2019-09-17 08:32:24 -0600 | received badge | ● Popular Question (source) |
2016-03-07 08:36:42 -0600 | received badge | ● Taxonomist |
2015-09-10 08:32:05 -0600 | received badge | ● Good Question (source) |
2014-10-28 13:39:50 -0600 | received badge | ● Nice Answer (source) |
2013-03-12 04:33:44 -0600 | commented answer | FREAK compute() speed up And could also be that every time I call freak-> compute(image, keyp, desc); internally buildpattern() is called? Is it possible to use the same pattern always if the image size doesn't varies, I guess. Maybe by modifying that... |
2013-03-12 03:37:51 -0600 | commented answer | FREAK compute() speed up Nice!, thanks, many good ideas, lets see what can I do. |
2013-02-06 08:56:14 -0600 | asked a question | FREAK compute() speed up Is it possible to reduce FREAK extraction time below 70ms? I am using FAST in pyramids for detection and it takes 1ms to detect. FREAK extraction never takes less than 70 ms. I tried to reduce points passed to the algorithm but never gets below that time, so it is not point-dependent. I am just doing one and then call the method, so it is not a constructor problem I guess. Maybe is something that FREAK does always when you call compute and it is slowing down all the process. Is there any way of calling the extractor in a static way, like with FAST? |
2013-02-06 08:53:34 -0600 | received badge | ● Necromancer (source) |
2013-02-06 05:57:27 -0600 | answered a question | Why is FREAK so slow? In my application The times are more or less like this in the PC: FREAK is still slower than I expected even if I only create the object once. It doesn't change that much for android as I use native JNI libraries. I think if you are getting times of 6 seconds for detection you may have a LOT of things wrong. Check all memory leaks, size of of frames you are processing, check that you create objects once (detector, extractor, matcher). Put timers just for the process of freak extraction to see the real time. |
2012-12-20 09:53:35 -0600 | asked a question | FREAKs patternScale parameter tuning For rotated and scale dimages I just achieve good matching results using FREAK when adjusting the patternScale parameter and downsampled the traingin image like this: Which is the relation of the patternScale parameter and the size of the training image? Is there a way to tune it for all cases of rotations and scalings? |
2012-12-17 13:30:36 -0600 | commented question | FREAK descriptor: scaleNormalized parameter I have the same problem as you and I am ging to mail the author of the codes to see if I can learn more. I have been playing with different scales of the training image (with cv::pyrDown(source, dest)) and the scaleNormalized parameter. I think it is very sensitive and dependent on the training image, its size and the number of keypoints. |
2012-11-29 02:01:56 -0600 | received badge | ● Nice Answer (source) |
2012-11-05 15:47:33 -0600 | received badge | ● Good Answer (source) |
2012-09-26 06:46:58 -0600 | received badge | ● Good Answer (source) |
2012-09-20 16:18:10 -0600 | received badge | ● Nice Answer (source) |
2012-09-20 08:06:13 -0600 | received badge | ● Good Question (source) |
2012-09-20 06:27:24 -0600 | received badge | ● Nice Question (source) |
2012-09-20 06:24:01 -0600 | received badge | ● Famous Question (source) |
2012-09-20 05:06:55 -0600 | received badge | ● Notable Question (source) |
2012-09-20 04:55:39 -0600 | received badge | ● Popular Question (source) |
2012-09-20 03:29:52 -0600 | received badge | ● Nice Question (source) |
2012-09-20 03:04:05 -0600 | commented answer | object detection using SURF & FLANN BFMatcher is also the matcher to use with new FREAK descriptor, using NORM_HAMMING as type because it is a binary descriptor. |
2012-09-20 01:57:49 -0600 | received badge | ● Civic Duty (source) |
2012-09-20 01:54:25 -0600 | received badge | ● Organizer (source) |
2012-09-20 01:10:48 -0600 | received badge | ● Nice Answer (source) |
2012-09-19 06:45:21 -0600 | received badge | ● Critic (source) |
2012-09-18 10:39:28 -0600 | received badge | ● Necromancer (source) |
2012-09-18 10:22:41 -0600 | answered a question | Does FREAK eat keypoints when it can't find any descriptors? I came across with this comment in the Pay attention to the line after |
2012-09-18 08:58:08 -0600 | received badge | ● Necromancer (source) |
2012-09-18 08:46:00 -0600 | answered a question | How to handle inappropriate editing habits? I think that "flagging as duplicate/low quality" is needed as an extra to "flag offensive" in order to call moderators attention. Maybe it is not necessary to copy all the tools from SO as this site is still small, but I am missing this tool right now. The flag duplicate will make possible to remove questions on the same topic and make it easier the search for users. As a coment, IMHO, I think that it wouldn't be a good idea to copy the policy of SO regarding theoretical questions or tutorial-like questions with no codes (where they usually close them), as this OpenCV sometimes requires kind of tutorials or suggestions/discussions. OpenCV is not only programing related, is also researching, thats why I think discussions/suggestions should be admited (following the Q&A format, always argumented). |
2012-09-18 05:29:01 -0600 | asked a question | Clarifying FREAK: Fast Retina Keypoint descriptor I have been reading information about FREAK descriptor and I understand it is a binary descriptor that claims to be more robust than previous descriptors. Reading the publication I noticed that they use a scale-space FAST (that works in pyramids with the image scale) detector for evaluation of FREAK. That means that they detect keypoints with FAST and then compute descriptors with FREAK. QUESTION I don't understand then which is the aim of the OpenCV function Is this supossed to be a kind of detector for FREAK? Which are the input/output parameters of the function? |
2012-09-18 05:08:45 -0600 | received badge | ● Necromancer (source) |
2012-09-18 05:06:35 -0600 | answered a question | Is FREAK scale and rotation invariant? SURF is a detector like FAST. FREAK is a descriptor extractor. It has more sense to compare it with SIFT. Actually, in the paper they say they use FREAK descriptors together with a pyramidal FAST detector that is called AGAST. So answering your question:
|
2012-09-18 01:11:11 -0600 | answered a question | How do I install OpenCV with IPP and TBB? There is a cool video that if you pay attention to every step there is no chance to get lost. The key is to download the TBB package to a folder (in the video is called "dep"), and when you click configure in CMake the route will be I think this video tutorial is what you need, there is no chance to fail. |
2012-09-17 12:18:12 -0600 | received badge | ● Nice Answer (source) |
2012-09-17 12:17:33 -0600 | received badge | ● Student (source) |
2012-09-17 12:16:33 -0600 | marked best answer | Replacing SIFT by FREAK I have an application using FAST detector and SIFT descriptors. I want to try the new FREAK descriptor.
|
2012-09-17 12:15:51 -0600 | received badge | ● Teacher (source) |