柴华彬, 严超, 邹友峰, 陈正超. 利用PSP Net实现湖北省遥感影像土地覆盖分类[J]. 武汉大学学报 ( 信息科学版), 2021, 46(8): 1224-1232. doi: 10.13203/j.whugis20190296
引用本文: 柴华彬, 严超, 邹友峰, 陈正超. 利用PSP Net实现湖北省遥感影像土地覆盖分类[J]. 武汉大学学报 ( 信息科学版), 2021, 46(8): 1224-1232. doi: 10.13203/j.whugis20190296
CHAI Huabin, YAN Chao, ZOU Youfeng, CHEN Zhengchao. Land Cover Classification of Remote Sensing Image of Hubei Province by Using PSP Net[J]. Geomatics and Information Science of Wuhan University, 2021, 46(8): 1224-1232. doi: 10.13203/j.whugis20190296
Citation: CHAI Huabin, YAN Chao, ZOU Youfeng, CHEN Zhengchao. Land Cover Classification of Remote Sensing Image of Hubei Province by Using PSP Net[J]. Geomatics and Information Science of Wuhan University, 2021, 46(8): 1224-1232. doi: 10.13203/j.whugis20190296

利用PSP Net实现湖北省遥感影像土地覆盖分类

Land Cover Classification of Remote Sensing Image of Hubei Province by Using PSP Net

  • 摘要: 提出了一种基于金字塔场景解析网络(pyramid scene parsing net,PSP Net)的深度学习算法。以湖北省遥感影像为实验数据,借助PSP Net的上下文场景解析能力,研究湖北省30 m分辨率的土地覆盖。实验使用了湖北省Landsat卫星影像中507景900×600像素的标准分幅影像,通过预处理生成了适用于深度学习的样本集。选择其中300景为样本,包括训练集240个、预测集44个和验证集16个。使用快速特征嵌入卷积结构(convolutional architecture for fast feature embedding,CAFFE)下的PSP Net模型对样本数据进行训练,设置了10×10-10的学习率,选择了第100万次的训练模型, 很好地防止了数据的过拟合。通过模型的泛化和样本的泛化与迭代,对湖北省2000年、2005年、2010年3期的Landsat卫星影像土地覆盖进行分类,分类精度分别达到82.2%、83.4%和83.7%。研究结果表明,基于PSP Net的深度学习算法可以快速、有效和精确地实现大范围的遥感影像土地覆盖分类。

     

    Abstract:
      Objectives  Pyramid scene parsing net (PSP Net), a kind of neural network with deep structure, extracts the features of remote sensing image better than the traditional model, e.g. artificial neural network, and supports vector machine. This algorithm can embed the contextual features of difficult scenes into the pixel prediction framework of the full convolutional neural network (FCN), fully understand the scene, realize accurate prediction of each pixel category, location and shape, and fuse local and global information together to propose an optimization strategy for moderate supervised loss. A deep learning algorithm based on PSP Net is proposed to achieve higher accuracy in image classification and effectively promote remote sensing image automation and intelligent interpretation.
      Methods  Conventional architecture for fast feature embedding (CAFFE) is a deep learning framework with is expressive, fast and thought modular, and supports a variety of deep learning architectures for image classification and segmentation. PSP Net model under the CAFFE framework is used by modifying and optimizing the network to eliminate the overfitting effect. Using the remote sensing image of Hubei Province as the experimental data, the land with the 30 m resolution is studied with the aid of the analysis ability of the context scene of PSP Net. The Python program is used in the CAFFE depth learning framework for operation. The operation network obtains the global feature information through the core structure (pyramid pooling module) and completes the generation of the data set. In the experiment, the 507 standard partial images of 900×600 pixels in the landsat image of Hubei Province are used, and the sample sets suitable for depth learning are generated by pre-processing. Among these, 300 data are selected, including 240 training sets, 44 prediction sets, and 16 validation sets. The overall accuracy (OA) index is used as the prediction accuracy index of the preliminary evaluation model to evaluate the accuracy of the prediction model.
      Results  PSP Net model under the deep learning framework of CAFFE is used to train the sample data. The learning rate of 10×10-10 is set, and the million times training model is selected to protect against overfitting of the data. Through the generalization of the model and the generalization and iteration of the samples, the land cover of the 3 phases of TM images about Hubei Province are classified, and the classification accuracy is 82.2%, 83.4% and 83.7%, respectively.
      Conclusions  The results show that the land cover classification of remote sensing images can be realized quickly, effectively and accurately by PSP Net.

     

/

返回文章
返回