Object id changing problem

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson Nano
• DeepStream Version 5.1
• JetPack Version (valid for Jetson only) 4.5.1
• TensorRT Version 7.1.3+cuda10.2
• Issue Type( questions, new requirements, bugs) Question

Hi ,

How is track_id changing here ?

                track_id = obj_meta.object_id
                now = time.time()
                if flag==0 and track_id != last_track_id:
                    print(str(track_id) + ' -- ' + str(last_track_id))
                    last_track_id = track_id
                    print('Photo')
                    takenow = time.time()
                    flag = 1
                    TAKE_PHOTO = True
                if now>takenow+5:
                    print('Reset')
                    flag = 0

This is the output

1 -- 0
Photo
Reset
18446744073709551615 -- 1
Photo
Reset
Reset
1 -- 18446744073709551615
Photo

Already asked here but I think it needs new topic

3

Sorry, which tracker are you using and what are you trying to do?

4

I am using same tracker in deepstream-test2 and I am trying to have same object id so I don’t take multiple photo for same object.

Thanks

5

I’m really sorry, could explain a little more, I still didn’t get what you are trying to do

6

Documentation says object_id is ‘Unique ID for tracking the object.’

In first line I got that id

track_id = obj_meta.object_id

Now track_id is equal to 1 and prints > 1 – 0

last_track_id = track_id

Now last_track_id is also equals to 1.

In second frame I am expect it to not pass first if because track_id and last_track_id should be equal.

But actual output is 18446744073709551615 – 1

Thanks

7

Hey @htopcu , does this topic still need to be supported?

8

Hi @bcao,

I decided not to use obj_meta.object_id because I can’t find out why id changes to 18446744073709551615 from 1.

Thank you.

9

Got it, thanks for the respond