Stream to kafka using deepstream

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

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)
i saw deepstream binding apps test4 but it is different from my idea
hi i have a problem can help me in that?
my pipeline is like this : source → uridecode → mux → videoconv → osd → nvmsgconv → nvmsg broker
i want to get each frame with metadata from NVDSFrameMeta but i have some problems in nvmsgconv config file so how can i get frame (binarry or numpy or whatever) and NVDSFrameMeta to send with nvmsgbroker ! or should i say how nvmsgconv config file have to be to doing this ?
for the sake of clarity : if i can’t get one of them to send to kafka how can i get another one to send by kafka? or if i can get both how can i do that?
Thanks a Lot!.

3

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)

4

Deepstream 7
GPU T4
driver version : 525.183.01
trt : 8.6.1.6.1+cuda12.0
cuda : 12.2
how can i send frame by msgbroker with the pipeline that i sent earlier(send frame and deepstream meta
)

5
  1. about sending NVDSFrameMeta to broker, please refer to DeepStream ready-made sample deeptream-test4. when msg2p-newapi: 0, generate_event_msg_meta in osd_sink_pad_buffer_metadata_probe will add event message meta.
  2. about sending frame to broker, deeptream-test4 also supports sending the image to broker. please refer to “3.Send the image by the broker based on Kafka” in \opt\nvidia\deepstream\deepstream\sources\apps\sample_apps\deepstream-test4\README.
6

Thanks a lot

7

Sorry for the late reply, Is this still an DeepStream issue to support? Thanks!