自然场景下多区域特征融合的混合航拍图像分割算法

doi:10.11772/j.issn.1001-9081.2020101567

计算机应用 ›› 2021, Vol. 41 ›› Issue (8): 2445-2452.DOI: 10.11772/j.issn.1001-9081.2020101567

所属专题：第八届CCF大数据学术会议（CCF Bigdata 2020）

• 第八届CCF大数据学术会议 • 上一篇下一篇

自然场景下多区域特征融合的混合航拍图像分割算法

杨瑞, 钱晓军, 孙振强, 许振

南京师范大学计算机与电子信息学院, 南京 210023

收稿日期:2020-10-12 修回日期:2020-11-04 出版日期:2021-08-10 发布日期:2021-01-27
通讯作者: 钱晓军
作者简介:杨瑞(1995-),男,江苏泰州人,硕士研究生,主要研究方向:图像处理、自动化识别;钱晓军(1971-),男,江苏南京人,教授,硕士,主要研究方向:物联网、图像处理;孙振强(1997-),男,江苏无锡人,硕士研究生,主要研究方向:图像处理、自动化识别;许振(1996-),男,江苏常州人,硕士研究生,主要研究方向:图像处理、自动化识别。
基金资助:
江苏省水利科技项目（2019052）。

Hybrid aerial image segmentation algorithm based on multi-region feature fusion for natural scene

YANG Rui, QIAN Xiaojun, SUN Zhenqiang, XU Zhen

School of Computer Science and Electronics Information, Nanjing Normal University, Nanjing Jiangsu 210023, China

Received:2020-10-12 Revised:2020-11-04 Online:2021-08-10 Published:2021-01-27
Supported by:
This work is partially supported by the Water Conservancy Science Project of Jiangsu (2019052).

摘要/Abstract

摘要： 混合图像分割算法所包含的两个部件中，初始分割不能形成低误分割率的过分割区域集，而区域合并存在缺少区域合并标号选择机制，且存在确定区域合并停止时刻的方式常不满足场景需求的不足。针对以上问题，提出一种基于多级区域信息融合的混合图像分割算法（MRIHS）。首先，使用改进的马尔可夫模型平滑超像素块，以形成初始分割区域；其次，在对初始分割区域进行相似性度量并选定待合并区域对后，利用设计出的区域标号选择机制来选定合并后的区域标号；最后，定义一种最佳合并状态以确定合并停止时刻。为验证MRIHS性能，在视觉对象类别（VOC）、剑桥驾驶标签视频数据库（CamVid）、自建的河湖巡检（rli）数据集上，将其与基于多维特征融合的混合图像分割算法（MFHS）、改进的基于区域合并的FCM图像分割算法（IFRM）、基于段间和边界均质性的混合图像分割算法（IBHHS）、基于多维色彩变换与一致性的混合图像分割算法（MCCHS）进行对比。结果表明：MRIHS在VOC、rli数据集上的边缘召回率（BR）、可达分割精准度（ASA）、查全率、重合率至少分别比其余算法提高了0.43个百分点、0.35个百分点、0.41个百分点、0.84个百分点；欠分割误差（UE）至少减少了0.65个百分点。在CamVid数据集上，MRIHS的查全率、重合率指标至少比其余算法提高了1.11个百分点、2.48个百分点。

关键词: 初始分割, 区域合并, 混合图像分割, 块状马尔可夫随机场, 超像素块

Abstract: In the two components of hybrid image segmentation algorithm, the initial segmentation cannot form the over-segmentation region sets with low wrong segmentation rate, while region merging lacks the label selection mechanism for region merging and the method of determining region merging stopping moment in this component commonly does not meet the scenario requirements. To solve the above problems, a Multi-level Region Information fusion based Hybrid image Segmentation algorithm (MRIHS) was proposed. Firstly, the improved Markov model was used to smooth the superpixel blocks, so as to form initial segmentation regions. Then, the designed region label selection mechanism was used to select the labels of the merged regions after measuring the similarity of the initial segmentation regions and selecting the region pairs to be merged. Finally, an optimal merging state was defined to determine region merging stopping moment. To verify MRIHS performance, comparison experiments between this algorithm with Multi-dimensional Feature fusion based Hybrid image Segmentation algorithm (MFHS), Improved FCM image segmentation algorithm based on Region Merging (IFRM), Inter-segment and Boundary Homogeneities based Hybrid image Segmentation algorithm (IBHHS), Multi-dimensional Color transform and Consensus based Hybrid image Segmentation algorithm (MCCHS) were carried out on Visual Object Classes (VOC), Cambridge-driving labeled Video database (CamVid) and the self-built river and lake inspection (rli) datasets. The results show that on VOC and rli datasets, the Boundary Recall (BR), Achievable Segmentation Accuracy (ASA), recall and dice of MRIHS are at least increased by 0.43 percentage points, 0.35 percentage points, 0.41 percentage points, 0.84 percentage points respectively and the Under-segmentation Error (UE) of MRIHS is at least decreased by 0.65 percentage points compared with those of other algorithms; on CamVid dataset, the recall and dice of MRIHS are at least improved by 1.11 percentage points, 2.48 percentage points respectively compared with those of other algorithms.

Key words: initial segmentation, region merging, hybrid image segmentation algorithm, Block Markov Random Field (BMRF), superpixel block

中图分类号:

TP391.41

杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.

YANG Rui, QIAN Xiaojun, SUN Zhenqiang, XU Zhen. Hybrid aerial image segmentation algorithm based on multi-region feature fusion for natural scene[J]. Journal of Computer Applications, 2021, 41(8): 2445-2452.

参考文献

[1] ZENG J,LIU Z Q. Type-2 fuzzy Markov random fields and their application to handwritten Chinese character recognition[J]. IEEE Transactions on Fuzzy Systems,2008,16(3):747-760.
[2] 张喆, 韩德强, 杨艺. 基于证据马尔可夫随机场模型的图像分割[J]. 控制与决策,2017,32(9):1607-1613.(ZHANG Z,HAN D Q,YANG Y. Image segmentation based on evidential Markov random field model[J]. Control and Decision,2017,32(9):1607-1613.)
[3] XU X F,GUAN Y,GONG H,et al. Automated brain region segmentation for single cell resolution histological images based on Markov random field[J]. Neuroinformatics, 2020, 18(2):181-197.
[4] HARIS K,EFSTRATIADIS S N,MAGLAVERAS N,et al. Hybrid image segmentation using watersheds and fast region merging[J]. IEEE Transactions on Image Processing,1998,7(12):1684-1699.
[5] YANG Y,HAN S D,WANG T J,et al. Multilayer graph cuts based unsupervised color-texture image segmentation using multivariate mixed student' s t-distribution and regional credibility merging[J]. Pattern Recognition,2013,46(4):1101-1124.
[6] PANAGIOTAKIS C,GRINIAS I,TZIRITAS G. Natural image segmentation based on tree equipartition,Bayesian flooding and region merging[J]. IEEE Transactions on Image Processing,2011, 20(8):2276-2287.
[7] FU K R,GONG C,GU I Y H,et al. Normalized cut-based saliency detection by adaptive multi-level region merging[J]. IEEE Transactions on Image Processing,2015,24(12):5671-5683.
[8] 孙丰, 秦开怀, 孙伟, 等. 基于区域合并的图像显著性检测[J]. 计算机辅助设计与图形学学报,2016,28(10):1679-1687. (SUN F,QIN K H,SUN W,et al. Image saliency detection based on region merging[J]. Journal of Computer-Aided Design and Computer Graphics,2016,28(10):1679-1687.)
[9] GARCIA UGARRIZA L,SABER E,VANTARAM S R,et al. Automatic image segmentation by dynamic region growth and multiresolution merging[J]. IEEE Transactions on Image Processing,2009,18(10):2275-2288.
[10] CALDERERO F,MARQUÉS F. Region merging techniques using information theory statistical measures[J]. IEEE Transactions on Image Processing,2010,19(6):1567-1586.
[11] ZHA L,LIU Z,LUO S H,et al. A novel region merging based image segmentation approach for automatic object extraction[C]//Proceedings of the 2013 IEEE International Symposium on Circuits and Systems. Piscataway:IEEE,2013:970-973.
[12] PENG B,ZHANG L,ZHANG D,et al. Image segmentation by iterated region merging with localized graph cuts[J]. Pattern Recognition,2011,44(10/11):2527-2538.
[13] 叶齐祥, 高文, 王伟强, 等. 一种融合颜色和空间信息的彩色图像分割算法[J]. 软件学报,2004,15(4):522-530.(YE Q X, GAO W, WANG W Q, et al. A color image segmentation algorithm by using color and spatial information[J]. Journal of Software,2004,15(4):522-530.)
[14] 刘磊, 石志国, 宿浩茹, 等. 基于高阶马尔可夫随机场的图像分割[J]. 计算机研究与发展,2013,50(9):1933-1942.(LIU L, SHI Z G,SU H R,et al. Image segmentation based on higher order Markov random field[J]. Journal of Computer Research and Development,2013,50(9):1933-1942.)
[15] YANG X,GAO X B,TAO D C,et al. An efficient MRF embedded level set method for image segmentation[J]. IEEE Transactions on Image Processing,2015,24(1):9-21.
[16] LIU Q B,DONG G Z. CPCQ:contrast pattern based clustering quality index for categorical data[J]. Pattern Recognition,2012, 45(4):1739-1748.
[17] 张志龙, 李爱华, 李楚为. 基于密度峰值搜索聚类的超像素分割算法[J]. 计算机学报,2020,43(1):1-15.(ZHANG Z L,LI A H,LI C W. Superpixel segmentation based on clustering by finding density peaks[J]. Chinese Journal of Computers,2020,43(1):1-15.)
[18] TAHA A A,HANBURY A. Metrics for evaluating 3D medical image segmentation:analysis, selection, and tool[J]. BMC Medical Imaging,2015,15:No. 29.
[19] BROSTOW G J, SHOTTON J, FAUQUEUR J, et al. Segmentation and recognition using structure from motion point clouds[C]//Proceedings of the 2008 European Conference on Computer Vision,LNCS 5302. Berlin:Springer,2008:44-57.
[20] EVERINGHAM M,VAN GOOL L,WILLIAMS C K I,et al. The PASCAL Visual Object Classes (VOC) challenge[J]. International Journal of Computer Vision,2010,88(2):303-338.
[21] KHAN Z,YANG J. Bottom-up unsupervised image segmentation using FC-Dense u-net based deep representation clustering and multidimensional feature fusion based region merging[J]. Image and Vision Computing,2020,94:No. 103871.
[22] 胡学刚, 段瑶, 严思奇. 基于区域合并的FCM图像分割改进算法[J]. 小型微型计算机系统,2018,39(9):2077-2080.(HU X G,DUAN Y,YAN S Q. Improved FCM image segmentation algorithm based on region merging[J]. Journal of Chinese Computer Systems,2018,39(9):2077-2080.)
[23] ZHANG Y H,WANG X,TAN H S,et al. Region merging method for remote sensing spectral image aided by inter-segment and boundary homogeneities[J]. Remote Sensing, 2019, 11(12):No. 1414.
[24] ZUBAIR K,YANG J. Image segmentation via multi dimensional color transform and consensus based region merging[J]. Multimedia Tools and Applications, 2019, 78(22):31347-31364.

自然场景下多区域特征融合的混合航拍图像分割算法

Hybrid aerial image segmentation algorithm based on multi-region feature fusion for natural scene

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

[1]	邓旭, 徐新, 董浩. 单极化合成孔径雷达图像颜色特征编码与分类[J]. 计算机应用, 2018, 38(7): 2056-2063.
[2]	韩建栋, 朱婷婷, 李月香. 结合粗糙集与分层思想的彩色图像分割算法[J]. 计算机应用, 2015, 35(7): 2020-2024.
[3]	彭浩蔡美玲陈继锋刘炽余炳锐. 面向导航型网页关键词自动抽取的视觉模型与算法[J]. 计算机应用, 2012, 32(08): 2360-2368.
[4]	许蓓蕾庄奕琪汤华莲张丽田进寿. 基于对象的多级图像增强法[J]. 计算机应用, 2011, 31(06): 1556-1559.
[5]	冷美萍鲍苏苏. 基于色调直方图和区域合并的彩色图像分割算法[J]. 计算机应用, 2010, 30(3): 653-656.
[6]	李光王朝英侯志强. 基于K均值聚类与区域合并的彩色图像分割算法[J]. 计算机应用, 2010, 30(2): 354-358.
[7]	沈清波吴炜杨晓敏何小海. 分水岭变换在岩屑图像分割中的应用[J]. 计算机应用, 2009, 29(10): 2859-2861.
[8]	陈家新吴颖黎蔚. 基于各向异性扩散的医学图像分水岭分割算法[J]. 计算机应用, 2008, 28(6): 1527-1529.
[9]	张平; 王文伟; 吴丽芸. 基于均匀性图分水岭变换及两步区域合并的彩色图像分割[J]. 计算机应用, 2006, 26(6): 1378-1380.
[10]	屈伸，王庆，池哲儒. 基于迭代神经网络的图像结构表示和分类[J]. 计算机应用, 2005, 25(04): 766-768.
[11]	殷海明，张明敏，潘志庚. 一种织物彩色图像的分割算法[J]. 计算机应用, 2005, 25(04): 966-967.