-
Notifications
You must be signed in to change notification settings - Fork 5.9k
Add Fine Grained Saliency algorithm #122
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
|
@bhack |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
sorry, we disallow the use of IplImage in the newly added code; please, use C++ Mat instead.
4019794 to
7249ab0
Compare
|
@vpisarev I updated the code, now the algorithm uses the new C++ interface. |
|
Hi @samontab, I have developed this module for the Google Summer of Code 2014 and I'm glad you want to contribute. Please note the comments on the code and remove the cv:: inside saliencySpecializedClasses.hpp |
|
Hi @fpuja As you suggested, I removed the extra cv:: in those files, and also removed the include by using COLOR_BGR2GRAY instead of CV_BGR2GRAY. |
|
Squashed last commit to keep a clean log. |
|
@vpisarev any reason why we are not including stuff like this? It passes all builds and has been standing around for ages :) |
|
@samontab that's the status of PR? Could you rebase the latest master into your branch? |
|
Replaced by #821 |
Since now there is a saliency module, I would like to add an implementation of fine grained saliency, which fits nicely in the static section of the module.
Fine grained saliency is based on algorithms described in:
Montabone, Sebastian and Soto, Alvaro. "Human Detection Using a Mobile Platform and Novel Features Derived from a Visual Saliency Mechanism." Image and Vision Computing, 2010.
This pull request implements the staticSaliencyFineGrained class, so that a new saliency algorithm FINE_GRAINED is available. The code was originally released at http://www.samontab.com/web/saliency
You can see an example of it here:
