Land-cover Classification Using Radarsat and Landsat Imagery for St. Louis, Missouri

Abstract

This paper presents the potential of integrating radar data features with optical data to improve automatic land-cover mapping. For our study area of St. Louis, Missouri, Landsat ETMϩ and Radarsat images are orthorectified and co-registered to each other. A maximum likelihood classifier is utilized to determine different land-cover categories. Ground reference data from sites throughout the study area are collected for training and validation. The variations in classification accuracy due to a number of radar imaging processing techniques are studied. The relationship between the processing window and the land classification is also investigated. In addition, the Landsat images are fused with several combinations of processed radar features. The classification accuracies from the Landsat and radar feature combinations are studied. Our research finds that fusion of multi-sensor data improves the classification accuracy over a single Landsat sensor, although different processing techniques on radar images are required to obtain the best results. In our study, fusion of Landsat images and Radarsat feature combinations from a 13 ϫ 13 entropy window, 9 ϫ 9 data range widow, and 19 ϫ 19 mean filter window achieves the highest overall accuracy improvement (10 percent) over the Landsat images alone.

A Review of the Application of Optical and Radar Remote Sensing Data Fusion to Land Use Mapping and Monitoring

“…Methods of image fusion can be grouped into three categories depending on the level at which the integration is performed: (i) pixel-level fusion (data fusion); (ii) feature fusion; and (iii) decision fusion. The first category refers to the combination of the original image pixels, while the second is based on combining features extracted from the individual datasets [46,[52][53][54]. In contrast, decision fusion requires preliminary analysis of the different datasets, e.g., the separate classifications of optical and SAR data, after which outputs are combined to generate a final result, e.g., [43,55,56].…”

LiDAR-Landsat data fusion for large-area assessment of urban land cover: Balancing spatial resolution, data volume and mapping accuracy

“…We first resampled 30 m TM data to 1, 5, 10, and 15 m resolutions using nearest neighbor (NN) resampling to minimize loss of original pixel values at finer resolutions (Gardner et al, 2008;Khan et al, 1995;Raptis et al, 2003). We then used layerstacking to combine LiDAR surface models and TM data into three types of composite images at the five key resolutions: (1) CHM + nDSM + IS + TM, (2) CHM + nDSM (LiDAR structural) + TM, and (3) IS (LiDAR intensity) + TM (Huang et al, 2007). In addition, we produced a LiDAR only composite image by layerstacking CHM, nDSM, and IS models.…”

Classification of Mangrove Species in the Northeastern of Brazil Based on Hybrid Images of Remote Sensing

“…Bruno Cesar Pereira da Costa;Venerando Eustáquio Amaro & Anderson Targino da Silva Ferreira 2002, 2005Huang et al, 2007;Blanco et al, 2009). Deste modo, a integração entre as imagens ópticas e de micro-ondas, também conhecida como fusão de imagens, vem se firmando como uma técnica para maximizar a extração de informações relevantes que possibilite a espacialização, considerando os aspectos composicionais e estruturais, das espécies de uma floresta de mangue.…”