Human Modeling and Simulation
A human is a complicated system. Various digital human models are used to describe human physical, biological, physiological, behavioral, mental, and cognitive features and characteristics and to simulate/predict human responses under various conditions, such as force, acceleration, heat, electro-magnetic waves, etc. Digital human models have been widely used in human-centered products and services. Innovision has more than 20 years of experience and broad capabilities in human modeling and simulation, from human shape modeling and musculoskeletal modeling to multi-rigid body modeling and full body anatomical structure finite element modeling. We are good at using a variety of open source software tools (e.g., Blender, Unity, OpenSim, Pulse Engine) and commercial-off-the-shelf tools (3dsMax, Motion Builder, and LSDYNA) to solve challenging problems of anthropometrics, ergonomics, biomechanics, and physiology.
Impact Biomechanical Modeling and Simulation
Impact or acceleration from an automobile crash, a helicopter harsh landing, or a road-side explosion to a human can cause serious or even fatal injuries. Impact biomechanical modeling and simulation can be used to discover the injury mechanism, to assess injury risks under various scenarios, and to optimize energy attenuating structure, restraint systems, and protection devices to mitigate injury risks. Innovision researchers have nearly 30 years of R&D experience in the area of impact biomechanical modeling and simulation. The projects we have worked include building a full-scale finite element crash model of 1997 Honda Accord, limiting performance analysis of seat belt, modeling and simulation of out-of-position occupant-airbag interaction, optimal control of helicopter seat cushion for the reduction of spinal injuries, ejection seat simulation, and mobile robot helicopter seat with optimized energy attenuation ( SBIR Phase I and II).
Computer Vision and Deep Learning
As one of most active research areas, computer vision and deep learning has been used for human identification and human activity recognition. Under the H-MASINT program (a multi-year, multi-million dollars cross directorate program charted by the AFRL), Innovision’s chief scientist had been leading a group of scientists and engineers utilizing computer vision and deep learning to develop technologies for human identification and human activity recognition. In recent years, using deep learning, Innovision has built technologies that can extract 3-D human shape model from 2-D imagery, estimate body measurements from a body shape model, and crate a shape model based on body measurements.
714 E Monument Ave
Dayton OH 45402