Inactive

The Walk-through Rendering from Images of Varying Altitudes (WRIVA) Program aims to develop software algorithm-based systems that can create photorealistic, navigable three-dimensional site models usi... The Walk-through Rendering from Images of Varying Altitudes (WRIVA) Program aims to develop software algorithm-based systems that can create photorealistic, navigable three-dimensional site models using a highly limited corpus of imagery, to include ground level imagery, surveillance height imagery (traffic camera), UAV altitude imagery, and Satellite imagery. Additionally, where imagery lacks metadata indicating geolocation or time of collection, WRIVA seeks to estimate these metadata parameters using image features and other indicators to incorporate them in site-modelling and other downstream algorithms. Many US IC and DOD agencies require this capability to enhance safety while conducting activities where a rich corpus of imagery is unavailable, such as HADR. Expanding site modelling capabilities will allow these activities to be conducted more effectively, with reduced risk to personnel. Site modelling is highly desired to support missions across the DOD, IC, and law enforcement to allow personnel to train and rehearse prior to executing an activity. Under current methods the set of locations for which site models can be easily created is highly limited due to the volume of supportive information that is necessary to build a model using conventional methodologies. Further, the construction of a site model can be challenging due to source imagery having varying environmental conditions, such as clouds, seasonal variation and shadow obscuration.