KITWARE INC — Department of Defense SBIR Phase II: A19-118

Description

There are many challenges in safely maneuvering combat vehicles through a battlespace. Path planning requires detailed knowledge of the terrain and any physical barriers as well as the location of dangers, such as landmines or enemy positions. Small UAVs are now convenient for battlespace reconnaissance using visible and thermal cameras, but the raw imagery needs to be quickly converted to 3D environment maps showing physical obstacles and threats. Kitware proposes Obstacle TeleSculptor to address this need. Obstacle TeleSculptor extends our existing open source TeleSculptor application for 3D scene modeling from UAV-collected imagery. In addition to reconstructing the environment, Obstacle TeleSculptor will map observations from multiple views and multiple sensors onto the 3D surface to enable detection and classification of threats such as landmines or enemy vehicles that should be avoided. The system will use deep networks to learn features that optimize these detection results using all available observations. It will also be open and configurable to allow reuse of the accumulated features for other applications. The combined map of 3D terrain and detected obstacles from timely UAV imagery will provide the critical intelligence needed to make informed decisions about battlespace navigation.