L
Lionel Gueguen
Researcher at DigitalGlobe
Publications - 61
Citations - 1333
Lionel Gueguen is an academic researcher from DigitalGlobe. The author has contributed to research in topics: Image segmentation & Change detection. The author has an hindex of 16, co-authored 61 publications receiving 1151 citations. Previous affiliations of Lionel Gueguen include Télécom ParisTech & Amazon.com.
Papers
More filters
Journal ArticleDOI
A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results
Martino Pesaresi,Guo Huadong,Xavier Blaes,Daniele Ehrlich,Stefano Ferri,Lionel Gueguen,Matina Halkia,Mayeul Kauffmann,Thomas Kemper,Linlin Lu,Mario A. Marin-Herrera,Georgios K. Ouzounis,Marco Scavazzon,Pierre Soille,Vasileios Syrris,Luigi Zanchetta +15 more
TL;DR: A new fully automatic image information extraction, generalization and mosaic workflow is presented that is based on multiscale textural and morphological image features extraction and a new systematic approach for quality control and validation allowing global spatial and thematic consistency checking is proposed and applied.
Proceedings Article
Faster Neural Networks Straight from JPEG
TL;DR: A simple idea is proposed and explored: train CNNs directly on the blockwise discrete cosine transform (DCT) coefficients computed and available in the middle of the JPEG codec, modified to produce DCT coefficients directly, and evaluated on ImageNet.
Proceedings ArticleDOI
Large-scale damage detection using satellite imagery
Lionel Gueguen,Raffay Hamid +1 more
TL;DR: A semi-supervised learning framework for large-scale damage detection in satellite imagery that results in a ten-fold reduction in human annotation time at a minimal loss in detection accuracy compared to manual inspection is presented.
Journal ArticleDOI
Change Detection Based on Information Measure
TL;DR: The results show a clear improvement in change detection using the proposed unsupervised change detection method compared to other state-of-the-art change detection techniques.
Journal ArticleDOI
Classifying Compound Structures in Satellite Images: A Compressed Representation for Fast Queries
TL;DR: A new compact representation for the fast query/classification of compound structures from very high resolution optical remote sensing imagery relying on the multiscale segmentation of the input image and the quantization of image structures pooled into visual word distributions for the characterization of compound structure is proposed.