Optimizing classification performance in an object-based very-high-resolution land use-land cover urban application

Stefanos Georganos; Tais Grippa; Sabine Vanhuysse; Moritz Lennert; Michal Shimoni; Eléonore Wolff

doi:10.1117/12.2278482

Translator Disclaimer

4 October 2017 Optimizing classification performance in an object-based very-high-resolution land use-land cover urban application

Stefanos Georganos, Tais Grippa, Sabine Vanhuysse, Moritz Lennert, Michal Shimoni, Eléonore Wolff

Author Affiliations +

Proceedings Volume 10431, Remote Sensing Technologies and Applications in Urban Environments II; 104310I (2017) https://doi.org/10.1117/12.2278482
Event: SPIE Remote Sensing, 2017, Warsaw, Poland

Abstract

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.

Conference Presentation

Citation Download Citation

Stefanos Georganos, Tais Grippa, Sabine Vanhuysse, Moritz Lennert, Michal Shimoni, and Eléonore Wolff "Optimizing classification performance in an object-based very-high-resolution land use-land cover urban application", Proc. SPIE 10431, Remote Sensing Technologies and Applications in Urban Environments II, 104310I (4 October 2017); https://doi.org/10.1117/12.2278482

ACCESS THE FULL ARTICLE