Inference video in a specific area

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GeForce GTX 1050Ti
• DeepStream Version 5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version 7.0
• NVIDIA GPU Driver Version (valid for GPU only) 440.100

Hi,
We want DS inference a specific area instead of the whole video, we can custom some parameters(e.g. x, y, w, h) and DS can only inference such area. We wonder how to meed our needs.

3

please refer to Run sqie if necessary

4

Hi, we found the roi-top-offset and roi-bottom-offset value in the configure file. But the two parameters only changed the top and bottom area, how about left and right?

6

Hi @yohoohhh,
This is not supported right now.
We will add its support in roadmap.

7

OK. Looking forward to the update.