Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (5): 1465-1470.DOI: 10.11772/j.issn.1001-9081.2020081221

Special Issue: 多媒体计算与计算机仿真

• Virtual reality and multimedia computing • Previous Articles     Next Articles

Multi-threshold segmentation of forest fire images based on modified symbiotic organisms search algorithm

JIA Heming1,2, LI Yao2, JIANG Zichao2, SUN Kangjian2   

  1. 1. School of Information Engineering, Sanming University, Sanming Fujian 365004, China;
    2. College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin Heilongjiang 150040, China
  • Received:2020-08-12 Revised:2020-10-03 Online:2021-05-10 Published:2020-12-09
  • Supported by:
    This work is partially supported by the Project of Ministry of Education Industry-University Cooperation Collaborative Education (202002064014), the Educational Research Project of Young and Middle-aged Teachers in Fujian Province (JAT200618), the Guiding Science and Technology Project in Sanming City (2020-G-61), the Scientific Research Start Fund for Sanming University Introduced High-Level Talents (20YG14), the Scientific Research and Development Fund of Sanming University (B202009), the Project of Sanming University Higher Education Research (SHE2013), the Open Research Fund of Fujian Provincial Key Laboratory of Agriculture Internet of Things Application (ZD2101).

基于改进共生生物搜索算法的林火图像多阈值分割

贾鹤鸣1,2, 李瑶2, 姜子超2, 孙康健2   

  1. 1. 三明学院 信息工程学院, 福建 三明 365004;
    2. 东北林业大学 机电工程学院, 哈尔滨 150040
  • 通讯作者: 贾鹤鸣
  • 作者简介:贾鹤鸣(1983-),男,辽宁辽阳人,教授,博士,CCF会员,主要研究方向:群体智能优化、特征选择、多阈值图像分割;李瑶(1997-),女,黑龙江伊春人,硕士研究生,主要研究方向:群智能优化、特征选择;姜子超(1995-),男,黑龙江齐齐哈尔人,硕士研究生,主要研究方向:机器学习、群智能优化、特征选择;孙康健(1996-),男,辽宁锦州人,硕士研究生,主要研究方向:群智能优化、特征选择。
  • 基金资助:
    教育部产学合作协同育人项目(202002064014);福建省教育厅中青年教师教育科研项目(JAT200618);三明市科技计划引导性项目(2020-G-61);三明学院引进高层次人才科研启动经费支持项目(20YG14);三明学院科学研究发展基金资助项目(B202009);三明学院高教研究课题(SHE2013);福建省农业物联网应用重点实验室开放研究基金资助项目(ZD2101)。

Abstract: To solve the problems that the traditional multi-threshold segmentation methods have the computational complexity increased with the increase of the number of thresholds, and have very low efficiency of multi-threshold segmentation for a given image, a multi-threshold segmentation method based on Symbiotic Organisms Search (SOS) algorithm combined with Kapur entropy threshold was proposed. Firstly, the Elite Opposition-Based Learning (EOBL) was added into the symbiotic stage of SOS algorithm, so as to solve the problem that the traditional SOS algorithms tend to fall into local optimum when dealing with complex optimization problems. Then, the Levy flight mechanism was introduced to expand the search range of SOS algorithm and enhance the randomness of the algorithm's search trajectory. Finally, the obtained Modified Symbiotic Organisms Search (MSOS) algorithm was applied to find the optimal threshold values for forest fire images. Experimental results show that compared with other optimization algorithms such as Particle Swarm Optimization (PSO) algorithm,Harmony Search Algorithm (HSA) and Bat Algorithm (BA), the MSOS algorithm has the superiority in segmenting images, so it is practical and valuable in practical engineering problems.

Key words: image multi-threshold segmentation, Symbiotic Organisms Search (SOS) algorithm, Elite Opposite Based Learning (EOBL), Levy flight, forest fire recognition

摘要: 针对传统多阈值分割方法计算复杂度随着阈值个数的增加而增长,以及对给定图像进行多阈值分割操作时效率很低等问题,提出了一种基于共生生物搜索(SOS)算法结合Kapur熵的多阈值分割方法。首先将精英反策略(EOBL)引入到SOS算法的共栖阶段,从而改善传统SOS算法处理复杂优化问题时易陷入局部最优的问题;然后引入莱维飞行策略扩大SOS算法的的搜索范围,增强其搜索轨迹的随机性;最终将得到的改进共生生物搜索(MSOS)算法应用到林火图像最佳阈值的选取问题上。实验结果表明,与粒子群优化算法、和声搜索算法、蝙蝠算法等对比算法相比,所提算法能更好地分割图像,在实际工程问题中具有一定的实用性和价值。

关键词: 图像多阈值分割, 共生生物搜索算法, 精英反策略, 莱维飞行, 林火识别

CLC Number: