帅爽, 张志, 张天, 张焜, 肖成志, 陈安. 特征优化结合随机森林算法的干旱区植被高光谱遥感分类方法[J]. 农业工程学报, 2023, 39(9): 287-293. DOI: 10.11975/j.issn.1002-6819.202210205
    引用本文: 帅爽, 张志, 张天, 张焜, 肖成志, 陈安. 特征优化结合随机森林算法的干旱区植被高光谱遥感分类方法[J]. 农业工程学报, 2023, 39(9): 287-293. DOI: 10.11975/j.issn.1002-6819.202210205
    SHUAI Shuang, ZHANG Zhi, ZHANG Tian, ZHANG Kun, XIAO Chengzhi, CHEN An. Hyperspectral image classification method for dryland vegetation by combining feature optimization and random forest algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(9): 287-293. DOI: 10.11975/j.issn.1002-6819.202210205
    Citation: SHUAI Shuang, ZHANG Zhi, ZHANG Tian, ZHANG Kun, XIAO Chengzhi, CHEN An. Hyperspectral image classification method for dryland vegetation by combining feature optimization and random forest algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(9): 287-293. DOI: 10.11975/j.issn.1002-6819.202210205

    特征优化结合随机森林算法的干旱区植被高光谱遥感分类方法

    Hyperspectral image classification method for dryland vegetation by combining feature optimization and random forest algorithm

    • 摘要: 针对高维光谱纹理特征空间的降维和特征优化算法结果的不确定性问题,该研究在提取多尺度纹理图像构建高维光谱纹理特征空间的基础上,将遗传算法(genetic algorithm,GA)、粒子群优化算法(particle swarm optimization,PSO)等传统特征优化算法和广义正态分布优化算法(generalized normal distribution optimization,GNDO)、原子搜索算法(atom search algorithm,ASO)、海洋捕食者算法(marine predators algorithm,MPA)等特征优化算法与随机森林(random forest,RF)图像分类算法相结合,提出了GA-RF、PSO-RF、GNDO-RF、ASO-RF和MPA-RF算法,并应用于青海省海西蒙古族藏族自治州都兰县宗加镇附近区域资源一号02D(ZY1-02D)高光谱数据的植被类型分类。结果显示,在高光谱反射率数据基础上加入多尺度纹理特征使总体分类精度(overall accuracy,OA)提升了8.02个百分点。与传统RF方法相比,提出算法的植被分类 OA提升了1.32~2.40个百分点,其中MPA-RF方法取得了最高的分类精度,OA和 Kappa系数分别为88.92%和0.86。研究表明从不同窗口大小、窗口移动方向提取的纹理图像有利于区分不同的植被与地物类型,在光谱特征基础上加入多尺度纹理特征能有效提升植被识别精度。以迭代优化的方式将特征优化算法与图像分类算法相结合,缓解了优化算法结果的随机性,克服了高维特征的休斯效应,提高了植被分类精度。该研究为高光谱遥感植被分类中特征提取、特征优化与分类算法选择提供了思路。

       

      Abstract: Hyperspectral remote sensing technology has been widely used in vegetation type mapping, and the integrated use of spectral and texture features of remote sensing data has become an effective way to improve the accuracy of vegetation classification, but the Hughes effect generated by the high-dimensional feature space composed of multi-scale texture features and hyperspectral features reduced the image classification accuracy, and the randomness of feature optimization algorithms such as genetic algorithm (GA) can also cause uncertainty in image classification accuracy. In order to solve those problems, a high-dimensional spectral-texture feature space was established by incorporating spectral features of ZY1 02D Advanced HyperSpectral Imager(AHSI) hyperspectral data and multi-scale texture features extracted from ZY1 02D Visible and Near Infrared Camera(VNIC) data at various window sizes and movement directions, covering the vicinity of Zongjia Town in Dulan County, Qinghai Province, China. Jeffries-Matusita(J-M) distance is employed to assess the sample separability between vegetation types of texture features derived from varying window sizes and movement directions. Based on a combination of feature optimization algorithms (GA algorithm, particle swarm optimization (PSO), generalized normal distribution optimization (GNDO), atom search algorithm (ASO) and marine predators algorithm (MPA)) and classification algorithm (random forest (RF)), GA-RF, PSO-RF, GNDO-RF, ASO-RF, and MPA-RF algorithms were proposed and applied to the vegetation type classification of the high-dimensional spectral-texture feature space. The results show that the texture features extracted from different window sizes and window movement directions showed maximum J-M distance between distinct vegetations. For instance, the J-M distance between wolfberry (old) and wolfberry (new) is highest in the 3×3 window size texture images, while the J-M distance between wolfberry (old) and haloxylon is highest in the 11×11 window size texture images. In the 0° window movement direction texture images, poplar and haloxylon had the best separability to other vegetation types with J-M distances greater than 1.87 and 1.86, respectively. Grass and other vegetation types achieved the best separability with J-M distances greater than 1.18 in the 90° window movement direction texture images. The inclusion of multi-scale texture features improved the overall classification accuracy (OA) by 8.02 percentage. The proposed GA-RF, PSO-RF, GNDO-RF, ASO-RF, and MPA-RF algorithms, when compared to the conventional random forest algorithm, led to an improvement in OA of vegetation classification by 1.32 to 2.41 percentage. Among them, the MPA-RF method exhibited the highest accuracy, achieving an OA and Kappa coefficient of 88.92% and 0.86, respectively. The results of this study demonstrate that texture images extracted from different window sizes and window movement directions are useful in distinguishing between different types of vegetation. The accuracy of vegetation recognition is significantly increased by adding multi-scale texture features to the spectral feature set. The combination of feature optimization algorithm and image classification algorithm by iterative optimization alleviates the randomness of the optimization algorithm results, overcomes the Hughes effect of high-dimensional features, and successfully improves the vegetation classification accuracy. This study proposes innovative ideas for feature extraction, feature optimization, and classification algorithm selection for hyperspectral vegetation classification studies.

       

    /

    返回文章
    返回