How to get frame matrix from tiler_src_pad_buffer_probe (c deepstream_test3.c) after inference to use it with opencv

[873389267]

I want to modify deepstream_test3 to use my tracker , i need to get frame after detection to insert it into the tracker . my problem that i can’t get the frame in c or c++ codes.

How to get frame matrix from tiler_src_pad_buffer_probe (python deepstream_test3.app) after inference to use it with opencv

I want to modify deepstream_test3 to use my tracker , i need to get frame after detection to insert it into the tracker . my problem that i can’t get the frame . frame_meta = pyds.glist_get_nvds_frame_meta(l_frame.data) has only meta data like frame_num,source_id,batch_id,source_frame_width ,source_frame_height and num_obj_meta. i can’t find a documentation about getting frame using pyds after inference , please help me

this website solves the similar problem but it’s python / I cant find the same function
n_frame = pyds.get_nvds_buf_surface(hash(gst_buffer), frame_meta.batch_id)
in c codes.

[Rabeb]

Hi i remamber that Every python code (binding) has a smilair one on c++ , i tested before but i can t remember the link now

[bcao]

pelase refer GitHub - NVIDIA-AI-IOT/deepstream_python_apps: DeepStream SDK Python bindings and sample applications