How to track and re-identificate people in multicamera scenario using RTSP

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi,

I want to create an application, preferably in Python, to track and re-identificate people in multicamera scenarios. Can anyone suggest any tutorial for same ?

Problem : connect 2 RTSP cameras, detect people, by using resnet caffe model, and draw their bounding boxes

Two Camera :
• IPv4 Address_1 : 192.168.10.28
• IPv4 Address _2: 192.168.10.138

Is below tutorial is right to follow ?

  1. deepstream_python_apps/apps/deepstream-rtsp-in-rtsp-out at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub
  2. deepstream_python_apps/apps/deepstream-test3 at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub

Which is one is best to follow ? Do you suggest any youtube video for this tutorials ?

How to run program ?

python3 deepstream_test1_rtsp_in_rtsp_out.py -i rtsp://sample_1.mp4 rtsp://sample_2.mp4 rtsp://sample_N.mp4 -g nvinfer

python3 deepstream_test_3.py -i [uri2] … [uriN] --pgie nvinferserver-grpc -c [–no-display] [–silent]

e.g.
In this case, .MP4 is input : how to create it ?

This is original RTSP :

rtsp://admin:paymentinapp82@192.168.10.138 -c H264 -b 4000000 -e 0
rtsp://admin:paymentinapp82@192.168.10.28 -c H264 -b 4000000 -e 0

4

When we run :

While inside the dir /opt/nvidia/deepstream/deepstream/samples/configs/tao_pretrained_models/ , run the deepstream-app
as follows:
deepstream-app -c deepstream_app_source1_peoplenet.txt

it return error : 0:00:21.726866009 11321 0xaaab022690d0 ERROR nvinfer gstnvinfer.cpp:676:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2129> [UID = 1]: build engine file failed
free(): double free detected in tcache 2
Aborted (core dumped)

  1. deepstream_python_apps/apps/deepstream-test3 at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub
5

Do you want to tracking object seperately between two cameras? Or you want to tracking object acrossing cameras?

6

Thank you very much. Two different rtsp camera : basically want to track only people

7

Here is the details steps to run the samples: deepstream_python_apps/apps/deepstream-test3 at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub

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)

8

Problem solved. Please closed it. Thank you very much.