[1]陈永明,林萍,何坚强,等.最优分辨率配置下典型湿地生境场景溯源方法[J].江苏农业学报,2015,(06):1318-1324.[doi:doi:10.3969/j.issn.1000-4440.2015.06.019]
　CHEN Yong-ming,LIN Ping,HE Jian-qiang,et al.A derivation approach for typical wetland habitat scenes based on optimum-resolution configuration[J].,2015,(06):1318-1324.[doi:doi:10.3969/j.issn.1000-4440.2015.06.019]
点击复制

最优分辨率配置下典型湿地生境场景溯源方法()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2015年06期
页码:
1318-1324
栏目:
耕作栽培·资源环境
出版日期:
2015-12-31

文章信息/Info

Title:
A derivation approach for typical wetland habitat scenes based on optimum-resolution configuration
作者:
陈永明; 林萍; 何坚强; 姚志垒
（盐城工学院电气工程学院，江苏盐城224051）
Author(s):
CHEN Yong-ming; LIN Ping; HE Jian-qiang; YAO Zhi-lei
(College of Electrical Engineering, Yancheng Institute of Technology, Yancheng 224051, China)
关键词:
湿地; 生态系统; 场景; 溯源; 最优分辨率
Keywords:
wetland; ecosystem; scene; derivation; optimum-resolution
分类号:
X171.1
DOI:
doi:10.3969/j.issn.1000-4440.2015.06.019
文献标志码:
A
摘要:
为利用最优分辨率配置下的空间网罗特征提升中国典型湿地生态系统生境场景溯源算法的性能，提出了正交配置溯源方法，即采用空频域中最优分辨率配置下空间网罗法，消除非正交多尺度滤波器频带交叠造成的冗余特征输出的影响，使用归一化处理方法去除空间网罗特征量纲影响，使用数据中心化处理方法消除空间网罗特征均值漂移的影响，使用主成分分析算法将高维空间网罗特征数据投影到低维特征子空间，使用大间隔最邻近法算法在高维特征空间中对场景主成分特征进行溯源。研究结果显示正交配置溯源方法对湿地生态系统生境场景的建模集和溯源集预测精度分别比现有非正交配置溯源方法提升了1个百分点和2个百分点。
Abstract:
This study aims to enhance the performance of derivation algorithm of the tpyical wetland ecological habitat scene (WEHS) in China by applying the optimum-resolution configuration of spatial envelope (SE) algorithm. The SE algorithm was designed as optimal multi resolution in the spatial-frequency domain in order to eliminate the effects of redundant features generated by the overlapping frequency bands of nonorthogonal multi-scale filters. The normalized algorithm was used to remove the influence of dimensions. Then the nomalized feature variables were centralized in order to eliminate the negative effects of mean drifts. The principal component analysis algorithm was employed to project the preprocessed features to the low-dimension subspace to extract the principal components. The large-margin nearest neighbor algorithm was used to project the principal components of the WEHS into high-dimension feature space and derive the WEHSs in the space. The results showed that the forecast accuracies of modeling and derivation set were boosted by one percentage point and two percentage points compared to the classical algorithm respectively.

参考文献/References:

[1]李玉凤,刘红玉. 湿地分类和湿地景观分类研究进展[J]. 湿地科学， 2014, 12 (1): 102-108.
[2]WARDLE D A, BARDGETT R D, CALLAWAY R M, et al. Terrestrial ecosystem responses to species gains and losses[J]. Science, 2011, 332 (6035): 1273-1277.
[3]BAI J, CUI B, CHEN B, et al. Spatial distribution and ecological risk assessment of heavy metals in surface sediments from a typical plateau lake wetland, China[J]. Ecological Modelling, 2011, 222(2): 301-306.
[4]杨昭,高隽,谢昭,等. 局部Gist特征匹配核的场景分类[J]. 中国图象图形学报, 2013, 18(3): 264-270.
[5]WANG Q, ZHANG X, LI M, et al. Adaboost and multi-orientation 2D Gabor-based noisy iris recognition[J]. Pattern Recognition Letters, 2012, 33(8): 978-983.
[6]LIU C, JIANG H, HOU Y, et al. Habitat changes for breeding waterbirds in Yancheng National Nature Reserve, China: A remote sensing study[J]. Wetlands, 2010, 30(5): 879-888.
[7]XIAO D, TIAN B, TIAN K, et al. Landscape patterns and their changes in Sichuan Ruoergai wetland national nature reserve[J]. Acta Ecologica Sinica, 2010, 30(1): 27-32.
[8]XIN K, HUANG X, HU J, et al. Land use change impacts on heavy metal sedimentation in Mangrove wetlands—A case study in Dongzhai harbor of Hainan, China[J]. Wetlands, 2014, 34(1): 1-8.
[9]ABDI H, WILLIAMS L J. Principal component analysis[J]. Wiley Interdisciplinary Reviews: Computational Statistics, 2010, 2(4): 433-459.
[10]HU Q, ZHU P, YANG Y, et al. Large-margin nearest neighbor classifiers via sample weight learning[J]. Neurocomputing, 2011, 74(4): 656-660.
[11]VAN DE SANDE K E A, GEVERS T, SNOEK C G M. Evaluating color descriptors for object and scene recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1582-1596.
[12]OLIVA A, TORRALBA A. Building the gist of a scene: the role of global image features in recognition[J]. Progress in Brain Research, 2006, 155: 23-36.

备注/Memo

备注/Memo:
收稿日期：2015-04-03 基金项目：国家自然科学基金项目 (51407153)；江苏省自然科学基金项目（BK20140467）；江苏省高校自然科学研究面上项目（13KJB210006）；盐城市农业科技指导性计划项目(YKN2014009、YKN2014010)；盐城工学院人才引进项目（KJC2014007、KJC2014006）；盐城工学院校级培育项目（XKY2013013、XKY2014056、XKY2014055） 作者简介：陈永明（1982-），男，江苏盐城人，博士，讲师，研究方向：生态计算。（Tel）15151009725；（E-mail）billrange@126.com 通讯作者：林萍,（Tel）0515-88168357；（E-mail）binglvcha007@126.com
更新日期/Last Update: 2015-12-31