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, | 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, it reduces 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: |
Revision as of 15:57, 10 March 2023
CUDA ISP for NVIDIA Jetson RidgeRun documentation is currently under development. |
CUDA ISP for NVIDIA Jetson! CUDA ISP for NVIDIA Jetson Plugin from RidgeRun. |
| ||||||||||||||||
CUDA ISP for NVIDIA Jetson | |||||||||||||||||
This wiki is a user guide for our CUDA ISP for NVIDIA Jetson project. What is CUDA ISP for NVIDIA Jetson?
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, it reduces 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:
In the image below you can see the software stack of the library. | |||||||||||||||||
RidgeRun also makes a binary-only evaluation version available. Please refer to Contact Us to get an evaluation binary. Use casesCUDA ISP provides an alternative solution to reduce CPU usage by allowing the GPU handle the image processing.
If you ever found yourself overloading the CPU processing capacity, the GPU can handle it via CUDA ISP. | |||||||||||||||||
Computers with x86 architecture does not have a built-in ISP. By adding a discrete GPU to the architecture, CUDA ISP can be used as an alternative processor.
Developing artificial intelligence (AI) applications, such as computer vision, can require intensive computations in which the GPU can help with the processing.
Using cameras in applications require CPU processing for capturing images. Applications that may use many cameras can overload the CPU processing capacity affecting the performance of the CPU for non-related camera data processing. By letting the GPU handle the image processing of the cameras, the CPU can focus on processing data for the other elements in the application.
Streaming applications require lots of CPU processing as well. By letting the GPU handle it with CUDA ISP, the CPU will be freed for other processing tasks. Tested PlatformsSince CUDA ISP is a C++ library, it can be run on different platforms:
| |||||||||||||||||
RidgeRun Support | |||||||||||||||||
RidgeRun provides support for embedded Linux development for NVIDIA, Xilinx, Freescale/NXP, and Texas Instruments platforms, specializing in multimedia applications. This page contains detailed guides and information on how to get started with the CUDA ISP for NVIDIA Jetson and start using its full capabilities. To get up-to-speed with your CUDA ISP for NVIDIA Jetson, start by clicking below:
|