生成高低阈值;最后对局部阈值进行优化,从而完成对 Canny 算子的改进。实验结果表明,针对不同的影像,改进算法能自适应地生成符合局部特征的高低阈值,在纹理细节丰富和图像对比度较小的区域,能够在避免过多冗余信息的情况下最大限度地保留局部细节,改进后的方法能够为边缘提取提供参考。
关键词:Canny;高低阈值;Otsu;中值;局部阈值优化
DOI:10.19850/j.cnki.2096-4706.2022.20.020
中图分类号:TP391.4 文献标识码:A 文章编号:2096-4706(2022)20-0081-04
Remote Sensing Image Edge Detection Based on Improved Canny Operator High and Low Threshold Selection
LI Bingxing, REN Jianglong
(Zhongshui North Survey, Design and Research Co., Ltd., Tianjin 300222, China)
Abstract: Due to the traditional Canny algorithm has the problems of simple gradient operator and the threshold selection is not adaptive, an improved high and low threshold selection algorithm is proposed. First, the convolution template is expanded to 3×3, and the weight in 45° and 135° direction is optimized. Then, the improved Otsu method is used to adaptively generate high and low thresholds. Finally, the local threshold is optimized to improve the Canny operator. The experimental results show that, for different images, the improved algorithm can adaptively generate high and low thresholds consistent with local features. In areas with rich texture details and low image contrast, the local details can be retained as much as possible without too much redundant information. The improved method can provide a reference for edge extraction.
Keywords: Canny; high and low threshold; Otsu; median value; local threshold optimization
参考文献:
[1] 娄平,杨欣,胡辑伟,等 . 基于边缘计算的驾驶疲劳检测方法 [J]. 计算机工程,2021,47(7):13-20+29.
[2] 王超 . 基于图像增强的几种雾天图像去雾算法 [J]. 自动化应用,2018(2):70+80.
[3] 李军军,曹建农,廖娟,等 . 多方向小波变换高分影像边缘提取 [J]. 国土资源遥感,2019,31(1):8-15.
[4] 孙汝萍 . 一种改进的图像边缘提取方法 [J]. 科技通报,2018,34(10):158-161+167.
[5] 王文豪,姜明新,赵文东 . 基于 Canny 算子改进的边缘检测算法 [J]. 中国科技论文,2017,12(8):910-915.
[6] 徐辛超,付晨,徐爱功 . 一种改进的 Canny 边缘提取方法 [J]. 遥感信息,2016,31(5):43-46.
[7] 郑健,王继,宋世铭 .Canny 双阈值算子在边缘提取中的优势 [J]. 地理空间信息,2019,17(11):128-130+12.
作者简介:李昺星(1990—),男,汉族,山西忻州人,工程师,硕士研究生,研究方向:工程管理、测绘工程、摄影测量与遥感。