Mirko Arnold, Anarta Ghosh, Glen Doherty, Hugh Mulcahy, Stephen Patchett, & Gerard Lacey. (2013). Towards Automatic Direct Observation of Procedure and Skill (DOPS) in Colonoscopy. In Proceedings of the International Conference on Computer Vision Theory and Applications (pp. 48–53).
|
Josep Llados, J. Lopez-Krahe, & Enric Marti. (1999). A Hough-based method for hatched pattern detection in maps and diagrams..
|
David Rotger, Cristina Cañero, Petia Radeva, J. Mauri, E. Fernandez, A. Tovar, et al. (2001). 3D Interactive Visualization and Volumetric Measurements of Coronary Vessels in IVUS..
|
A. Pujol, Alex Caralps, & Juan J. Villanueva. (2001). On the suitability of pixel-outlier removal in face recognition..
|
A. Pujol, Jose Luis Alba, & Juan J. Villanueva. (2001). Supervised Hausdorff-based measures for face recognition..
|
Joan Serrat, X. Varona, Antonio Lopez, Xavier Roca, & Juan J. Villanueva. (2001). P3: a three-dimensional digitizer prototype..
|
V. Chapaprieta, & Ernest Valveny. (2001). Handwritten Digit Recognition Using Point Distribution Models..
|
Jose Luis Alba, A. Pujol, & Juan J. Villanueva. (2001). ST-SOM: A Shape+Texture Self Organizing Map..
|
J.M. Sanchez, & X. Binefa. (2001). Semantics from motion in news videos..
|
Lluis Barcelo, & X. Binefa. (2001). Bayesian Video Mosaicing with Moving Objects..
|
Jordi Gonzalez, X. Varona, Juan J. Villanueva, & Xavier Roca. (2001). On-line Human Activity Recognition for Video Surveillance..
|
David Guillamet, & Jordi Vitria. (2001). Unsupervised Learning of Structural Object Representations.
|
Gemma Sanchez, Josep Llados, & K. Tombre. (2001). An Algorithm to Recognize Graphical Textured Symbols using String Representations..
|
David Lloret, C. Mariño, Joan Serrat, Antonio Lopez, & Juan J. Villanueva. (2001). Landmark-based registration of full SLO video sequences..
|
Hannes Mueller, Andre Groeger, Jonathan Hersh, Andrea Matranga, & Joan Serrat. (2021). Monitoring war destruction from space using machine learning. PNAS - Proceedings of the National Academy of Sciences of the United States of America, 118(23), e2025400118.
Abstract: Existing data on building destruction in conflict zones rely on eyewitness reports or manual detection, which makes it generally scarce, incomplete, and potentially biased. This lack of reliable data imposes severe limitations for media reporting, humanitarian relief efforts, human-rights monitoring, reconstruction initiatives, and academic studies of violent conflict. This article introduces an automated method of measuring destruction in high-resolution satellite images using deep-learning techniques combined with label augmentation and spatial and temporal smoothing, which exploit the underlying spatial and temporal structure of destruction. As a proof of concept, we apply this method to the Syrian civil war and reconstruct the evolution of damage in major cities across the country. Our approach allows generating destruction data with unprecedented scope, resolution, and frequency—and makes use of the ever-higher frequency at which satellite imagery becomes available.
|