Please wait a minute...
img

官方微信

遥感技术与应用  2018, Vol. 33 Issue (3): 408-417    DOI: 10.11873/j.issn.1004-0323.2018.3.0408
城市遥感专栏     
增大特征空间复杂度的方法——以城镇下垫面遥感分类为
任浙豪,周坚华
(华东师范大学地理科学学院,上海 200241)
A Novel Method to Make Feature Space Adequately Complex:A Case Study on the Classification of Underlying Surfacein Urban Area from Remote Sensing Data
Ren Zhehao,Zhou Jianhua
(School of Geographic Sciences,East China Normal University,Shanghai 200241,China)
 全文: PDF(11730 KB)  
摘要:
在城镇复杂场景中对下垫面做遥感分类,通常要求分类特征空间具有相应的复杂度。增加特征空间维数(即增加描述符的数量),并保持各特征维之间的独立性,是满足这种复杂度的主要方法。为此,提出了3种增加特征空间复杂度的方法。它们对现有基础描述符做扩展,并保证扩展者与原描述符彼此独立,这3种方法是:①邻域标准差权值。即对某基础描述符,以若干指定尺度邻域的灰度标准差作为中心像素权重,构成多尺度层;然后将这些尺度层按照一定规则组合,构成描述符扩展。它提取并组合不同尺度层信息,改善了描述符的表征能力;②多尺度纹元组合。以若干尺度的结构元素提取不同尺寸的亮、暗细节,以表征不同尺度的纹元,并以不同尺度的细节密度构成多尺度层;然后将这些尺度层单独使用,形成对基础细节密度描述符的扩展。它表征了不同地物在不同尺度层中的粗糙度;③多态密度维。在由若干基础描述符构成的特征空间里,以邻域元素的多特征相似性为测度,构成密度维,通过改变基础描述符的组合,形成多态密度维,实现对单一密度维的扩展,从而综合了多描述符的信息。精度验证表明:在不增加基础描述符数量的情况下,依靠这3种扩展增加特征空间维数,全局精度平均提高7.86%,同时计算复杂度无明显增大。

 
关键词: 城镇下垫面 邻域 多尺度 多态密度维 遥感    
Abstract: An adequately complex feature space is indispensible as classifying underlying surface in urban area from remote sensing data.Therefore,more independent descriptors are required to increase dimension of the feature space.However,pervasive basic descriptors,as we all know,are usually not enough to construct the feature space.Three novel and pervasive approaches to getting new descriptors by extending these basic descriptors are explored in this paper.They are introduced as follows.1) Take standard deviation of neighbourhood elements in a basic descriptor as weight to indicate neighbourhood\|based multi\|scale information for the center pixel and name the approach as NMIS.The NMIS\|extended value of the center pixel is summed from several layers.These layers are different from each other only in the size of neighbourhood in which the standard deviation is calculated.2) Form multi\|scale texture layers by using a set of size\|given structure elements and name this approach as STIM.Each layer is a STIM\|extended descriptor and serves as an independent descriptor in the feature space.With a set of STIM\|extended descriptors having a basic texture descriptor as their common source,the difference in coarseness between classes can be identified.3) The third extending approach knows as polymorphic density dimension.The density dimension (De) is an algorithm for combining multiple basic features into a single descriptor to indicate geographical distribution of neighborhood elements carrying these features.Compared with previous De,a descriptor of the polymorphic De also combines multiple basic features but allows these features in different types (e.g.being spectrum and texture ones).The extending descriptor is independent from anyone of these combined features and able to be added into the feature space including these features.Accuracy assessment indicated that the average overall accuracy of classification with an extended\|descriptor\|involved input feature vector is 7.86% better than that with only basic\|descriptor\|involved one.
Key words: Urban underlying surface; Neighbourhood\    based; Multi-scale; Polymorphic density dimension; Remote sensing
收稿日期: 2017-08-01 出版日期: 2018-07-04
:  TP75  
基金资助: 国家自然科学基金项目(J1310028)。

作者简介: 任浙豪(1995-),男,浙江永康人,本科生,主要从事遥感与地理信息系统研究。Email:13681956189@126.com。
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  
任浙豪
周坚华

引用本文:

任浙豪,周坚华. 增大特征空间复杂度的方法——以城镇下垫面遥感分类为[J]. 遥感技术与应用, 2018, 33(3): 408-417.

Ren Zhehao,Zhou Jianhua. A Novel Method to Make Feature Space Adequately Complex:A Case Study on the Classification of Underlying Surfacein Urban Area from Remote Sensing Data. Remote Sensing Technology and Application, 2018, 33(3): 408-417.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2018.3.0408        http://www.rsta.ac.cn/CN/Y2018/V33/I3/408

[1] 王卷乐, 程凯, 边玲玲, 韩雪华, 王明明. 面向SDGs和美丽中国评价的地球大数据集成框架与关键技术[J]. 遥感技术与应用, 2018, 33(5): 775-783.
[2] 王恺宁,王修信,黄凤荣,罗涟玲. 喀斯特城市地表温度遥感反演算法比较[J]. 遥感技术与应用, 2018, 33(5): 803-810.
[3] 张晓峰,吕晓琪,张信雪,张继凯,王月明,谷宇,樊宇. 多时刻海色遥感数据融合及其可视化[J]. 遥感技术与应用, 2018, 33(5): 873-880.
[4] 谢旭,陈芸芝. 基于PSO-RBF神经网络模型反演闽江下游水体悬浮物浓度[J]. 遥感技术与应用, 2018, 33(5): 900-907.
[5] 迟文峰,匡文慧,贾静,刘正佳. 京津风沙源治理工程区LUCC及土壤风蚀强度动态遥感监测研究[J]. 遥感技术与应用, 2018, 33(5): 965-974.
[6] 胡云锋,商令杰,张千力,王召海. 基于GEE平台的1990年以来北京市土地变化格局及驱动机制分析[J]. 遥感技术与应用, 2018, 33(4): 573-583.
[7] 李晨伟,张瑞丝,张竹桐,曾敏 . 基于多源遥感数据的构造解译与分析—以西藏察隅吉太曲流域为例[J]. 遥感技术与应用, 2018, 33(4): 657-665.
[8] 李生生,王广军,梁四海,彭红明,董高峰,罗银飞. 基于Landsat-8 OLI数据的青海湖水体边界自动提取[J]. 遥感技术与应用, 2018, 33(4): 666-675.
[9] 廖凯涛,齐述华,王成,王点. 结合GLAS和TM卫星数据的江西省森林高度和生物量制图[J]. 遥感技术与应用, 2018, 33(4): 713-720.
[10] 张震,刘时银,魏俊锋,蒋宗立. 1974~2012年珠穆朗玛峰地区冰川物质平衡遥感监测研究[J]. 遥感技术与应用, 2018, 33(4): 731-740.
[11] 王琳,徐涵秋,李胜. 重钢重工业区迁移对区域生态的影响研究[J]. 遥感技术与应用, 2018, 33(3): 387-397.
[12] 王宁,陈方,于博. 基于形态学开运算的面向对象滑坡提取方法研究[J]. 遥感技术与应用, 2018, 33(3): 520-529.
[13] 王宝刚,晋锐,赵泽斌,亢健. 被动微波遥感在地表冻融监测中的应用研究进展[J]. 遥感技术与应用, 2018, 33(2): 193-201.
[14] 秦振涛,杨茹,张靖,杨武年. 基于聚类结构自适应稀疏表示的高光谱遥感图像修复研究[J]. 遥感技术与应用, 2018, 33(2): 212-215.
[15] 郭宇柏,卓莉,陶海燕,曹晶晶,王芳. 基于空谱初始化的非负矩阵光谱混合像元盲分解[J]. 遥感技术与应用, 2018, 33(2): 216-226.