Please provide complete information as applicable to your setup.
**• Hardware Platform (Jetson / GPU)**GPU docker
• DeepStream Version5.x/6.0
• TensorRT Version7.0/8.0
**• NVIDIA GPU Driver Version (valid for GPU only)**440.33/440.33
**• Issue Type( questions, new requirements, bugs)**bugs
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) deepstream_lpr_app
The attribute information of the vehicle corresponding to the license plate can be obtained from the obj_meta->parent structure
In deepstream-5.x, obj_meta->parent is not empty (!=NULL)
In deepstream-6.0, obj_meta->parent is empty (=NULL)
Why is this the case? How to solve it?
I tried this guy’s method with the probes in different positions and the result is the same.
Can you try to probe in the src pad of SGIE?
Thank you very much and wish you a happy life. I try to probe in the src pad of secondary_classifier. obj_meta->parent is not empty (!=NULL)
Glad to know it fixed your issue. Thanks.
Excuse me again below. Why in DS5 version and DS6 version, the probe must be placed in different positions to obtain license plate attribute data?
what is your mean of different positions?
For example, in the DS5 version, after placing the probe in the sink of nvosd, the attribute data of the license plate can be obtained. But in DS6 version, same operation, obj_meta->parent is empty (=NULL). So I can only put the probe in the src pad of secondary_classifier, obj_meta->parent is not empty (!=NULL). why?
Please create new topic for new questions.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.