generic-library/opencv
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Doxygen tutorials: cpp done

Browse Source
This commit is contained in:
Maksim Shabunin
2014-11-28 16:21:28 +03:00
parent c5536534d8
commit 36a04ef8de
92 changed files with 2142 additions and 3691 deletions
Download Patch File Download Diff File Expand all files Collapse all files

140
doc/tutorials/features2d/akaze_matching/akaze_matching.markdown
View File

@@ -4,10 +4,10 @@ AKAZE local features matching {#tutorial_akaze_matching}
Introduction
------------
In this tutorial we will learn how to use [AKAZE]_ local features to detect and match keypoints on
In this tutorial we will learn how to use AKAZE @cite ANB13 local features to detect and match keypoints on
two images.
We will find keypoints on a pair of images with given homography matrix, match them and count the
number of inliers (i. e. matches that fit in the given homography).
You can find expanded version of this example here:
@@ -18,7 +18,7 @@ Data
We are going to use images 1 and 3 from *Graffity* sequence of Oxford dataset.
![image](images/graf.png)
![](images/graf.png)
Homography is given by a 3 by 3 matrix:
@code{.none}
@@ -35,92 +35,92 @@ You can find the images (*graf1.png*, *graf3.png*) and homography (*H1to3p.xml*)
### Explanation
1. **Load images and homography**
@code{.cpp}
Mat img1 = imread("graf1.png", IMREAD_GRAYSCALE);
Mat img2 = imread("graf3.png", IMREAD_GRAYSCALE);
-# **Load images and homography**
@code{.cpp}
Mat img1 = imread("graf1.png", IMREAD_GRAYSCALE);
Mat img2 = imread("graf3.png", IMREAD_GRAYSCALE);
Mat homography;
FileStorage fs("H1to3p.xml", FileStorage::READ);
fs.getFirstTopLevelNode() >> homography;
@endcode
We are loading grayscale images here. Homography is stored in the xml created with FileStorage.
Mat homography;
FileStorage fs("H1to3p.xml", FileStorage::READ);
fs.getFirstTopLevelNode() >> homography;
@endcode
We are loading grayscale images here. Homography is stored in the xml created with FileStorage.
1. **Detect keypoints and compute descriptors using AKAZE**
@code{.cpp}
vector<KeyPoint> kpts1, kpts2;
Mat desc1, desc2;
-# **Detect keypoints and compute descriptors using AKAZE**
@code{.cpp}
vector<KeyPoint> kpts1, kpts2;
Mat desc1, desc2;
AKAZE akaze;
akaze(img1, noArray(), kpts1, desc1);
akaze(img2, noArray(), kpts2, desc2);
@endcode
We create AKAZE object and use it's *operator()* functionality. Since we don't need the *mask*
parameter, *noArray()* is used.
AKAZE akaze;
akaze(img1, noArray(), kpts1, desc1);
akaze(img2, noArray(), kpts2, desc2);
@endcode
We create AKAZE object and use it's *operator()* functionality. Since we don't need the *mask*
parameter, *noArray()* is used.
1. **Use brute-force matcher to find 2-nn matches**
@code{.cpp}
BFMatcher matcher(NORM_HAMMING);
vector< vector<DMatch> > nn_matches;
matcher.knnMatch(desc1, desc2, nn_matches, 2);
@endcode
We use Hamming distance, because AKAZE uses binary descriptor by default.
-# **Use brute-force matcher to find 2-nn matches**
@code{.cpp}
BFMatcher matcher(NORM_HAMMING);
vector< vector<DMatch> > nn_matches;
matcher.knnMatch(desc1, desc2, nn_matches, 2);
@endcode
We use Hamming distance, because AKAZE uses binary descriptor by default.
1. **Use 2-nn matches to find correct keypoint matches**
@code{.cpp}
for(size_t i = 0; i < nn_matches.size(); i++) {
DMatch first = nn_matches[i][0];
float dist1 = nn_matches[i][0].distance;
float dist2 = nn_matches[i][1].distance;
-# **Use 2-nn matches to find correct keypoint matches**
@code{.cpp}
for(size_t i = 0; i < nn_matches.size(); i++) {
DMatch first = nn_matches[i][0];
float dist1 = nn_matches[i][0].distance;
float dist2 = nn_matches[i][1].distance;
if(dist1 < nn_match_ratio * dist2) {
matched1.push_back(kpts1[first.queryIdx]);
matched2.push_back(kpts2[first.trainIdx]);
if(dist1 < nn_match_ratio * dist2) {
matched1.push_back(kpts1[first.queryIdx]);
matched2.push_back(kpts2[first.trainIdx]);
}
}
}
@endcode
If the closest match is *ratio* closer than the second closest one, then the match is correct.
@endcode
If the closest match is *ratio* closer than the second closest one, then the match is correct.
1. **Check if our matches fit in the homography model**
@code{.cpp}
for(int i = 0; i < matched1.size(); i++) {
Mat col = Mat::ones(3, 1, CV_64F);
col.at<double>(0) = matched1[i].pt.x;
col.at<double>(1) = matched1[i].pt.y;
-# **Check if our matches fit in the homography model**
@code{.cpp}
for(int i = 0; i < matched1.size(); i++) {
Mat col = Mat::ones(3, 1, CV_64F);
col.at<double>(0) = matched1[i].pt.x;
col.at<double>(1) = matched1[i].pt.y;
col = homography * col;
col /= col.at<double>(2);
float dist = sqrt( pow(col.at<double>(0) - matched2[i].pt.x, 2) +
pow(col.at<double>(1) - matched2[i].pt.y, 2));
col = homography * col;
col /= col.at<double>(2);
float dist = sqrt( pow(col.at<double>(0) - matched2[i].pt.x, 2) +
pow(col.at<double>(1) - matched2[i].pt.y, 2));
if(dist < inlier_threshold) {
int new_i = inliers1.size();
inliers1.push_back(matched1[i]);
inliers2.push_back(matched2[i]);
good_matches.push_back(DMatch(new_i, new_i, 0));
if(dist < inlier_threshold) {
int new_i = inliers1.size();
inliers1.push_back(matched1[i]);
inliers2.push_back(matched2[i]);
good_matches.push_back(DMatch(new_i, new_i, 0));
}
}
}
@endcode
If the distance from first keypoint's projection to the second keypoint is less than threshold,
then it it fits in the homography.
@endcode
If the distance from first keypoint's projection to the second keypoint is less than threshold,
then it it fits in the homography.
We create a new set of matches for the inliers, because it is required by the drawing function.
We create a new set of matches for the inliers, because it is required by the drawing function.
1. **Output results**
@code{.cpp}
Mat res;
drawMatches(img1, inliers1, img2, inliers2, good_matches, res);
imwrite("res.png", res);
...
@endcode
Here we save the resulting image and print some statistics.
-# **Output results**
@code{.cpp}
Mat res;
drawMatches(img1, inliers1, img2, inliers2, good_matches, res);
imwrite("res.png", res);
...
@endcode
Here we save the resulting image and print some statistics.
### Results
Found matches
-------------
![image](images/res.png)
![](images/res.png)
A-KAZE Matching Results
-----------------------

11
doc/tutorials/features2d/akaze_matching/akaze_matching.rst
View File

@@ -152,8 +152,9 @@ A-KAZE Matching Results
--------------------------
.. code-block:: none
Keypoints 1: 2943
Keypoints 2: 3511
Matches: 447
Inliers: 308
Inlier Ratio: 0.689038
Keypoints 1 2943
Keypoints 2 3511
Matches 447
Inliers 308
Inlier Ratio 0.689038

124
doc/tutorials/features2d/akaze_tracking/akaze_tracking.markdown
View File

@@ -11,16 +11,17 @@ The algorithm is as follows:
- Detect and describe keypoints on the first frame, manually set object boundaries
- For every next frame:
1. Detect and describe keypoints
2. Match them using bruteforce matcher
3. Estimate homography transformation using RANSAC
4. Filter inliers from all the matches
5. Apply homography transformation to the bounding box to find the object
6. Draw bounding box and inliers, compute inlier ratio as evaluation metric
-# Detect and describe keypoints
-# Match them using bruteforce matcher
-# Estimate homography transformation using RANSAC
-# Filter inliers from all the matches
-# Apply homography transformation to the bounding box to find the object
-# Draw bounding box and inliers, compute inlier ratio as evaluation metric
![image](images/frame.png)
![](images/frame.png)
### Data
Data
----
To do the tracking we need a video and object position on the first frame.
@@ -31,14 +32,16 @@ To run the code you have to specify input and output video path and object bound
@code{.none}
./planar_tracking blais.mp4 result.avi blais_bb.xml.gz
@endcode
### Source Code
Source Code
-----------
@includelineno cpp/tutorial_code/features2D/AKAZE_tracking/planar_tracking.cpp
### Explanation
Explanation
-----------
Tracker class
-------------
### Tracker class
This class implements algorithm described abobve using given feature detector and descriptor
matcher.
@@ -63,62 +66,60 @@ matcher.
- **Processing frames**
1. Locate keypoints and compute descriptors
@code{.cpp}
(*detector)(frame, noArray(), kp, desc);
@endcode
To find matches between frames we have to locate the keypoints first.
In this tutorial detectors are set up to find about 1000 keypoints on each frame.
-# Locate keypoints and compute descriptors
@code{.cpp}
(*detector)(frame, noArray(), kp, desc);
@endcode
1. Use 2-nn matcher to find correspondences
@code{.cpp}
matcher->knnMatch(first_desc, desc, matches, 2);
for(unsigned i = 0; i < matches.size(); i++) {
if(matches[i][0].distance < nn_match_ratio * matches[i][1].distance) {
matched1.push_back(first_kp[matches[i][0].queryIdx]);
matched2.push_back( kp[matches[i][0].trainIdx]);
To find matches between frames we have to locate the keypoints first.
In this tutorial detectors are set up to find about 1000 keypoints on each frame.
-# Use 2-nn matcher to find correspondences
@code{.cpp}
matcher->knnMatch(first_desc, desc, matches, 2);
for(unsigned i = 0; i < matches.size(); i++) {
if(matches[i][0].distance < nn_match_ratio * matches[i][1].distance) {
matched1.push_back(first_kp[matches[i][0].queryIdx]);
matched2.push_back( kp[matches[i][0].trainIdx]);
}
}
}
@endcode
If the closest match is *nn_match_ratio* closer than the second closest one, then it's a
match.
@endcode
If the closest match is *nn_match_ratio* closer than the second closest one, then it's a
match.
2. Use *RANSAC* to estimate homography transformation
@code{.cpp}
homography = findHomography(Points(matched1), Points(matched2),
RANSAC, ransac_thresh, inlier_mask);
@endcode
If there are at least 4 matches we can use random sample consensus to estimate image
transformation.
-# Use *RANSAC* to estimate homography transformation
@code{.cpp}
homography = findHomography(Points(matched1), Points(matched2),
RANSAC, ransac_thresh, inlier_mask);
@endcode
If there are at least 4 matches we can use random sample consensus to estimate image
transformation.
3. Save the inliers
@code{.cpp}
for(unsigned i = 0; i < matched1.size(); i++) {
if(inlier_mask.at<uchar>(i)) {
int new_i = static_cast<int>(inliers1.size());
inliers1.push_back(matched1[i]);
inliers2.push_back(matched2[i]);
inlier_matches.push_back(DMatch(new_i, new_i, 0));
-# Save the inliers
@code{.cpp}
for(unsigned i = 0; i < matched1.size(); i++) {
if(inlier_mask.at<uchar>(i)) {
int new_i = static_cast<int>(inliers1.size());
inliers1.push_back(matched1[i]);
inliers2.push_back(matched2[i]);
inlier_matches.push_back(DMatch(new_i, new_i, 0));
}
}
}
@endcode
Since *findHomography* computes the inliers we only have to save the chosen points and
matches.
@endcode
Since *findHomography* computes the inliers we only have to save the chosen points and
matches.
4. Project object bounding box
@code{.cpp}
perspectiveTransform(object_bb, new_bb, homography);
@endcode
If there is a reasonable number of inliers we can use estimated transformation to locate the
object.
-# Project object bounding box
@code{.cpp}
perspectiveTransform(object_bb, new_bb, homography);
@endcode
### Results
If there is a reasonable number of inliers we can use estimated transformation to locate the
object.
Results
-------
You can watch the resulting [video on youtube](http://www.youtube.com/watch?v=LWY-w8AGGhE).
@@ -129,6 +130,7 @@ Inliers 410
Inlier ratio 0.58
Keypoints 1117
@endcode
*ORB* statistics:
@code{.none}
Matches 504

2
doc/tutorials/features2d/feature_description/feature_description.markdown
View File

@@ -87,4 +87,4 @@ Result
Here is the result after applying the BruteForce matcher between the two original images:
![image](images/Feature_Description_BruteForce_Result.jpg)
![](images/Feature_Description_BruteForce_Result.jpg)

8
doc/tutorials/features2d/feature_detection/feature_detection.markdown
View File

@@ -79,10 +79,10 @@ Explanation
Result
------
1. Here is the result of the feature detection applied to the first image:
-# Here is the result of the feature detection applied to the first image:
![image](images/Feature_Detection_Result_a.jpg)
![](images/Feature_Detection_Result_a.jpg)
2. And here is the result for the second image:
-# And here is the result for the second image:
![image](images/Feature_Detection_Result_b.jpg)
![](images/Feature_Detection_Result_b.jpg)

8
doc/tutorials/features2d/feature_flann_matcher/feature_flann_matcher.markdown
View File

@@ -130,10 +130,10 @@ Explanation
Result
------
1. Here is the result of the feature detection applied to the first image:
-# Here is the result of the feature detection applied to the first image:
![image](images/Featur_FlannMatcher_Result.jpg)
![](images/Featur_FlannMatcher_Result.jpg)
2. Additionally, we get as console output the keypoints filtered:
-# Additionally, we get as console output the keypoints filtered:
![image](images/Feature_FlannMatcher_Keypoints_Result.jpg)
![](images/Feature_FlannMatcher_Keypoints_Result.jpg)

4
doc/tutorials/features2d/feature_homography/feature_homography.markdown
View File

@@ -134,8 +134,8 @@ Explanation
Result
------
1. And here is the result for the detected object (highlighted in green)
-# And here is the result for the detected object (highlighted in green)
![image](images/Feature_Homography_Result.jpg)
![](images/Feature_Homography_Result.jpg)

4
doc/tutorials/features2d/trackingmotion/corner_subpixeles/corner_subpixeles.markdown
View File

@@ -122,9 +122,9 @@ Explanation
Result
------
![image](images/Corner_Subpixeles_Original_Image.jpg)
![](images/Corner_Subpixeles_Original_Image.jpg)
Here is the result:
![image](images/Corner_Subpixeles_Result.jpg)
![](images/Corner_Subpixeles_Result.jpg)

4
doc/tutorials/features2d/trackingmotion/generic_corner_detector/generic_corner_detector.markdown
View File

@@ -30,7 +30,7 @@ Explanation
Result
------
![image](images/My_Harris_corner_detector_Result.jpg)
![](images/My_Harris_corner_detector_Result.jpg)
![image](images/My_Shi_Tomasi_corner_detector_Result.jpg)
![](images/My_Shi_Tomasi_corner_detector_Result.jpg)

2
doc/tutorials/features2d/trackingmotion/good_features_to_track/good_features_to_track.markdown
View File

@@ -111,5 +111,5 @@ Explanation
Result
------
![image](images/Feature_Detection_Result_a.jpg)
![](images/Feature_Detection_Result_a.jpg)

4
doc/tutorials/features2d/trackingmotion/harris_detector/harris_detector.markdown
View File

@@ -201,9 +201,9 @@ Result
The original image:
![image](images/Harris_Detector_Original_Image.jpg)
![](images/Harris_Detector_Original_Image.jpg)
The detected corners are surrounded by a small black circle
![image](images/Harris_Detector_Result.jpg)
![](images/Harris_Detector_Result.jpg)