Object-Based Distinction between Building Shadow and Water in High-Resolution Imagery Using Fuzzy-Rule Classification and Artificial Bee Colony Optimization
Object-Based Distinction between Building Shadow and Water in High-Resolution Imagery Using Fuzzy-Rule Classification and Artificial Bee Colony Optimization
复制标题
使用模糊规则分类和人工蜂群优化在高分辨率图像中基于对象区分建筑物阴影和水
DOI：
10.1155/2016/2385039
复制
发表时间：
2016-07
影响因子：
1.9
通讯作者：
Zhang XX
中科院分区：
文献类型：
--
作者：
He Yuanrong;Zhang Xinxin;Hua Lizhong;Zhang XX
由于城市水体和建筑物阴影光谱的高度相似性，高分辨率卫星图像经常混淆和错误地分类这些特征。为了解决这个问题，我们提出了一个基于对象的方法区分建筑物的阴影从水使用人工蜂群算法。在该方法中，首先计算四个光谱比值带作为额外的输入参数，以提高分割结果的准确性。在分割过程中，一系列的统计因素，如频谱，比率，和尖锐的功能，计算，以弥补在高分辨率图像的缺陷。最后，我们提出了一个模糊规则为基础的分类器，以产生提取规则。该分类器基于人工蜂群优化算法，采用几何平均值（-mean）作为适应度函数。该方法在厦门市的两个试验点进行了试验。基于GF-1卫星数据的实验结果表明，与SVM方法相比，该方法的总体提取精度提高了约6%~ 15%，kappa系数值提高了约0.1 ~ 0.2。对提取规律的分析也证明了建筑物阴影和水体的区分对红/近红外波段和长宽比波段的影响显著。
Due to the high similarity of the spectra of urban water and building shadows, high-resolution satellite imagery often confuses and wrongly classifies these features. To address this problem, we propose an object-based method for distinguishing building shadow from water using an artificial bee colony algorithm. In the method, four spectral ratio bands are first calculated as additional input parameters for improving the accuracy of segmentation results. During the segmentation, a series of statistical factors, such as spectrum, ratio, and sharp features, are calculated to make up for defects in the high-resolution imagery. Finally, we propose a fuzzy-rule-based classifier to generate extraction rules. The classifier is based on artificial bee colony optimization, which employs the geometric mean (-mean) as fitness function. The proposed method was carried out on two test sites in Xiamen City. The experimental results based on GF-1 satellite date show that, compared with SVM method, the proposed method improved the overall accuracy of extraction by approximately 6% to 15% and the kappa coefficient values by approximately 0.1 to 0.2. The analysis of the extraction rules also proves that the red/NIR band and the length-width ratio band are significantly influenced by the distinction between building shadow and water.
登录
查看更多内容
DOI：
10.11834/jrs.20050586
发表时间：
2005
期刊：
National Remote Sensing Bulletin
影响因子：
--
作者：
Han-qiu Xu
通讯作者：
Han-qiu Xu
DOI：
10.3390/rs5073544
发表时间：
2013-07
期刊：
Remote. Sens.
影响因子：
--
作者：
S. K. McFeeters
通讯作者：
S. K. McFeeters
影响因子：
6.7
作者：
Zhang, Y.;Wu, L.;Wang, S.
通讯作者：
Wang, S.
DOI：
10.1016/j.isprsjprs.2013.02.003
发表时间：
2013-06-01
影响因子：
12.7
作者：
Adeline, K. R. M.;Chen, M.;Paparoditis, N.
通讯作者：
Paparoditis, N.
影响因子：
13.5
作者：
Feyisa, Gudina L.;Meilby, Henrik;Proud, Simon R.
通讯作者：
Proud, Simon R.