Power limitations while using gstreamer

Hi,

I am using the following GStreamer pipeline:

gst-launch-1.0 zedsrc camera-resolution=3 camera-fps=30 stream-type=0 od-enabled=true od-detection-model=1 ! queue max-size-buffers=32 max-size-time=0 ! zedodoverlay ! queue max-size-buffers=32 max-size-time=0 ! autovideoconvert ! fpsdisplaysink sync=false

Setup Details:

Device: Jetson AGX Orin

JetPack Version: 6

ZED SDK Version: 4.2

GStreamer Version: 1.20

Power mode : MAXn

Observations:

  1. Without object detection enabled, the pipeline achieves 30 FPS. However, enabling object detection reduces the FPS to 15

  2. If sync=true is set:

The current FPS drops to 2.

  1. If sync=false is used:

The current FPS is capped at 15, with dropped frames = 0, despite setting camera-fps=30.

  1. Once I did this and current fps acheived with average 21 :

“Sudo nvpmodel -m 0
Sudo jetson_clocks”

  1. While object detection is true , with/without zedoverlay I got same result

if i put paper on front of cam lens the fps being 29 , if there is objects the fps mainly 21

I shared this with stereolabs community and told me the problem with processing power limitations!!

Please check my case in detail, and assist me to detect the problem and solve it.

Is there anyone can help ???

Hello,

Thanks for visiting the NVIDIA Developer forums! Your topic will be best served in the Jetson category.

I will move this post over for visibility.

Cheers,
Tom

Thank u!

1 Like

Kindly, help in this !!!

I asked from 5 days and there is no any response from ur side !!!

Kindly assust, @TomNVIDIA

This has been assigned to a Jetson engineer. Let me remind them about this topic.

Thanks,
Tom

Hi,
The gstreamer plugins zedsrc and zedodoverlay are from 3rdparty. Would suggest check with the vendor for the performance issue.

For running deep learning inference, we have DeepStream SDK:

NVIDIA Metropolis - NVIDIA Docs

You may consider try it and then develop your use-case based on it.