Land Cover and Land Use Classification with TWOPAC: towards Automated Processing for Pixel- and Object-Based Image Classification

Abstract

We present a novel and innovative automated processing environment for the derivation of land cover (LC) and land use (LU) information. This processing framework named TWOPAC (TWinned Object and Pixel based Automated classification Chain) enables the standardized, independent, user-friendly, and comparable derivation of LC and LU information, with minimized manual classification labor. TWOPAC allows classification of multi-spectral and multi-temporal remote sensing imagery from different sensor types. TWOPAC enables not only pixel-based classification, but also allows classification based on object-based characteristics. Classification is based on a Decision Tree approach (DT) for which the well-known C5.0 code has been implemented, which builds decision trees based on the concept of information entropy. TWOPAC enables automatic generation of the decision tree classifier based on a C5.0-retrieved ascii-file, as well as fully automatic validation of the classification output via sample based accuracy assessment. Envisaging the automated generation of standardized land cover products, as well as area-wide classification of large amounts of data in preferably a short processing time, standardized interfaces for process control, Web Processing Services (WPS), as introduced by the Open Geospatial Consortium (OGC), are utilized. TWOPAC's functionality to process geospatial raster or vector data via web resources (server, network) enables 2531TWOPAC's usability independent of any commercial client or desktop software and allows for large scale data processing on servers. Furthermore, the components of TWOPAC were built-up using open source code components and are implemented as a plug-in for Quantum GIS software for easy handling of the classification process from the user's perspective.

A Python-Based Open Source System for Geographic Object-Based Image Analysis (GEOBIA) Utilizing Raster Attribute Tables

“…Within OTB, there are also per-pixel methods for image classification, including a number of machine learning algorithms through OpenCV (http://opencv.org). The TWinned Object and Pixel-based Automated classification Chain (TWOPAC; [11]) aims to be a complete framework for pixel and object-based classification utilizing a decision tree approach for classification. However, the authors currently perform the segmentation outside of the framework using eCognition.…”

Varying Scale and Capability of Envisat ASAR-WSM, TerraSAR-X Scansar and TerraSAR-X Stripmap Data to Assess Urban Flood Situations: A Case Study of the Mekong Delta in Can Tho Province

“…While most authors prefer radar data for the mapping of floods and inundation [8,38], also optical [39,40] and even thermal [41] approaches exist to map inundated areas (permanent water bodies and flooded regions). Huth et al [39] used 6.25 m resolved Rapid Eye data and an object oriented approach to derive 14 land cover and land use classes for the Mekong Delta-amongst them rivers, canals, and aquaculture ponds.…”

“…Huth et al [39] used 6.25 m resolved Rapid Eye data and an object oriented approach to derive 14 land cover and land use classes for the Mekong Delta-amongst them rivers, canals, and aquaculture ponds. However, this mapping was performed on data acquired at the start of the dry season end of January, when cloud cover was low.…”

Aplicación del Estimador de Parámetros de Segmentación por Media-desplazada (EPSM) a las imágenes de satélite de muy alta resolución espacial: Tetuán (Marruecos)

“…Este proceso es lento y no satisface los requerimientos, en términos de frecuencia de actualización, del usuario (Hanson y Wolff, 2010). Además, con el aumento del uso de imágenes de satélite de muy alta resolución espacial, los requisitos del procesamiento automático/semiautomático de un menor número de parámetros es una necesidad (Huth et al, 2012).…”