Getting Access to the PVA

From RidgeRun Developer Wiki


Follow Us in Twitter LinkedIn Email Share this page



NVIDIA partner logo






It is possible to unlock the potential of the PVA hardware acceleration using three different methods:

  1. Vision Programming Interface (VPI); an NVIDIA library with several image signal processing and analysis algorithms accelerated using CPU, CUDA, and PVA.
  2. RidgeRun GstVPI; a GStreamer plug-in with elements that leverage VPI to GStreamer.
  3. Custom Applications; which involve custom C++ applications based on RidgeRun LibPVA, porting and/or developing custom algorithms, and a library that exposes an API to access the PVA for hardware acceleration.