On Sunday, May 22, 2022, Andrea paz <gamberucci.andrea@gmail.com> wrote:
Some time ago I had contacted the SURF developer (Herbert Bay); I
report the email exchange:
Andrea paz
"I would like to ask for clarification about the implementation of
SURF: Speeded Up Robust Features in the FindObj plugin of OpenCV,
which is used in the open source NLE software Cinelerra-GG.
(https://www.cinelerra-gg.org/).
Like all NLE programs, it can be used in an amateur way, but also to
produce videos for commercial use. The doubt is about SURF license: is
it possible to use OpenCV FindObj in Cinelerra-GG? For now an old
version is implemented from which SURF has been excluded; but I was
wondering if it is possible to use more updated versions that include
SURF."
Answer (Herbert Bay)
"Sorry, don't know. That's too long time ago and I personally didn't
implement SURF in Open CV. Here's the original source code:
https://github.com/herbertbay/SURF"
License in github:
LICENSE CONDITIONS
Copyright (2006): ETH Zurich, Switzerland
Katholieke Universiteit Leuven, Belgium
All rights reserved.
For details, see the paper:
Herbert Bay, Tinne Tuytelaars, Luc Van Gool,
"SURF: Speeded Up Robust Features"
Proceedings of the ninth European Conference on Computer Vision, May 2006
Permission to use, copy, modify, and distribute this software and
its documentation for educational, research, and non-commercial
purposes, without fee and without a signed licensing agreement, is
hereby granted, provided that the above copyright notice and this
paragraph appear in all copies modifications, and distributions.
Any commercial use or any redistribution of this software
requires a license from one of the above mentioned establishments.
For further details, contact Herbert Bay (herbert.bay@gmail.com).
In my opinion, if the direct supervisor is not interested, it means
that he gives the green light for its use in CinGG.
In your opinion, is it better not to risk it?
I do not know..
there seems to be patent at least in skme countries involving Toyota (?), and it valid until 2029...
Robust interest point detector and descriptor
Abstract
Methods and apparatus for operating on images are described, in particular methods and apparatus for interest point detection and/or description working under different scales and with different rotations, e.g. for scale-invariant and rotation-invariant interest point detection and/or description. The present invention can provide improved or alternative apparatus and methods for matching interest points either in the same image or in a different image. The present invention can provide alternative or improved software for implementing any of the methods of the invention. The present invention can provide alternative or improved data structures created by multiple filtering operations to generate a plurality of filtered images as well as data structures for storing the filtered images themselves, e.g. as stored in memory or transmitted through a network. The present invention can provide alternative or improved data structures including descriptors of interest points in images, e.g. as stored in memory or transmitted through a network as well as datastructures associating such descriptors with an original copy of the image or an image derived therefrom, e.g. a thumbnail image.
Classifications
G06V10/446 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering using Haar-like filters, e.g. using integral image techniques
View 5 more classifications
US20090238460A1
United States
Download PDF Find Prior Art Similar
InventorRyuji FunayamaHiromichi YanagiharaLuc Van GoolTinne TuytelaarsHerbert BayCurrent Assignee KU Leuven Research and Development Eidgenoessische Technische Hochschule Zurich ETHZ Toyota Motor Corp
Worldwide applications
2006 EP AT DE 2007 KR EP US WO AU KR JP 2012 US
Application US12/298,879 events
2006-04-28
Priority to EP06447060A
2007-04-30
Application filed by Toyota Motor Europe NV SA, KU Leuven Research and Development, Eidgenoessische Technische Hochschule Zurich ETHZ
2009-09-24
Publication of US20090238460A1
2012-04-24
Application granted
2012-04-24
Publication of US8165401B2
Status
Active
2029-04-13
Adjusted expiration
===
FIG. 10 shows a comparison of experimental results between a method according to the present invention and known methods. “SURF” refers to application of the present invention. SURF 37 refers to the number of dimensions of the descriptor used, i.e. 37, and similarly for SURF 65 and 129.
===
If I understand correctly similar patent concerns also apply to x264/x265 ... should we disable them in binary (appimage) distribution of CinGG?