Human View (HumV)

There is a need to develop a sufficient-fidelity simulation tool to create multi-sensor datasets for human activity detection and recognition. To address this critical need, Intelligent Automation Inc. (IAI), Infoscitex Corporation (IST), Rochester Institute of Technology (RIT), and Raytheon IDS propose a novel, integrated, high-fidelity simulation tool: HumanView (HumV) of human signatures. The proposed software system will integrate various multi-physics simulation tools and develop new simulation models and algorithms to address capability gaps sensor data simulation. The key elements of the proposed HumV system are: (i) HumV editor module, which allows researchers to view available models, manage the simulation configuration using intuitive graphical user interface. (ii) HumV models module, which is a data store containing 3D human models, 3D geometric models of environment, and relevant sensor models (EO, IR, LIDAR and hyperspectral). (iii) HumV simulator module, which allows the user to simulate multiple scenarios that will generate the synthetic sensor data for analytics. In Phase I, the HumV Team has built a preliminary prototype and demonstrated the HumVs capability to synthesize multi-modal sensor response of human activity. The goal of Phase II is to build a fully functional prototype of HumV and conduct test and validation of HumV with real