Probe OSD input and output

Accelerated Computing Intelligent Video Analytics DeepStream SDK
#1

• Hardware Platform (Jetson / GPU) : GPU - RTX3080
• DeepStream Version : 6.1
• TensorRT Version : 8.2.5-1+cuda11.4
• NVIDIA GPU Driver Version (valid for GPU only) : 510.73.05
• Issue Type( questions, new requirements, bugs) : Question

I want to be able to save osd frames based on batch metadata. As I’m seeing in the docs, the osd only outputs the rgba buffer, so metadata gets lost inside. Is there a nice way to accomplish this??

#3

Hi @madisi98 ,
You can use Object Encoder APIs and sample /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-image-meta-test to encode the OSD frames.

#4

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.
Thanks