Nvinferserver : Do post porcessing on image buffer and send it back to DeepStream pipeline

[m.elkateb]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson Orin
• DeepStream Version 6.1
• JetPack Version (valid for Jetson only) 5.0
• TensorRT Version 8
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) Questions
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
Hi ! I am using nvdsinferserver with triton to run a segmentation model with Deepstream. I want to do post processing within Triton using the python backend to draw polygons and other shapes that Nvosd cannot handle on the image buffer and push it back to the pipeline. Is this possible? Because if i refer to the nvdsinferserver documentation page, the figure only indicates that only metadata is being pushed back to Deepstream pipeline and not the entire buffer. If yes could you provide code snippet ? Thank you in advance!

[fanzh]

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

do you mean want to draw on frame before nvosd ?

1. Nvosd can draw polygons ,please refer to Gst-nvdsosd — DeepStream 6.1.1 Release documentation
2. you can add display meta in probe function, nvosd will process these meta, please refer to osd_sink_pad_buffer_probe in deepstream-test1.
3. some code in probe function, Push frame back to DeepStream pipeline inside a probe function