激光与光电子学进展, 2019, 56 (7): 072801, 网络出版: 2019-07-30
基于深度迁移学习的无人机高分影像树种分类与制图 下载: 1353次
Tree Species Classification and Mapping Based on Deep Transfer Learning with Unmanned Aerial Vehicle High Resolution Images
遥感 树种分类 深度迁移学习 卷积神经网络 超像素分割 remote sensing tree species classification deep transfer learning convolution neural network super-pixel segmentation
摘要
提出一种基于深度迁移学习的无人机高分影像树种分类与制图方法。利用ImageNet上训练的大型卷积神经网络提取树种影像特征,采用全局平均池化压缩树种影像特征,使用简单线性迭代聚类生成超像素,以超像素为最小分类单元,生成树种专题地图。实验结果表明,在类间差距小、类内差距大的情况下,与小型卷积神经网络相比,本文方法收敛更快,总体精度和Kappa系数分别提高了9.04%和0.1547,超像素树种制图边界更加精确。
Abstract
A tree species classification and mapping method is proposed based on the deep transfer learning with unmanned aerial vehicle high resolution images. The image features of tree species are extracted using a large convolution neural network trained on ImageNet. The features of tree species images are compressed by the global average pooling. A simple linear iterative clustering method is used to generate the super-pixel, which are used as the minimum classification unit to generate tree species maps. The experimental results show that the proposed method can accelerate the convergence of the training process. The overall accuracy and Kappa coefficient are increased by 9.04% and 0.1547, respectively, compared with the small convolutional neural network method in the case of small inter-class gap and the large intra-class gap, and the boundary of the super-pixel tree mapping is more accurate.
滕文秀, 温小荣, 王妮, 施慧慧. 基于深度迁移学习的无人机高分影像树种分类与制图[J]. 激光与光电子学进展, 2019, 56(7): 072801. Wenxiu Teng, Xiaorong Wen, Ni Wang, Huihui Shi. Tree Species Classification and Mapping Based on Deep Transfer Learning with Unmanned Aerial Vehicle High Resolution Images[J]. Laser & Optoelectronics Progress, 2019, 56(7): 072801.