A Novel Remote Sensing Image Classification Scheme Based on Data Fusion, Multiple Features and Ensemble Learning
- PDF / 806,955 Bytes
- 10 Pages / 547.087 x 737.008 pts Page_size
- 96 Downloads / 215 Views
RESEARCH ARTICLE
A Novel Remote Sensing Image Classification Scheme Based on Data Fusion, Multiple Features and Ensemble Learning Peijun Du & Yu Chen & Junshi Xia & Kun Tan
Received: 30 October 2011 / Accepted: 18 January 2012 / Published online: 24 April 2012 # Indian Society of Remote Sensing 2012
Abstract In this paper, we propose a novel scheme to improve the accuracy of remote sensing image classification by integrating data fusion, multiple feature combination and ensemble learning. Intensity-Hue-Saturation (IHS), Gram-Schmidt (GS), Brovey and wavelet fusion methods are first performed to obtain the optimal fusion images of high resolution and multispectral images. Support Vector Machine (SVM) classifier is then adopted to classify the fused image with different feature sets, and ensemble learning algorithm based on dynamic classifier selection (DCS) is finally used to integrate multiple classification maps. The proposed classification scheme is implemented with three remote sensing data sets, obtaining the highest overall accuracy and kappa coefficient in all cases (92.63% and 0.8917 for BJ-1 data set, 81.89% and 0.7513 for Landsat TM and
P. Du (*) Department of Geographical Information Science, Nanjing University, Nanjing 210093, China e-mail: [email protected] P. Du e-mail: [email protected] P. Du : Y. Chen : J. Xia : K. Tan Key Laboratory for Land Environment and Disaster Monitoring of SBSM, China University of Mining and Technology, Xuzhou 221116, China
SPOT4 data set, 92.21% and 0.8838 for ALOS data set respectively). The experimental results show that the integration of data fusion, feature combination and ensemble learning improves the classification performance obviously and has great potential in practical uses. Keywords Data fusion . Remote sensing . Ensemble learning . Classification . Support vector machine (SVM) . Dynamic classifier selection (DCS)
Introduction Image classification is one of the most important tasks of remote sensing information processing and applications. With the rapid development of remote sensing data acquisition technology, more advanced classification schemes to generate accurate and reliable results are on the increasing demand. A lot of classification algorithms and techniques have been put forward to improve remote sensing image classification accuracy. Many advanced approaches, such as SVM (Zhu & Blumberg 2002; Melgani & Bruzzone 2004), artificial neural networks (ANN) (Serpico & Roli 1995; Bruzzone et al. 1997), fuzzy set (Nadeau & Englefield 2006; Qu et al. 2009) and expert systems (Liu et al. 2008; Kahya et al. 2010), have been widely applied. However, many factors, such as the complexity of the landscape, selected remote sensing data, image pre-processing, a prior
214
knowledge and classification approaches, affect the performance of a classification task (Lu & Weng 2007).Therefore, a series of new methods, aiming at improving the performance of remote sensing image classification, are still required. For example, image fusion performs well in enhancing the cla
Data Loading...
