Crop a part(section) of primary gie inference and pass to the secondary gie

Please provide complete information as applicable to your setup.

**• Hardware Platform :GPU
±----------------------------------------------------------------------------+
| NVIDIA-SMI 525.125.06 Driver Version: 525.125.06 CUDA Version: 12.0 |
|-------------------------------±---------------------±---------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce … Off | 00000000:01:00.0 Off | N/A |
| N/A 38C P3 N/A / 40W | 6MiB / 6144MiB | 0% Default |
| | | N/A |
±------------------------------±---------------------±---------------------+

±----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 2485 G /usr/lib/xorg/Xorg 4MiB |
±----------------------------------------------------------------------------+
• DeepStream Version
Deepstream 6.2

I would like to explain our problem and get the possible directions to solve this. The primary gie inference bounding box is by default passed in to the secondary gie. Our requirement is we want to crop the horizontal bottom half of the primary inference(bounding coordinates from the primary gie ) and pass to the secondary gie. Please let me known which plugin are responsible and where I could possibly add my custom logic to crop the primary inference and pass to secondary inference. Is there a way to visualize the cropped region in the inference data.

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

You can refer to the videotemplate plugin: gst-nvdsvideotemplate
This is a demo to use the plugin to process the images: nvocdrlib_impl.cpp

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