Save the picture data of the first few frames of the tracking object

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson)
**• DeepStream Version6.x
• JetPack Version (4.6
**• TensorRT Version8.x
Hello:
I successfully ran example deepstream-test2 and enabled the tracker.According to the code, I can get the position coordinates of the tracking object in the past period of time, but I don’t know how to use the position coordinates to save the corresponding picture data.

You can refer to thedeepstream-imagedata-multistream-redaction.

Sorry, I’ve seen the source code of the example you gave. I can only save the picture data at the current time. What I want to save is the picture information of the first few frames after the tracking target disappears from the visual area

What do you mean by

If it’s a certain area, maybe you can usenvanalytics.

And I didn’t get your point. If you want to save the frames once one tracked object disappears, just add a simple logic? For example, you can get all tracked id in one frame, compare them with previous.

I want to keep the historical frame after the tracking object disappears

Ok, that’s a question. Sorry I don’t know either.

There is no place to store the previous frames. Yo may need to store and crop the historical frames in your app.

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

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.