|
Distributed simulation environments are increasingly using video to stimulate operational systems and their prototypical
equivalents. Traditionally, this video has been synthesized and delivered by an analog means to consuming software
applications. Scene generators typically render to commodity video cards, generate out of band metadata, and convert
their outputs to formats compatible with the stimulated systems. However, the approach becomes hardware intensive as
environment scale and distribution requirements grow. Streaming video technologies can be applied to uncouple video
sources from their consumers, thereby enabling video channel quantities beyond rendering hardware outputs. Moreover,
metadata describing the video content can be multiplexed, thereby ensuring temporal registration between video and its
attribution. As an application of this approach, the Night Vision Image Generator (NVIG) has been extended and
integrated with distribution architectures to deliver streaming video in virtual simulation environments. Video capture
hardware emulation and application frame buffer reads are considered for capturing rendered scenes. Video source to
encoder bindings and content multiplexing are realized by combining third party video codec, container, and transport
implementations with original metadata encoders. Readily available commercial and open source solutions are utilized
for content distribution and demultiplexing to a variety of formats and clients. Connected and connectionless distribution
approaches are discussed with respect to latency and reliability. Client side scalability, latency, and initialization issues
are addressed. Finally, the solution is applied to tactical systems stimulus and training, showing the evolvement from the
analog to the streamed video approach.
|
