Paper 14029-18
Paper 14029-18
From miniature vehicles to mission scenarios: an indoor proving ground for air-to-ground vehicle detection, recognition, and identification
29 April 2026 • 9:30 AM - 9:50 AM EDT | National Harbor 7
Abstract
This work presents an indoor proving ground framework for training and evaluating air-to-ground vehicle detection models. To avoid costly outdoor acquisition campaigns, we reuse miniature military vehicle models—previously employed for semi-synthetic training—within a physically realistic diorama that simulates diverse environments and conditions such as occlusions, clutter, smoke, and camouflage. Images are captured using real camera systems, ensuring realistic sensor characteristics. By employing identical miniature vehicles in both training and testing, the approach reduces the domain gap between synthetic and real data, enabling focused investigation of model performance under complex scenes and between visually similar military vehicles. The framework provides a cost-effective, scalable solution for developing robust AI-based vehicle detection, recognition and identification.
Presenter
Institut Franco-Allemand de Recherches de Saint-Louis (France)
Nicolas Hueber received the Ph.D. degree in optoelectronics and systems in 2007, from the University of Haute Alsace (UHA), Mulhouse, France. In 2007 he joined as a researcher, the French-German Research Institute of Saint-Louis (ISL), France, and was first involved in the optronic countermeasure and laser dazzling studies. From 2009 to 2021, he joined, as a research project manager the European Laboratory for Sensory Intelligence (ELSI); an ISL research team focused on edge computing and embedded Artificial Intelligence for automatic object detection, recognition and tracking. Since then, he has joined IGC team as researcher. His current research interests focus on deep learning and relevant dataset generation, event-based sensors and bi-modal optronic systems.. He is currently involved in the NATO STO SET-243, 247 and SET-ET-137 groups. He received a best paper award at the SPIE conference “Machine Intelligence and Bio-inspired Computation IX” in 2015.