2016/09/22 by Nicolas Audebert, Audebert, Nicolas, Bertrand Le Saux +3 · 1 citation
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Remote-Sensing Image Classification #cs.CV
paper · pdf · doi:10.48550/arxiv.1609.06861
IEEE International Geosciences and Remote Sensing Symposium (IGARSS), Jul 2016, Beijing, China
arxiv created 2016/09/22 · openalex publication_date 2016/09/22 · arxiv updated 2016/09/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, we investigate the impact of segmentation algorithms as a preprocessing step for classification of remote sensing images in a deep learning framework. Especially, we address the issue of segmenting the image into regions to be classified using pre-trained deep neural networks as feature extractors for an SVM-based classifier. An efficient segmentation as a preprocessing step helps learning by adding a spatially-coherent structure to the data. Therefore, we compare algorithms producing superpixels with more traditional remote sensing segmentation algorithms and measure the variation in terms of classification accuracy. We establish that superpixel algorithms allow for a better classification accuracy as a homogenous and compact segmentation favors better generalization of the training samples.