Send bounding boxes to RabbitAMQP

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) : GTX1080TI
• DeepStream Version: 5.0
• TensorRT Version : 7.0
• NVIDIA GPU Driver Version (valid for GPU only) : 440.33
• Issue Type( questions, new requirements, bugs) : Question

Hi
I am working with python binding in the sample 4 (deepstream_test_4) but it only sends the metadata of the first object that find each 30 frames to cloud. I would like to send all the metadata found in that frame, not only one. I tried changing some code lines in the function generate_event_msg_meta but I dont really know how exactly.

Can you suggest me how to do it? thanks in advance.

3

Hi leo2105,

To send all object meta for the frame, remove the filter for first object. On this line:

`if(is_first_object and not (frame_number%30)):`

Change it to

`if(not (frame_number%30)):`
4

Yeah, but It will send one bounding per message, but I want to do I kind of list and send all the bboxes per frame in only one message.
Another question, I want to send input frames inside the message to Rabbit. Because I need to save some frames in cloud. Do you know if deepstream can do it?
thanks in advance.

7

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

Can you give more details, why you need all the bounding boxes in the form of a list and in a single message? Is there any analytics/processing done on these messages in the cloud?