结合面向对象和深度特征的高分影像树种分类

doi:10.13474/j.cnki.11-2246.2019.0109

测绘通报 ›› 2019, Vol. 0 ›› Issue (4): 38-42.doi: 10.13474/j.cnki.11-2246.2019.0109

结合面向对象和深度特征的高分影像树种分类

滕文秀¹, 王妮^2,3, 施慧慧², 许振宇¹

1. 南京林业大学林学院, 江苏南京 210037;
2. 滁州学院地理信息与旅游学院, 安徽滁州 239000;
3. 安徽省地理信息智能感知与服务工程实验室, 安徽滁州 239000

收稿日期:2018-10-12 出版日期:2019-04-25 发布日期:2019-05-07
通讯作者: 王妮。E-mail:wnstrive@163.com E-mail:wnstrive@163.com
作者简介:滕文秀(1994-),男,硕士生,主要从事遥感与地理信息系统研究。E-mail:wenxiu_teng@163.com
基金资助:
国家自然科学基金项目（41601455）；安徽高校省级自然科学研究重点项目（KJ2016A531）

Tree species classification of high resolution image combining with object-oriented and deep feature

TENG Wenxiu¹, WANG Ni^2,3, SHI Huihui², XU Zhenyu¹

1. College of Forest, Nanjing Forestry University, Nanjing 210037, China;
2. School of Geographic Information and Tourism, Chuzhou University, Chuzhou 239000, China;
3. Anhui Engineering Laboratory of Geographical Information Intelligent Sensor and Service, Chuzhou 239000, China

Received:2018-10-12 Online:2019-04-25 Published:2019-05-07

摘要/Abstract

摘要：

针对传统手工提取特征方法需要专业领域知识，提取高质量特征困难的问题，将深度迁移学习技术引入到高分影像树种分类中，提出一种结合面向对象和深度特征的高分影像树种分类方法。为了获取树种的精确边界，该方法首先利用多尺度分割技术分割整幅遥感影像，并选择训练样本作为深度卷积神经网络的输入。为了避免样本数量少导致过拟合问题，采用迁移学习方法，使用ImageNet上训练的VGG16模型参数初始化深度卷积神经网络，并利用全局平局池化压缩参数，在网络最后添加1024个节点的全连接层和7个节点的Softmax分类器，利用反向传播和Adam优化算法训练网络。最后分类整幅遥感影像，生成树种专题地图。以安徽省滁州市的皇甫山国家森林公园为研究区，QuickBird高分影像作为数据源，采用本文方法进行树种分类。试验结果表明，本文方法树种分类总体精度和Kappa系数分别为78.98%和0.685 0，在保证树种精度的同时实现了端到端的树种分类。

关键词: 高分影像, 树种分类, 卷积神经网络, 迁移学习, 多尺度分割

Abstract:

A tree species classification of high resolution image combining with object-oriented and deep feature is proposed to overcome the problem that traditional manual extraction features need professional knowledge and difficult to extract high quality features.In order to obtain the precise boundary of tree species, the method firstly uses multiscale segmentation technology to segment the whole remote sensing image, and selects the training samples as the input of the deep convolution neural network.In order to avoid over-fitting caused by a small number of samples, transfer learning method is used to initialize the deep convolution neural network with the parameters of VGG16 model trained on ImageNet. Using global average pooling compression parameters, a 1024 nodes fully connected layer and 7 nodes Softmax classifier are added at the end of the network. The network is trained by back propagation and Adam optimization algorithm.Finally, the whole remote sensing image is classified and the tree thematic map is generated. The test site is located in the Huangfu Mountain National Forest Park in Anhui province.QuickBird high resolution image is the data source.The results show that the overall accuracy and Kappa coefficient of this method are 78.98% and 0.6850 respectively, which can ensure the accuracy of tree species and achieve end-to-end tree species classification.

Key words: high resolution image, tree species classification, convolutional neural network, transfer learning, multiscale segmentation

中图分类号:

P237

滕文秀, 王妮, 施慧慧, 许振宇. 结合面向对象和深度特征的高分影像树种分类[J]. 测绘通报, 2019, 0(4): 38-42.

TENG Wenxiu, WANG Ni, SHI Huihui, XU Zhenyu. Tree species classification of high resolution image combining with object-oriented and deep feature[J]. 测绘通报, 2019, 0(4): 38-42.

参考文献

[1] ZHANG Z, KAZAKOVA A, MOSKAL L, et al. Object-based tree species classification in urban ecosystems using LiDAR and hyperspectral data[J].Forests, 2016, 7(6):122.
[2] WASER L T, GINZLER C, KUECHLER M, et al. Semi-automatic classification of tree species in different forest ecosystems by spectral and geometric variables derived from airborne digital sensor (ADS40) and RC30 data[J].Remote Sensing of Environment, 2011, 115(1):76-85.
[3] 任冲, 鞠洪波, 张怀清,等. 多源数据林地类型的精细分类方法[J]. 林业科学, 2016, 52(6):54-65.
[4] LOUARN M L, CLERGEAU P, BRICHE E, et al. "Kill two birds with one stone":urban tree species classification using bi-temporal Pléiades images to study nesting preferences of an invasive bird[J]. Remote Sensing, 2017, 9(9):916.
[5] 王妮, 彭世揆, 李明诗. 基于树种分类的高分辨率遥感数据纹理特征分析[J]. 浙江农林大学学报, 2012, 29(2):210-217.
[6] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521:436-444.
[7] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[8] 龚健雅, 季顺平. 摄影测量与深度学习[J]. 测绘学报, 2018,47(6):693-704.
[9] ZHANG F, DU B, ZHANG L. Scene classification via a gradient boosting random convolutional network framework[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(3):1793-1802.
[10] HUAN Y U, ZHANG S Q, KONG B, et al. Optimal segmentation scale selection for object-oriented remote sensing image classification[J]. Journal of Image and Graphics, 2010, 15(2):352-360.
[11] 孙坤, 鲁铁定. 顾及多尺度分割参数的FNEA面向对象分类[J]. 测绘通报, 2018(3):43-48.
[12] DENG J, DONG W, SOCHER R, et al. ImageNet:a large-scale hierarchical image database[C]//IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE, 2009:248-255.
[13] LIN M, CHEN Q, YAN S.Network in network[C]//International Conference on Learning Representations (ICLR).[S.l.]:Cornell University, 2014.
[14] KINGMA D, BA J.ADAM:a method for stochastic optimization[C]//International Conference on Learning Representations (ICLR).[S.l.]:Cornell University, 2015.
[15] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//arXiv preprint arXiv.[S.l.]:University of Oxford, 2014.

结合面向对象和深度特征的高分影像树种分类

Tree species classification of high resolution image combining with object-oriented and deep feature

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[2]	蔡柔丹. 一种基于用户异步轨迹的身份识别智能方法[J]. 测绘通报, 2022, 0(7): 158-162,167.
[3]	滕文鑫, 张建辰, 邵杰. 集成时空邻近与卷积网络车道级高精度定位算法[J]. 测绘通报, 2022, 0(6): 1-5,61.
[4]	文奴, 郭仁忠, 贺彪, 万远. YOLO v4框架下Multi-Patch多帧增量式交通视频目标检测[J]. 测绘通报, 2022, 0(5): 38-44.
[5]	段晨阳, 冯建中, 全斌, 白林燕, 王盼盼. 利用深度学习进行GF-6影像枣园检测识别[J]. 测绘通报, 2022, 0(3): 54-59.
[6]	王胜利, 朱寿红, 蒋毅. 基于CNN模型迁移的OLI影像光伏电池板场景识别[J]. 测绘通报, 2022, 0(2): 5-9.
[7]	贾煜, 汪泓, 蔡宏, 张磊. 结合地形因子与分层策略的喀斯特地区无人机影像分类[J]. 测绘通报, 2022, 0(2): 121-127.
[8]	耿万轩, 周维勋, 金双根. 基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类[J]. 测绘通报, 2021, 0(8): 14-21.
[9]	赵恒谦, 杨屹峰, 刘泽龙, 宋瑞. 农作物叶片病害迁移学习分步识别方法[J]. 测绘通报, 2021, 0(7): 34-38.
[10]	聂倩, 七珂珂, 赵艳福. 融入超像素分割的高分辨率影像面向对象分类[J]. 测绘通报, 2021, 0(6): 44-49.
[11]	贾文翰, 刘越岩. 基于卷积神经网络的高分遥感影像内陆盐沼湿地信息提取[J]. 测绘通报, 2021, 0(6): 89-92.
[12]	段雅鸣, 张锦水, 朱爽. 基于深度卷积神经网络的云检测方法[J]. 测绘通报, 2021, 0(4): 33-39.
[13]	刘明轩, 张黎明, 王昊, 马文骏, 李玉. 运用ULBP的高分辨率遥感影像感知哈希完整性认证算法[J]. 测绘通报, 2021, 0(12): 22-27.
[14]	马林飞, 倪欢, 周子涵. 基于注意力机制的高分遥感图像采石场识别[J]. 测绘通报, 2021, 0(11): 96-100.
[15]	彭述刚, 王大成, 谭军辉, 敖旋峰, 俞佳颖. 基于改进卷积神经网络的城市地下排水管道视频智能识别[J]. 测绘通报, 2021, 0(10): 132-135,167.