Imx8mp verdin face blur using opencv

Hi, I’m the Toradex AI Assistant.

I might make mistakes or occasionally get you wrong. Our support team will step in if needed.


OpenCV Face Recognition/Blur on Verdin iMX8M Plus

I’d be glad to help! Could you let me know which OS and version you are using?

To guide you properly with your OpenCV face recognition/blur implementation and troubleshoot the pipeline and frame start errors, I need to understand your setup better. You can use the tdx-info command to get detailed information about your system - more details available at this link.

Available OpenCV Resources

For Torizon OS

Toradex provides a comprehensive OpenCV sample for computer vision applications(1). The sample demonstrates how to use OpenCV with Python on arm64v8 based SoMs like the Verdin iMX8M Plus(1).

You can quickly test the sample without building by running(1):

# wget https://github.com/toradex/torizon-samples/raw/bookworm/opencv/docker-compose.yaml  
# docker-compose -f docker-compose.yaml up  

(1)

For Yocto BSP

OpenCV is also available for Yocto-based images(2). The documentation includes a face detection example using Haar Cascade classifiers(2).

Troubleshooting Pipeline and Frame Errors

Based on the community discussions, pipeline errors and frame start issues on Verdin iMX8M Plus can be related to:

  1. Video device resource management - Multiple open/close cycles can cause video devices to lock(3)
  2. CSI interface timing issues - Some modules may experience inconsistent behavior with camera interfaces(4)
  3. Power management - Chips may enter low power mode unexpectedly(4)

Once you provide your OS version and setup details, I can give you more specific guidance for implementing face recognition/blur and resolving your pipeline errors.

Best regards, Toradex AI Assistant.


Did you like my answer? :+1: :-1:

If I answered your question, please tick the “Solution” checkbox.

For follow-up questions to me, please use @ToradexAI in your post.

1 Like