A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Optimizing classification performance in an object-based very-high-resolution land use-land cover urban application
This study evaluates the impact of three Feature Selection (FS) algorithms in an Object Based Image Analysis (OBIA) framework for Very-High-Resolution (VHR) Land Use-Land Cover (LULC) classification. The three selected FS algorithms, Correlation Based Selection (CFS), Mean Decrease in Accuracy (MDA) and Random Forest (RF) based Recursive Feature Elimination (RFE), were tested on Support Vector Machine (SVM), K-Nearest Neighbor, and Random Forest (RF) classifiers. The results demonstrate that the accuracy of SVM and KNN classifiers are the most sensitive to FS. The RF appeared to be more robust to high dimensionality, although a significant increase in accuracy was found by using the RFE method. In terms of classification accuracy, SVM performed the best using FS, followed by RF and KNN. Finally, only a small number of features is needed to achieve the highest performance using each classifier. This study emphasizes the benefits of rigorous FS for maximizing performance, as well as for minimizing model complexity and interpretation.
Optimizing classification performance in an object-based very-high-resolution land use-land cover urban application
This study evaluates the impact of three Feature Selection (FS) algorithms in an Object Based Image Analysis (OBIA) framework for Very-High-Resolution (VHR) Land Use-Land Cover (LULC) classification. The three selected FS algorithms, Correlation Based Selection (CFS), Mean Decrease in Accuracy (MDA) and Random Forest (RF) based Recursive Feature Elimination (RFE), were tested on Support Vector Machine (SVM), K-Nearest Neighbor, and Random Forest (RF) classifiers. The results demonstrate that the accuracy of SVM and KNN classifiers are the most sensitive to FS. The RF appeared to be more robust to high dimensionality, although a significant increase in accuracy was found by using the RFE method. In terms of classification accuracy, SVM performed the best using FS, followed by RF and KNN. Finally, only a small number of features is needed to achieve the highest performance using each classifier. This study emphasizes the benefits of rigorous FS for maximizing performance, as well as for minimizing model complexity and interpretation.
Optimizing classification performance in an object-based very-high-resolution land use-land cover urban application
Georganos, Stefanos (author) / Grippa, Tais (author) / Vanhuysse, Sabine (author) / Lennert, Moritz (author) / Shimoni, Michal (author) / Wolff, Eléonore (author)
Remote Sensing Technologies and Applications in Urban Environments II ; 2017 ; Warsaw,Poland
Proc. SPIE ; 10431
2017-10-04
Conference paper
Electronic Resource
English
Urban land-cover dynamics in arid China based on high-resolution urban land mapping products
| BASE | 2017
Learning selfhood scales for urban land cover mapping with very-high-resolution satellite images
| Online Contents | 2016
Hybrid Object-based Approach for Land Use /Land Cover Mapping using High Resolution Imagery
| BASE | 2011