DC-ATR: Distributed Co-operative ATR Using Low Resolution Mobile Sensors

We propose to leverage recent advances in computationally efficient and accurate object detection and recognition using EO imaging to develop a novel multi-sensor distributed ATR capability. The proliferation of UGVs and UAVs has resulted in a unique opportunity for large scale surveillance and monitoring. However, weight and power constraints require that a distributed ATR system be both extremely efficient to avoid using unnecessary power and extremely effective at integrating information from multiple camera viewpoints to avoid the limitations of inherently low-resolution sensors. There is a need for a cooperative ATR approach which is based on the extraction of potential targets by individual mobile sensor platforms followed by a fusion stage which pools information across multiple camera viewpoints to create an accurate, high-resolution ATR decision.