• Hardware Platform (Jetson / GPU)
Jetson Orin
• DeepStream Version
6.1.1
• JetPack Version (valid for Jetson only)
5.0.2
• TensorRT Version
8.4.1-1+cuda11.4
I need to send cropped detections from my python Deesptream app through Kafka. I read in the documentation that:
To handle custom object types, you must modify the payload generator library
nvmsgconv.cpp. See deepstream-test4 for details about adding custom objects as
NVDS_EVENT_MSG_META user metadata with buffers for generating a custom payload to send
to back end.
from: Gst-nvmsgconv — DeepStream 6.1.1 Release documentation
However, deepstream-test4 only shows the implementation of existing objects NVDS_OBJECT_TYPE_VEHICLE
and NVDS_OBJECT_TYPE_PERSON
, and the documentation just gives a brief explanation of how to achieve this. Also, I don’t underestand how modify nvmsgconv.cpp to achieve this.
How can I send the detections over Kafka? What are the exact steps to follow?