Crop Image with Nvanalytics Labelling and Nvosd Labelling

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Hi, I am asking is it possible to crop the frames out, with the Nvanalytics Labelling (ROI, Line, Direction) & Nvosd detection labelling?

n_frame = pyds.get_nvds_buf_surface(hash(gst_buffer), frame_meta.batch_id)
frame_copy = np.array(n_frame, copy=True, order='C')
frame_copy = cv2.cvtColor(frame_copy, cv2.COLOR_RGBA2BGRA)

My current pipeline can crop images, but without any labelling, I need the Nvanalytics & NvOsd labelling.

3

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)

• DeepStream Version

• JetPack Version (valid for Jetson only)

• TensorRT Version

• NVIDIA GPU Driver Version (valid for GPU only)

• Issue Type( questions, new requirements, bugs)

• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

4

My pipeline is working fine, just to ask is there any workaround to crop with Nvanalytics & Nvosd output together using the code above

5
  1. which sample are you testing or referring to? do you mean On the video there is only osd detection labels, but no Nvanalytics Labelling?
  2. nvosd draws all labels on the video. you can set “osd-mode=2” in the configuration file of nvanalytic pulugin for drawing Nvanalytics Labelling (ROI, Line, Direction) with osd. then you can move the code above to the probe function which is added on osd src or after osd.
6

I have my own pipeline. It is working.
Yes, when i put display sink, the Nvanalytics and Nvosd labelling is drawn on my screen. Is just I would like to take a screenshot of some certain detection using code below

n_frame = pyds.get_nvds_buf_surface(hash(gst_buffer), frame_meta.batch_id)
frame_copy = np.array(n_frame, copy=True, order='C')
frame_copy = cv2.cvtColor(frame_copy, cv2.COLOR_RGBA2BGRA)

How can i attach the labelling into the buffer so that my screenshot will include the Nvanalytics & Nvosd labelling as well, instead of just a raw image of my video. Currently the probe function is looped on tiler’s pad.

7

As written in my last comment, you can move the code above to the probe function which is added on osd src or after osd because all labels are drawn by osd not tiler.

8

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.

9

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