Deep feature tracking in Deepstream

[ismael.ghouddana]

Dear Nvidia Team,

I need to apply a deep feature tracking using the output from Deepstream. I would like to get the cropped image from the target.

Can I have the numpy array corresponding to this image using the NvDsTracker? If it is the case, is there any example of how to use this API?

Thanks

[iyaqoobi]

hi ismaeel, you can extract detected object using gstdsexample.

https://devtalk.nvidia.com/default/topic/1061422/deepstream-sdk/how-to-crop-the-image-and-save/post/5375174/#5375174

[kayccc]

hi ismaeel, you can extract detected object using gstdsexample.

https://devtalk.nvidia.com/default/topic/1061422/deepstream-sdk/how-to-crop-the-image-and-save/post/5375174/#5375174

Hi iyaqoobi,

Thanks for your sharing and contribution.

[iyaqoobi]

@kayccc

Hi iyaqoobi,

Thanks for your sharing and contribution.

you are welcome.

[jinmochong]

Is there any way to do this using Python?