[1]颜玉杰,刘向阳.基于测地距离的超像素分析算法[J].计算机技术与发展,2022,32(02):58-62.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 009]
　YAN Yu-jie,LIU Xiang-yang.Superpixel Analysis Algorithm Based on Geodesic Distance[J].,2022,32(02):58-62.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 009]
点击复制

基于测地距离的超像素分析算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年02期
页码:
58-62
栏目:
图形与图像
出版日期:
2022-02-10

文章信息/Info

Title:
Superpixel Analysis Algorithm Based on Geodesic Distance
文章编号:
1673-629X(2022)02-0058-05
作者:
颜玉杰; 刘向阳
河海大学 理学院,江苏 南京 211100
Author(s):
YAN Yu-jie; LIU Xiang-yang
School of Science,Hohai University,Nanjing 211100,China
关键词:
超像素分析; 超像素; Fast Marching 算法; 局部密度; 测地距离
Keywords:
superpixel analysis; superpixel; Fast Marching algorithm; local density; geodesic distance
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 02. 009
摘要:
超像素分析指的是将数字图像细分为多个超像素的过程,旨在简化或改变图像的表示形式,使得图像更容易理解和分析。 文章提出了一种基于测地距离的超像素分析算法,该算法采用引入代价函数的 Fast Marching 算法来计算像素点间的测地距离。 将目标图像大致均匀地划分成 k 个初始长方形区域,在每个区域内选取局部密度最大的像素点作为种子点,再由种子点出发计算像素点间的测地距离,并根据测地距离对像素点进行标记,故而可以得到大小均衡,形状规整的超像素。 该算法在计算测地距离时,充分考虑了像素点的颜色和位置特征,并且以小区域为单位计算测地距离不仅缩小了 Fast Marching 算法的搜索范围,加快了算法的运行速度,还可以使得某些像素点的测地距离被重复计算,便于选取最优值。 该算法所得超像素的分割精度及规整度都取得了良好的效果。
Abstract:
Superpixel analysis refers to the process of subdividing a digital image into multiple superpixels, which aims to simplify orchange the representation of the image and make the image easier to understand and analyze. We propose a superpixel analysis algorithmbased on geodesic distance,which uses Fast Marching algorithm with cost function to calculate the geodesic distance between pixels. Thetarget image is roughly evenly divided into k initial rectangular regions. In each region,the pixel with the highest local density is selectedas the seed point,and then the geodesic distance between the pixels is calculated from the seed point,and the pixels are marked accordingto the geodesic distance, so the size of the balanced and regular shape super - pixel can be obtained. When calculating the geodesicdistance,the algorithm fully takes the color and location of pixels into account,and calculates the geodesic distance in a small area, whichnot only reduces the search scope of Fast Marching algorithm,speeds up the operation speed of the algorithm,but also makes the geodesicdistance of some pixels be repeatedly calculated,which is convenient for selecting the optimal value. The segmentation accuracy andregularity of the superpixel obtained by this algorithm is effective.

相似文献/References:

[1]辛月兰.基于超像素的Grabcut彩色图像分割[J].计算机技术与发展,2013,(07):48.
　XIN Yue-lan.Superpixel-based Grabcut Color Image Segmentation[J].,2013,(02):48.
[2]袁恒东.基于标签传递图割的图像分割算法[J].计算机技术与发展,2017,27(12):35.[doi:10.3969/ j. issn.1673-629X.2017.12.008]
　YUAN Heng-dong.An Image Segmentation Algorithm Based on Label Propagation Graph Cut[J].,2017,27(02):35.[doi:10.3969/ j. issn.1673-629X.2017.12.008]
[3]张小凤,刘向阳.基于图像超像素分析的图像分割方法[J].计算机技术与发展,2018,28(07):25.[doi:10.3969/ j. issn.1673-629X.2018.07.006]
　ZHANG Xiao-feng,LIU Xiang-yang.Image Segmentation Based on Image Superpixel Analysis[J].,2018,28(02):25.[doi:10.3969/ j. issn.1673-629X.2018.07.006]
[4]张 健,钟中志,柯艳国,等.基于 MHSW 特征融合的火焰检测[J].计算机技术与发展,2019,29(12):184.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 033]
　ZHANG Jian,ZHONG Zhong-zhi,KE Yan-guo,et al.Flame Detection Based on MHSW Feature Fusion[J].,2019,29(02):184.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 033]
[5]汪 昊,刘向阳.基于区域中心的交互式图像前景提取方法[J].计算机技术与发展,2020,30(02):12.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 003]
　WANG Hao,LIU Xiang-yang.An Interactive Image Foreground Extraction Method Based on Region Center[J].,2020,30(02):12.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 003]
[6]赵晓梅,刘兆邦,张正平,等.基于超像素和密度聚类算法的皮肤镜图像分割[J].计算机技术与发展,2020,30(06):167.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 032]
　ZHAO Xiao-mei,LIU Zhao-bang,ZHANG Zheng-ping,et al.Dermoscopy Image Segmentation Based on Superpixel and Density Clustering Algorithm[J].,2020,30(02):167.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 032]
[7]李 普,陈 黎.基于超像素随机游走的自然场景图像分割方法[J].计算机技术与发展,2021,31(12):61.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 011]
　LI Pu,CHEN Li.Natural Scene Image Segmentation Method Based on Super-pixel Random Walk[J].,2021,31(02):61.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 011]

更新日期/Last Update: 2022-02-10