Are there any examples in the sdk (or point me to the docs) where I can run the gstreamer/deepstream elements async. I want to run the rtsp streaming and the nvdsanalytics pipeline asynchronously in c++. Appreciate it.
Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) GPU • DeepStream Version 6.0.1 • JetPack Version (valid for Jetson only) • TensorRT Version • NVIDIA GPU Driver Version (valid for GPU only) • Issue Type( questions, new requirements, bugs) • 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)
So I have couple of rtsp cameras in my pipeline, I batch around 100 frames and use that for generating business metrics (nvdsanalytics). I noticed that, as the total number of tracks increase (during peak times) the business metrics (analytics) blocks the main pipeline by a couple hundred milliseconds. Just wondering what could be the best solution for this use case.
Did you use our nvdsanalytics whiout any change and what’s the pipeline you used?
If you implement by your self, you can open a new thread to do the analytics.
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
What’s your pipeline like? Do you implement your own plugin? If you just use our plugin, you can start a thread on the plugin probe function.