This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA4VM: How to Extract Pixel Coordinates and Visualize Features from DKAZE in Visual Localization?

Part Number: TDA4VM


Tool/software:

Hello!

We would like to use the deep kaze feature extractor from the Visual Localization example. www.ti.com/.../spracx1a.pdf

Currently, we are able to run DKAZE, but we need the pixel coordinates of the features it finds. How can we obtain these from the output tensor? Is there a way to even draw these features on the image?

Thanks in advance for the help,

Best regards, Pali