Please wait a minute...
 
自然资源遥感  2021, Vol. 33 Issue (3): 36-44    DOI: 10.6046/zrzyyg.2020303
  技术方法 本期目录 | 过刊浏览 | 高级检索 |
基于多尺度LBP特征融合的遥感图像分类
姜亚楠1(), 张欣2, 张春雷3, 仲诚诚1, 赵俊芳1
1.中国地质大学(北京)数理学院,北京 100083
2.北京师范大学统计学院,北京 100875
3.北京中地润德石油科技有限公司,北京 100083
Classification of remote sensing images based on multi-scale feature fusion using local binary patterns
JIANG Yanan1(), ZHANG Xin2, ZHANG Chunlei3, ZHONG Chengcheng1, ZHAO Junfang1
1. School of Science, China University of Geosciences(Beijing), Beijing 100083, China
2. School of Statistics, Beijing Normal University, Beijing 100875, China
3. Beijing Zhongdirunde Petroleum Technology Co.Ltd., Beijing 100083, China
全文: PDF(4495 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

针对高光谱遥感图像分类问题,传统的特征提取方法常忽略其本征属性信息和图像的多尺度局部结构特性而使其获取的图像信息量较少,为改进这一缺陷,提出了一种多尺度灰度和纹理结构特征融合的方法模型(multi-scale gray and texture structure feature fusion,Ms_GTSFF)进行遥感图像特征提取。首先用多尺度方法提取图像不同尺度下的灰度属性特征,然后利用局部二进制模式的思想获得图像的局部纹理特征信息,同时利用多尺度还能够获取图像更大感受野的特征,接着利用得到的多尺度LBP直方图获取每种编码所对应的灰度属性信息,最后将上述得到的多尺度特征信息进行编码融合,构成了Ms_GTSFF特征提取模型,再连接多种机器学习分类器进行分类识别。以雄安新区(马蹄湾村)航空高光谱遥感影像作为测试数据集,对数据分块预处理后再进行特征提取与分类测试,最高获得了99.44%的分类准确率,在遥感图像分类上与传统方法的识别能力相比有很大的提升,验证了提出模型对于增强遥感图像的特征提取能力以及提高分类识别性能的有效性。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
姜亚楠
张欣
张春雷
仲诚诚
赵俊芳
关键词 高光谱遥感多尺度特征灰度属性特征局部二进制模式特征融合    
Abstract

For the classification of remote sensing images, traditional feature extraction methods frequently ignore their intrinsic properties and the multi-scale local characteristics of the images. As a result, only a small amount of image information can be acquired. Given this, this study proposed a model of multi-scale gray level and texture feature fusion (Ms_GTSFF ) for the feature extraction of remote sensing images, and the extraction steps are as follows. Firstly, extract the gray-level features of the images at different scales. Then obtain the local texture features of the images using the local binary pattern (LBP) algorithm and meanwhile, obtain the image features of a larger receptive field using a multi-scale method. Afterward, obtain the gray-level attributes corresponding to various codes using the obtained multi-scale LBP histograms. Finally, code and fuse multi-scale feature information obtained from the above steps to constitute the Ms_GTSFF feature extraction model, to which multiple machine learning classifiers are connected for classification and recognition. Taking the aerial hyperspectral remote sensing images of Xiongan New Area (Matiwan Village) as the test dataset, the feature extraction and classification tests were performed following the data preprocessing by blocks. The classification accuracy was up to 99.44%, indicating a great improvement in the recognition capability compared with traditional methods. This verified the effectiveness of the proposed model in enhancing the feature extraction capability and improving the classification and reorganization performance of remote sensing images.

Key wordsHyperspectral remote sensing    multi-scale characteristic    gray-level attribute feature    local binary pattern    feature fusion
收稿日期: 2020-09-23      出版日期: 2021-09-24
ZTFLH:  TP79  
基金资助:国家自然科学基金青年基金项目“变分法在多时滞微分方程及微分系统中的应用研究”(11601493)
作者简介: 姜亚楠(1993-),女,硕士,主要从事统计学、机器学习在遥感图像分类的研究。Email: 2463613347@qq.com
引用本文:   
姜亚楠, 张欣, 张春雷, 仲诚诚, 赵俊芳. 基于多尺度LBP特征融合的遥感图像分类[J]. 自然资源遥感, 2021, 33(3): 36-44.
JIANG Yanan, ZHANG Xin, ZHANG Chunlei, ZHONG Chengcheng, ZHAO Junfang. Classification of remote sensing images based on multi-scale feature fusion using local binary patterns. Remote Sensing for Natural Resources, 2021, 33(3): 36-44.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/zrzyyg.2020303      或      https://www.gtzyyg.com/CN/Y2021/V33/I3/36
Fig.1  局部二进制模式特征提取原理图
Fig.2  多尺度局部二进制模式特征提取原理图
Ri-LBP8,1
二进制编码
Ri-LBP8,1
编码值
LBP8,1
编码值
00000000 0 0
00000001 1 1,2,4,8,16,32,64,128
…… …… ……
11011111 34 127,191,223,239,247,251,253,254
11111111 35 255
Tab.1  旋转不变LBP编码与原始LBP编码对应表
Fig.3  Ms_GTSFF方法模型
Fig.4  数据集示意图
Fig.5  梨树类区域经LB P 8,1 ri 36特征提取直方图
Fig.6  选取PCA01下20类地物的灰度图及LB P 8,1 ri 36分布直方图
Fig.7  图像在不同尺度下的灰度特征图和MsLB P 8,1 ri 36分布直方图
分类器 Original PCA20 LBP Ms_GTSFF
Bayes 29.16 56.81
KNN 50.88 72.53
DT 43.75 61.17
BP 75.83 81.81 93.28 99.44
SVM 48.75 77.55
RF 56.52 77.54 93.54 98.94
XGB 61.27 79.52 91.70 99.20
LightGBM 61.32 79.30 92.44 99.17
LeNet5 94.72
GoogLeNet 95.59
Tab.2  不同分类器精度对比
Fig.8  遥感图像各类场景分类结果图对比
[1] 滕文秀, 王妮, 陈泰生, 等. 基于深度对抗域适应的高分辨率遥感影像跨域分类[J]. 激光与光电子学进展, 2019, 56(11):236-246.
Teng W X, Wang N, Chen T S, et al. Deep adversarial domain adaptation method for cross-domain classification in high-resolution remote sensing images[J]. Laser & Optoelectronics Progress, 2019, 56(11):236-246.
[2] 董蕴雅, 张倩. 基于CNN的高分遥感影像深度语义特征提取研究综述[J]. 遥感技术与应用, 2019, 34(1):1-11.
Dong Y Y, Zhang Q. A survey of depth semantic feature extraction of high-resolution remote sensing images based on CNN[J]. Remote Sensing Technology and Application, 2019, 34(1):1-11.
[3] Yang Y, Newsam S. Comparing SIFT descriptors and Gabor texture features for classification of remote sensed imagery[C]. 2008 15th IEEE International Conference on Image Processing,San Diego,CA, 2008:1852-1855.doi: 10.1109/ICIP.2008.4712139.
doi: 10.1109/ICIP.2008.4712139
[4] Dos Santos J A, Penatti,O A B, Torres R D S. Evaluating the potential of texture and color descriptors for remote sensing image retrieval and classification[C]. VISAPP 2010-Proceedings of the International Conference on Computer Vision Theory and Applications, 2010(2):203-208.
[5] Chen C, Zhang B, Su H, et al. Land-use scene classification using multi-scale completed local binary patterns[J]. Signal,Image& Video Processing, 2016, 10(4):745-752.
[6] Luo B, Jiang S J, Zhang L P. Indexing of remote sensing images with different resolutions by multiple features[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013, 6(4):1899-1912.
doi: 10.1109/JSTARS.4609443
[7] Lecun Y, Bottou L. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
doi: 10.1109/5.726791
[8] Zhong Y F, Fei F, Zhang L P. Large patch convolutional neural networks for the scene classification of high spatial resolution imagery[J]. Journal of Applied Remote Sensing, 2016, 10(2):025006.
doi: 10.1117/1.JRS.10.025006
[9] Hu F, Xia G S, Hu J w, et al. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery[J]. Remote Sensing, 2015, 7(11):14680-14707.
doi: 10.3390/rs71114680
[10] 许夙晖, 慕晓冬, 赵鹏, 等. 利用多尺度特征与深度网络对遥感影像进行场景分类[J]. 测绘学报, 2016, 45(7):834-840.
Xu S H, Mu X D, Zhao P, et al. Scene classification of remote sensing image based on multi-scale feature and deep neural network[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(7):834-840.
[11] Li E, Xia J, Du P, et al. Integrating multilayer features of convolutional neural networks for remote sensing scene classification[J]. IEEE Transactions on Geosience & Remote Sensing, 2017(10):1-13.
[12] Wang G L, Fan B, Xiang S M, et al. Aggregating rich hierarchical features for scene classification in remote sensing imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(9):4104-4115.
doi: 10.1109/JSTARS.4609443
[13] Ojala T, Pietikäinen M, Mäenpää T. Multi-resolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 24(7):971-987.doi: 10.1109/TPAMI.2002.1017623
doi: 10.1109/TPAMI.2002.1017623
[14] Lee S W, Li S Z. Face detection based on multi-block LBP representation[C]// Advances in Biometrics,International Conference,Icb,Seoul,Korea,August.DBLP, 2007:11-18.
[15] 王家臣, 李良晖, 杨胜利. 不同照度下煤矸图像灰度及纹理特征提取的实验研究[J]. 煤炭学报, 2018, 43(11):3051-3061.
Wang J C, Li L H, Yang S L. Experimental study on gray and texture features extraction of coal and gangue image under different illuminance[J]. Journal of China Coal Society, 2018, 43(11):3051-3061.
[16] 岑奕, 张立福, 张霞, 等. 雄安新区马蹄湾村航空高光谱遥感影像分类数据集[J]. 遥感学报, 2020, 24(11):1299-1306.
Cen Y, Zhang L F, Zhang X, et al. Aerial hyperspectral remote sensing classification dataset of Xiongan New Area (Matiwan Village)[J]. Journal of Remote Sensing (Chinese), 2020, 24(11):1299-1306.
[1] 牛祥华, 黄微, 黄睿, 蒋斯立. 基于注意力特征融合的高保真遥感图像薄云去除[J]. 自然资源遥感, 2023, 35(3): 116-123.
[2] 郑宗生, 刘海霞, 王振华, 卢鹏, 沈绪坤, 唐鹏飞. 改进3D-CNN的高光谱图像地物分类方法[J]. 自然资源遥感, 2023, 35(2): 105-111.
[3] 孔卓, 杨海涛, 郑逢杰, 李扬, 齐济, 朱沁雨, 杨忠霖. 高光谱遥感图像大气校正研究进展[J]. 自然资源遥感, 2022, 34(4): 1-10.
[4] 王茜, 任广利. 高光谱遥感异常信息在阿尔金索拉克地区铜金矿找矿工作中的应用[J]. 自然资源遥感, 2022, 34(1): 277-285.
[5] 高文龙, 张圣微, 林汐, 雒萌, 任照怡. 煤矿开采中SOM的遥感估算和时空动态分析[J]. 自然资源遥感, 2021, 33(4): 235-242.
[6] 臧传凯, 沈芳, 杨正东. 基于无人机高光谱遥感的河湖水环境探测[J]. 自然资源遥感, 2021, 33(3): 45-53.
[7] 刘万军, 高健康, 曲海成, 姜文涛. 多尺度特征增强的遥感图像舰船目标检测[J]. 自然资源遥感, 2021, 33(3): 97-106.
[8] 韩彦岭, 崔鹏霞, 杨树瑚, 刘业锟, 王静, 张云. 基于残差网络特征融合的高光谱图像分类[J]. 国土资源遥感, 2021, 33(2): 11-19.
[9] 胡新宇, 许章华, 陈文慧, 陈秋霞, 王琳, 刘辉, 刘智才. 基于PROBA/CHRIS影像的归一化阴影植被指数NSVI构建与应用效果[J]. 国土资源遥感, 2021, 33(2): 55-65.
[10] 卢麒, 秦军, 姚雪东, 吴艳兰, 朱皓辰. 基于多层次感知网络的GF-2遥感影像建筑物提取[J]. 国土资源遥感, 2021, 33(2): 75-84.
[11] 孙珂. 融合超像元与峰值密度特征的遥感影像分类[J]. 国土资源遥感, 2020, 32(4): 41-45.
[12] 王瑞军, 张春雷, 孙永彬, 王诜, 董双发, 王永军, 闫柏琨. 高光谱在甘肃红山多金属找矿模型构建中的应用[J]. 国土资源遥感, 2020, 32(3): 222-231.
[13] 张东辉, 赵英俊, 秦凯. 典型目标地面光谱信息系统设计与实现[J]. 国土资源遥感, 2018, 30(4): 206-211.
[14] 任广利, 杨敏, 李健强, 高婷, 梁楠, 易欢, 杨军录. 高光谱蚀变信息在金矿找矿预测中的应用研究——以北山方山口金矿线索为例[J]. 国土资源遥感, 2017, 29(3): 182-190.
[15] 张川, 叶发旺, 徐清俊, 刘洪成, 孟树. 新疆白杨河铀铍矿区航空高光谱矿物填图及蚀变特征分析[J]. 国土资源遥感, 2017, 29(2): 160-166.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发