Request python deepstream demo based on RTP video feed

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

Is there any python deepstream demo based on RTP video feed?

Or any similar python code in v1.1.8 repo?

PS: below is my environment based on jetson orin nano 8GB

Software part of jetson-stats 4.2.12 - (c) 2024, Raffaello Bonghi
Model: NVIDIA Orin Nano Developer Kit - Jetpack 5.1.4 [L4T 35.6.0]
NV Power Mode[0]: 15W
Serial Number: [XXX Show with: jetson_release -s XXX]
Hardware:
 - P-Number: p3767-0005
 - Module: NVIDIA Jetson Orin Nano (Developer kit)
Platform:
 - Distribution: Ubuntu 20.04 focal
 - Release: 5.10.216-tegra
jtop:
 - Version: 4.2.12
 - Service: Active
Libraries:
 - CUDA: 11.4.315
 - cuDNN: 8.6.0.166
 - TensorRT: 8.5.2.2
 - VPI: 2.4.8
 - OpenCV: 4.9.0 - with CUDA: YES
DeepStream C/C++ SDK version: 6.3

Python Environment:
Python 3.8.10
    GStreamer:                   YES (1.16.3)
  NVIDIA CUDA:                   YES (ver 11.4, CUFFT CUBLAS FAST_MATH)
        OpenCV version: 4.9.0  CUDA True
          YOLO version: 8.3.33
         Torch version: 2.1.0a0+41361538.nv23.06
   Torchvision version: 0.16.1+fdea156
DeepStream SDK version: 1.1.8
3

Do you mean rtp multicast?

The following command line shows how to build a pipeline. Just follow the command line to implement the Python code.

gst-launch-1.0 uridecodebin uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264 ! nvvideoconvert ! "video/x-raw(memory:NVMM),format=NV12" ! nvv4l2h264enc bitrate=2000000 insert-sps-pps=true ! h264parse ! rtph264pay ! udpsink host=224.224.255.255 port=5400

 gst-launch-1.0 udpsrc address=224.224.255.255 port=5400 caps="application/x-rtp, media=(string)video, clock-rate=(int)90000, encoding-name=(string)H264, payload=(int)96" ! rtph264depay ! decodebin ! mux.sink_0 nvstreammux name=mux batch-size=1 width=1280 height=720 live-source=true ! nvinfer config-file-path=/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test2/dstest2_pgie_config.txt ! nvdsosd ! nvvideoconvert ! 'video/x-raw(memory:NVMM),format=NV12' ! nv3dsink

We recommend you upgrade to DS-7.1. We usually do not fix issues on older versions.

4

I have writen a python code, which is similar to gst-launch-1-0 command , but the performance is NOT good.

Can you help to take a look and based on this python code I want to use deep stream code.

As currently, I didn’t find any python deepstream code for RTP video source.

5 
gst-launch-1.0 udpsrc port=5600 buffer-size=8388608 ! application/x-rtp,encoding-name=H265,payload=96 ! rtph265depay ! h265parse ! nvv4l2decoder ! nv3dsink
6

I tried pipline:

pipeline_str = (
    "udpsrc port=5600 buffer-size=8388608 ! "
    "application/x-rtp,encoding-name=H265,payload=96 ! "
    "rtph265depay ! "
    "h265parse ! "
    "nvv4l2decoder ! "
    "nv3dsink"
)

only get below result: (better than gst-launch-1.0 udpsrc port=5600 ! application/x-rtp,encoding-name=H265,payload=96 ! rtph265depay ! h265parse ! nvv4l2decoder ! nvvidconv ! xvimagesink, but not close to 60FPS)

FPS: 6.98
FPS: 21.99
FPS: 15.99
FPS: 19.98
FPS: 17.99
FPS: 18.00
FPS: 19.98
FPS: 17.99
FPS: 19.98
FPS: 19.99
FPS: 19.99
FPS: 18.00
FPS: 17.98
FPS: 17.98
FPS: 20.99
FPS: 16.99
7

duplicate with Gst-launch-1.0 only get 15FPS on jetson orin? - #6 by daniel2008_12

8

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