激光与光电子学进展, 2020, 57 (10): 101001, 网络出版: 2020-05-08   

基于FCN的无人机可见光影像树种分类 下载: 1202次

Tree Species Identification Based on FCN Using the Visible Images Obtained from an Unmanned Aerial Vehicle
戴鹏钦 1,2,3,*丁丽霞 1,2,3,**刘丽娟 1,2,3董落凡 1,2,3黄依婷 3
作者单位
1 省部共建亚热带森林培育国家重点实验室, 浙江 杭州 311300
2 浙江省森林生态系统碳循环与固碳减排重点实验室, 浙江 杭州 311300
3 浙江农林大学环境与资源学院, 浙江 杭州 311300
摘要
将深度学习和面向对象方法用于处理超高空间分辨率的无人机可见光影像,以期实现高精度的森林树种遥感分类。首先,利用面向对象方法对无人机影像进行最优尺度分割,基于对象提取特征变量,运用随机森林(RF)法对树种遥感分类,同时对参与分类的变量按重要性排序,并筛选出对分类贡献率最高的两个特征变量——可见光差异植被指数(VDVI)和过绿减过红指数(ExG-ExR)。然后,将这两个特征变量和无人机原始RGB波段融合生成新的数据,针对该数据与原始RGB波段数据,分别利用基于Res-U-Net模型的全卷积神经网络(FCN)方法进行树种分类,并对结果精度评价。最后,为了消除FCN法基于像元分类引起的缺陷,结合面向对象最优分割法对分类结果进行修正。实验结果表明,融合了VDVI和ExG-ExR的FCN方法对无人机影像的树种分类效果最好,总精度为97.8%,Kappa系数为0.970。RF法能够有效筛选分类特征变量,对原始影像添加特征变量能有效提高FCN方法的分类精度,再对面向对象分割结果进行修正,可以基本消除椒盐现象,减弱边缘效应,使总精度提高0.9个百分点,Kappa系数提高了0.013。
Abstract
In this study, we attempt to use deep learning and object-oriented methods to deal with very-high-resolution visible images obtained from an unmanned aerial vehicle (UAV) for achieving high-precision classification of the forest tree species. First, we use the optimal-scale object-oriented method to segment the images obtained from the UAV. The random forest (RF) method is used to classify the tree species for extracting the feature variables. In addition, the classification variables are sorted based on their importance and significance. Further, the most important feature variables with respect to the classification, including the visible light difference vegetation index (VDVI) and the over-green to over-red reduction index (ExG-ExR), are selected. Subsequently, new data are generated by combining two characteristic variables and the original RGB band of the UAV images. Based on the new data and the original RGB band data are both used to classify tree species by the full convolutional neural network (FCN) method based on the Res-U-Net model. Then, the classification result accuracies in the aforementioned cases are evaluated and compared. Finally, the object-oriented segmentation method is used to correct the optimal tree species classification results. The experimental results denote that FCN with respect to VDVI and ExG-ExR exhibits the best classification effect in case of the original images of the tree species obtained via UAVs. The total accuracy is 97.8%, and the Kappa coefficient is 0.970. RF methoed can effectively screen out the classification feature variables. The addition of characteristic variables to the original image can effectively improve the classification accuracy of the FCN method. Finally, the best classification result is obtained using object-oriented segmentation, resulting in the elimination of the salt and pepper phenomenon and the attenuation of the edge effect. The total accuracy improves by 0.9 percentage points and the Kappa coefficient increases by 0.013.

戴鹏钦, 丁丽霞, 刘丽娟, 董落凡, 黄依婷. 基于FCN的无人机可见光影像树种分类[J]. 激光与光电子学进展, 2020, 57(10): 101001. Pengqin Dai, Lixia Ding, Lijuan Liu, Luofan Dong, Yiting Huang. Tree Species Identification Based on FCN Using the Visible Images Obtained from an Unmanned Aerial Vehicle[J]. Laser & Optoelectronics Progress, 2020, 57(10): 101001.

本文已被 4 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!