The deepstream_lpr_app performs well when processing videos, but encounters issues when using IP cameras as the data source in MultiStream

This is the device specification:
image

The command used:

    ./deepstream-lpr-app 1 2 0 infer rtsp://cam_1 rtsp://cam_2 output.264

Here we are replacing rtsp://cam_1, rtsp://cam_2 with actual camera rtsp link.

The deepstream_lpr_app performs well when used videos for MultiStream, but encounters issues (pipeline got stuck and neither output nor the error or warning was returned) when using IP cameras as the data source in MultiStream.*

Could you assist us with this? Thank you.

Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• 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)

Changing to Deepstream forum.

Hello Morganh pardon me for the delayed reply.

Below is the information you requested.
• Hardware Platform: Jetson Nano
• DeepStream Version:

deepstream-app --version
deepstream-app version 6.0.1
DeepStreamSDK 6.0.1

• JetPack Version: LT 32.7.4
• TensorRT Version: 8.2.1.9

This project is in continuation of:

The program is same but this time we are trying dual streaming.

When using a single RTSP stream, the application performs well. However, when working with more than one stream, there are issues. With dual streams, the video stream occasionally works, but it fails to detect all license plates and also running with 20 sec delay compared with original stream even after enabling live-source =1 in Gst-nvstreammux (no delays in single streaming and single stream is also detecting all the number plates it came across).

deepstream_lpr_app does not support rtsp source. please refer to this code.

OK,
so if we want to run 6+ RTSP stream using LPD and LPR model, which approach or sample code should we follow?

please refer to /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test3/, it can support local file and rtsp source.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.