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: 1224次
Tree Species Identification Based on FCN Using the Visible Images Obtained from an Unmanned Aerial Vehicle
图 & 表
图 4. 研究区植被影像与面向对象分割结果
Fig. 4. Vegetation image and object-oriented segmentation results in the study area
图 5. 标签制作。(a)标签图;(b)样本和对应标签的旋转图
Fig. 5. Label making. (a) Label map; (b) rotation of the sample and corresponding label
图 8. 训练过程中的损失率与精度变化。(a)损失率;(b)精度
Fig. 8. Loss and accuracy change during training. (a) Loss; (b) accuracy
图 9. 不同方法的分类结果。 (a)真实地物图;(b)原始RGB数据与VDVI、ExG-ExR数据融合的FCN法;(c)基于原始RGB数据FCN法; (d)基于33个特征变量RF法
Fig. 9. Classification results by different methods. (a) Groundtruth map; (b) FCN method with fused data including original RGB data, VDVI data and ExG-ExR data; (c) FCN method with original RGB data; (d) RF method with 33 feature variables
表 1对无人机影像进行分类的精度评价
Table1. Accuracy evaluation of classification of UAV images
|
表 2面向对象分割对FCN分类结果修正精度评价
Table2. Correction of FCN classification results by object-oriented segmentation
|
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.