Template

Version 11 (Gary Bradski, 2016-01-12 06:12 pm)

1 9 Gary Bradski
h2. 2013-XX-XX
2 1
3 1
_*Agenda*_
4 1
5 1
 * .
6 1
7 1
*_Minutes_*
8 1
9 1
 * . 
10 1
11 1
12 1
_*Vadim*_
13 1
<pre>
14 11 Gary Bradski
[OpenCV 2.4.4: Evgeny + Tegra team]
15 11 Gary Bradski
OpenCV 2.4.4 is out! Here is the announce: http://opencv.org/opencv-2-4-4-is-out.html
16 11 Gary Bradski
Big thanks to Tegra team, who took responsibility over the release process (and do that very well) and Evgeny who 
17 11 Gary Bradski
helped a lot, in parallel with the work on the text detection algorithm.
18 11 Gary Bradski
19 11 Gary Bradski
At the same time, the number of downloads from sf.net/projects/opencvlibrary exceeded 6,000,000!
20 11 Gary Bradski
21 11 Gary Bradski
2.4.5 will almost certainly be released around June 1st, i.e. ~the same time as 2.5.0 (if 2.5.0 is on time)
22 11 Gary Bradski
23 11 Gary Bradski
[OpenCV 2.5: Vadim]
24 11 Gary Bradski
Stereo correspondence classes in calib3d have been refactored. Now they have the same class StereoMatcher - the change 
25 11 Gary Bradski
requested by Adrian and several other people.
26 11 Gary Bradski
27 11 Gary Bradski
The whole module video has been refactored too: Meanshift, Camshift and motion templates have been rewritten in C++, 
28 11 Gary Bradski
background subtractor classes have been cleaned too to adhere OpenCV 2.5 principles.
29 11 Gary Bradski
30 11 Gary Bradski
The document "Towards OpenCV 2.5" has been written. This is initial todo list and discussion of the key things that 
31 11 Gary Bradski
should be done by 2.5.0. The basic idea is that we should do as much of necessary API changes by 2.5.0 as possible, 
32 11 Gary Bradski
since after that we can not break API for a very long time. Everything else, i.e. implementation-related things, can be 
33 11 Gary Bradski
done in 2.5.x. We already discussed a bit possible modifications in the base Algorithm class.
34 11 Gary Bradski
35 11 Gary Bradski
[Bilateral filter optimization: Ilya]
36 11 Gary Bradski
Ilya Lavrenov got back to his previous work - optimization of the bilateral filter. By optimizing the memory access 
37 11 Gary Bradski
pattern he managed to squeeze some more performance (~10% for floating-point images, ~20% for 8-bit images).
38 11 Gary Bradski
39 11 Gary Bradski
[Text detection: Evgeny]
40 11 Gary Bradski
I finally realized that it's not quite fair to call this a Matas algorithm, since the first author of the paper is his 
41 11 Gary Bradski
student Neumann. So, let's call it NM text detection algorithm. And this is how it's called in the code (more exactly 
42 11 Gary Bradski
ERFilterNM1, 1 is for the first stage).
43 11 Gary Bradski
Evgeny is finishing work on the 1st stage of the NM algorithm and will switch to another task next week. Convenient and 
44 11 Gary Bradski
flexible API has been developed. Basically, user supplies image an callback (the "classifier") that takes extremal 
45 11 Gary Bradski
region (ER) and returns probability - the measure of how good it is. On output the algorithm gives the list of survived 
46 11 Gary Bradski
extremal regions. Following the paper philosophy, each ER, regardless of its area and shape, takes O(1) space and O(1) 
47 11 Gary Bradski
time to process. The actual region mask can then be extracted using cv::floodfill or cv::threshold + cv::findContours 
48 11 Gary Bradski
functions.
49 11 Gary Bradski
50 11 Gary Bradski
[github statistics]
51 11 Gary Bradski
Over 35 pull requests have been closed during the last week.
52 6 Gary Bradski
</pre>
53 6 Gary Bradski
54 1
*_Action Items_*
55 1
56 1
*Gary*
57 1
58 1
 * . 
59 1
60 1
*Vincent*
61 1
62 1
 * . 
63 1
64 1
*Vadim*
65 1
66 1
 * . 
67 1
68 1
*Victor*
69 1
70 5 Gary Bradski
 * . 
71 1
72 1
_*From Last Time*_
73 1
74 1
*Gary*
75 1
76 1
 * . 
77 1
78 1
*Vincent*
79 1
80 1
 * . 
81 1
82 1
*Vadim*
83 1
84 1
 * . 
85 1
86 1
*Victor*
87 1
88 1
 * . 
89 2 Gary Bradski
90 2 Gary Bradski
<pre>
91 4 Gary Bradski
      <><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>
92 2 Gary Bradski
</pre>