CUDA ISP for NVIDIA Jetson
CUDA-based Image Signal Processing (ISP) Library for NVIDIA platforms!
CUDA ISP accelerates Image Processing algorithms by offloading their execution to an available NVIDIA GPU, allowing the CPU to handle more critical tasks. The CUDA ISP core is based on NPP and is GStreamer-ready thanks to GstCUDA. It is also compatible with x86-based systems and NVIDIA Jetson embedded platforms.
With our CUDA ISP library, you can now perform essential image processing tasks such as:
​
-
Bayer binary shifting
-
Debayering
-
Auto-white balancing on interleaved RGB and I420 planar formats
All with the help of your NVIDIA GPU!
CUDA ISP offers an alternative for image signal processing. The key features are:
-
Processing done by GPU with NVIDIA's NPP library and CUDA.
-
Compatible with other CUDA applications
-
Reduce usage of CPU processing.
-
Compatible with x86 architecture and discrete GPUs.
​
​
Platforms Supported
NVIDIA Jetson
NVIDIA discrete GPUs