A Deep Learning based Framework for UAV Trajectory Pattern Recognition
| Autor: | Serge Chaumette, Pascal Desbarats, Xingyu Pan |
|---|---|
| Přispěvatelé: | Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), Pan, Xingyu, Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Université Sciences et Technologies - Bordeaux 1-Université Bordeaux Segalen - Bordeaux 2 |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Contextual image classification
Unmanned Aerial Vehicles (UAV) business.industry Computer science Deep learning pattern recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION deep learning [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] ComputerApplications_COMPUTERSINOTHERSYSTEMS 02 engineering and technology 010501 environmental sciences 01 natural sciences [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV] trajectory [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] Pattern recognition (psychology) Trajectory pattern 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | International Conference on Image Processing Theory, Tool & Applications International Conference on Image Processing Theory, Tool & Applications, Nov 2019, Istanbul, Turkey IPTA |
| Popis: | International audience; Recognizing the trajectory patterns of Unmanned Aerial Vehicles (UAV) allows to identify their missions also to detect abnormalities for intelligent supervision. To take advantage of the developments of deep learning on image classification, we proposed a method that converts 3D trajectory data into 2D images and trains a deep network adapted to sketch-like images. We achieved a promising recognition rate of 99.5% on the database of simulated UAV trajectory images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|