Jump to content

Template:CUDA ISP for NVIDIA Jetson/Main contents: Difference between revisions

Line 26: Line 26:
{{Review|I think we can do it better. We can focus more on what it does and why people do need it rather than focusing on the NVIDIA ISP. Let's focus on our product. We can just place one sentence that it can work as an alternative to the NVIDIA ISP|lleon}}
{{Review|I think we can do it better. We can focus more on what it does and why people do need it rather than focusing on the NVIDIA ISP. Let's focus on our product. We can just place one sentence that it can work as an alternative to the NVIDIA ISP|lleon}}


CUDA ISP is a RidgeRun library developed to provide an alternative approach to image signal processing using CUDA rather than NVIDIA's Jetson ISP. Since our library's CUDA algorithms run on the GPU, they reduce the CPU usage. It is intended to be used in programs that require a large amount of CPU usage, so by using CUDA ISP, the CPU does not have to take into account the processing done by NVIDIA's Jetson ISP resulting in a better performance of the application by letting the GPU handle the processing. It can also be used with GStreamer applications.   
CUDA ISP is a RidgeRun library developed to provide an alternative approach to image signal processing using CUDA rather than NVIDIA's Jetson ISP. Since our library's CUDA algorithms run on the GPU, they reduce the CPU usage thus freeing its processing capacity for others applications. It is intended to be used for programs that require a large amount of CPU usage. It can also be used with GStreamer applications.   


The algorithms provided by the CUDA ISP are:
The algorithms provided by the CUDA ISP are:
704

edits

Cookies help us deliver our services. By using our services, you agree to our use of cookies.