hi,
目前我们相机部分占用CPU和GPU资源较高,所以想使用非CUDA方式进行转化,想请教一下几个问题,是否有相关的示例代码?
硬件为:Jetson Orin 64GB,software: JetPack5.1.3
1、YUV422转YUV420是否可以用非CUDA方式实现,如VIC?
2、YUV420缩放及去畸变是否可以用非CUDA方式实现,如VIC?
3、YUV422是否可以直接转换RGB格式?用非CUDA方式
谢谢
hi,
目前我们相机部分占用CPU和GPU资源较高,所以想使用非CUDA方式进行转化,想请教一下几个问题,是否有相关的示例代码?
硬件为:Jetson Orin 64GB,software: JetPack5.1.3
1、YUV422转YUV420是否可以用非CUDA方式实现,如VIC?
2、YUV420缩放及去畸变是否可以用非CUDA方式实现,如VIC?
3、YUV422是否可以直接转换RGB格式?用非CUDA方式
谢谢
Based on the provided context, I will answer the question by comparing the supported output formats for VIC-based nvvidconv and CUDA-based nvvidconv on Jetson AGX Orin.
VIC-based nvvidconv
The VIC-based nvvidconv on Jetson AGX Orin supports the following RAW-YUV output formats:
I420
UYVY
YUY2
YVYU
NV12
NV16
NV24
GRAY8
BGRx
RGBA
Y42B
CUDA-based nvvidconv
The CUDA-based nvvidconv on GPU supports the following RAW-YUV output formats:
I420
NV12
P010_10LE
I420_10LE
GRAY8
BGRx
RGBA
Comparison
Comparing the two lists, we can see that:
Both VIC-based and CUDA-based nvvidconv support I420, NV12, GRAY8, BGRx, and RGBA output formats.
VIC-based nvvidconv supports additional output formats, including UYVY, YUY2, YVYU, NV16, NV24, and Y42B.
CUDA-based nvvidconv supports P010_10LE and I420_10LE output formats, which are not supported by VIC-based nvvidconv.
Answer to the question
Based on the comparison, we can conclude that:
YUV422 is supported by VIC-based nvvidconv (UYVY, YUY2, and YVYU) but not by CUDA-based nvvidconv.
YUV420 is supported by both VIC-based and CUDA-based nvvidconv (I420 and NV12).
RGB is supported by both VIC-based and CUDA-based nvvidconv (BGRx and RGBA).
Therefore, the correct answer is:
YUV422: VIC
YUV420: Both VIC and CUDA
RGB: Both VIC and CUDA
hi,
可以提供VIC的相关示例代码吗?
抱歉刚刚描述有点问题,我们的设计是从YUV422最终转成BGR格式
We don’t public the source but provide API.
hi
请问那我们应该如何用起来呢??
没有参考代码吗
You can check the MMAPI sample code.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.