Multi-int Multi-look 3D Features Image Fusion with Machine Learning

Under this SBIR Phase I project, we propose a deep-learning based framework for detecting targets from multi-int airborne sensors. Novateur will develop a generalized Transformer-based framework to fuse multi-modal sensor data in the feature space for improved target detection in complex scenarios. The proposed system takes advantage of self-attention in Transformers to capture long-term dependencies in multi-modal sensor data and estimates the relevance of the computed deep features from heterogenous sensors. We will also develop methods for hard example mining and augmentation policies to optimize the detector performance for detecting occluded targets. The Phase I effort will focus on developing an end-to-end detection pipeline and a prototype software application to demonstrate the capabilities different sensors modalities on publicly available aerial and satellite data. The proposed effort will build upon the experience and expertise of Novateur team in the areas of deep neural networks, sensor fusion, data exploitation, and development of real-time systems for robotic applications.