基于改进藤壶优化算法的森林冠层图像分割

Forest Canopy Image Segmentation Based on Improved Barnacle Optimization Algorithm

为解决森林冠层图像因结构复杂,提取时受光照不均的影响而导致分割精度低的问题,采用一种基于自适应调整策略的混沌藤壶交配优化算法(Chaotic Adaptive Barnacle Mating Optimization,CABMO)的森林冠层图像分割方法。首先采用Logistic混沌映射初始化藤壶种群以提高算法的探索能力;然后设计非线性递增阴茎系数使探索和开发之间更平衡;最后将Kapur熵作为适应度函数,利用CABMO算法选取适应度函数的最优值,降低复杂度的同时,加强阈值的搜索效率。为验证CABMO算法在森林冠层图像分割上的有效性,以适应度值、峰值信噪比值(Peak Signal to Noise Ratio,PSNR)、特征相似性指数测试值(feature similarity index mersure,FSIM)和计算时间作为性能指标来评估分割效果。研究结果表明,在适应度值、PSNR值和FSIM值上CABMO算法分别以100%、99%、97.9%的占比优于对比算法,在计算时间上100%优于基本藤壶交配优化算法(Barnacle Mating Optimization,BMO)。结果表明,CABMO算法在提高森林冠层图像分割精度的同时也获得了更高质量的分割图像。

A Chaotic Adaptive Barnacle Mating Optimization(CABMO)method based on an adaptive adjustment strategy for forest canopy image segmentation was used in this paper to solve the problem of low segmentation accuracy due to the complex structure of forest canopy images and the influence of uneven illumination during extraction.Firstly,a Logistic chaotic mapping was used to initialize the barnacle population to improve the exploration ability of the algorithm;then,a nonlinear incremental penis coefficient was designed to make a better balance between exploration and exploitation;finally,Kapur entropy was used as the fitness function,and the optimal value of the fitness function was selected by using the CABMO algorithm to reduce the complexity and enhance the search efficiency of the threshold at the same time.For verifying the effectiveness of the CABMO algorithm on forest canopy image segmentation,the fitness value,Peak Signal to Noise Ratio(PSNR)value,and Feature Similarity Index Measure(FSIM)value were used as performance indicators to evaluate the segmentation effect.The study results showed that the CABMO algorithm outperformed the comparison algorithm with 100%,99%,and 97.9%of the fitness value,PSNR value,and FSIM value,respectively,and outperformsed the basic Barnacle Mating Optimization(BMO)algorithm with 100%of the computation time.The results of this study showed that the CABMO algorithm improved the segmentation accuracy of forest canopy images while obtaining higher-quality segmented images.