openvino multiple source

[Nexn]

Hello,

Could I know is it possible to capture the multiple live streams and run the different inference on the each soure (each streams) in open vino?

Thanks and regards,

Nexn.

[Aznie_Intel]

Hi Nexn,

Thanks for reaching out. It is possible with the DL Streamer multi-stream pipeline, which contains multiple sub-pipelines, each processing one source. You may check these Video streams from multiple cameras.

I hope this helps you.

Regards,

Aznie

[Nexn]

Hi Aznie,

Thanks for your response.

I need to run individual inference in all my multiple live rtsp streams. 

In the (source 1) first stream , I want to detect persons only . In the (source 2) second stream, I want to detect other some sort of things rather than persons.

Is that possible in openvino?

Best regards,

Nexn.

[Aznie_Intel]

Hi Nexn,

Yes, you can perform multi-input and multi-object detection. However, the performance might drop significantly and might not work if too much input video is supplied. The Multi Camera Multi Target Python* Demo is a demo from Open Model Zoo that might suit your objective.

Regards,

Aznie

[Nexn]

Hi Aznie,

I will try.

Thanks and regards,

Nexn.

[Aznie_Intel]

Hi Nexn,

This thread will no longer be monitored since we have provided information. If you need any additional information from Intel, please submit a new question.

Regards,

Aznie