Hi,
I am trying to use fastcv decriptors for object recognition.
According to my experiments, the 36 bytes descriptor seems to be a 3x3 oriented matrix of 4 bytes.
What is the best way to make the 36 bytes descriptor robust against scaling and rotation, like SIFT descriptors?
Cyril
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
Hey ciryl, could you share the code you used to create the 17x17 patch and the descriptors?
I'm also trying to use fastcv for object recognition (see the post below yours).
Thank you! :)
Sincerly, Steve.