Computer vision and deep learning—among the most active research areas today—have been used for human identification and human activity recognition. Under the H-MASINT program (a multi-year, multi-million-dollar, cross-directorate program chartered by the AFRL), Innovision’s chief scientist led 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 models from 2-D imagery, estimate body measurements from a body shape model, and create a shape model based on body measurements. Our visual computing work also supports medical imaging, training, and immersive simulation—including 3D models, extended reality (XR) environments, and serious games that enhance learning, analysis, and engagement.