I want to use Detection model as an SGIE . My PGIE is also a Detection model

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hardware Platform (Tesla T4 16 GB)**
DeepStream Version 7.1
TensorRT Version 10.7.0.23-1+cuda12.6
NVIDIA GPU Driver Version 550.127.05

i’m using Detection model as a PGIE and also Using 2nd Detection model as a SGIE. Now if i’m trying to extract the Object wise metadata using
l_obj = frame_meta.obj_meta_list
while l_obj:
obj_meta = pyds.NvDsObjectMeta.cast(l_obj.data)
object_id = obj_meta.object_id
class_name = obj_meta.obj_label
this method , then its giving me a metadata for both detection models. Can anyone help me in this?
Thanks in advance.

3

We have similar sample in C/C++ back_to_back_detectors.c. You can distinguish that by the following parameters: obj_meta->unique_component_id.

4

okay its working ! Thanks for helping :)

5

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