I've been trying to refine my camera parameters with CvLevMarq but after reading about it, it seems to be causing mixed results - which is exactly what I am experiencing. I read about the alternatives and came upon EIGEN - and also found this library that utilizes it.
However, the library above seems to use a stitching class that doesn't support OpenCV and will probably require me to port it to OpenCV.
Before going ahead and doing so, which will probably not be an easy task, I figured I'd ask around first and see if anyone else had the same problem?
I'm currently using:
1. Calculating features with FASTFeatureDetector
Ptr<FeatureDetector> detector = new FastFeatureDetector(5,true);
detector->detect(firstGreyImage, features_global[firstImageIndex].keypoints); // Previous picture
detector->detect(secondGreyImage, features_global[secondImageIndex].keypoints); // New picture
2. Extracting features with SIFTDescriptorExtractor
Ptr<SiftDescriptorExtractor> extractor = new SiftDescriptorExtractor();
extractor->compute(firstGreyImage, features_global[firstImageIndex].keypoints, features_global[firstImageIndex].descriptors); // Previous Picture
extractor->compute(secondGreyImage, features_global[secondImageIndex].keypoints, features_global[secondImageIndex].descriptors); // New Picture
3. Matching features with BestOf2NearestMatcher
vector<MatchesInfo> pairwise_matches;
BestOf2NearestMatcher matcher(try_use_gpu, 0.50f);
matcher(features_global, pairwise_matches);
matcher.collectGarbage();
4. CameraParams.R quaternion passed from a device (slightly inaccurate which causes the issue)
5. CameraParams.Focal == 389.0f -- Played around with this value, 389.0f is the only value that matches the images horizontally but not vertically.
6. Bundle Adjustment (cvLevMarq, calcError & calcJacobian)
Ptr<BPRefiner> adjuster = new BPRefiner();
adjuster->setConfThresh(0.80f);
adjuster->setMaxIterations(5);
(*adjuster)(features,pairwise_matches,cameras);
7. ExposureCompensator (GAIN)
8. OpenCV MultiBand Blender
What works so far:
SeamFinder - works to some extent but it depends on the result of the cvLevMarq algoritm. I.e. if the algoritm is off, seamFinder is going to be off too.
HomographyBasedEstimator works beautifully. However, since it "relies" on the features, it's unfortunately not the method that I'm looking for.
I wouldn't want to rely on the features since I already have the matrix, if there's a way to "refine" the current matrix instead - then that would be the targeted result.
Results so far:
cvLevMarq "Russian roulette" 6/10:
This is what I'm trying to achieve 10/10 times. But 4/10 times, it looks like the picture below this one.
By simply just re-running the algorithm, the results change. 4/10 times it looks like this (or worse):
cvLevMarq "Russian roulette" 4/10:
Desired Result:
I'd like to "refine" my camera parameters with the features that I've matched - in hope that the images would align perfectly. Instead of hoping that cvLevMarq will do the job for me (which it won't 4/10 times), is there another way to ensure that the images will be aligned?
Update:
I've tried these versions:
OpenCV 3.1: Using CVLevMarq with 3.1 is like playing Russian roulette. Some times it can align them perfectly, and other times it estimates focal as NAN which causes segfault in the MultiBand Blender (ROI = 0,0,1,1 because of NAN)
OpenCV 2.4.9/2.4.13: Using CvLevMarq with 2.4.9 or 2.4.13 is unfortunately the same thing minus the NAN issue. 6/10 times it can align the images perfectly, but the other 4 times it's completely off.
My Speculations / Thoughts:
Template Matching using OpenCV. Maybe if I template match the ends of the images (i.e. x = 0, y = 0,height = image.height, width = 50). Any thoughts about this?
I found this interesting paper about Levenberg Marquardt applied in Homography. That looks like something that could solve my problem since the paper uses corner detection and whatnot to detect the features in the images. Any thoughts about this?
Maybe the problem isn't in CvLevMarq but instead in BestOf2NearestMatcher? However, I've searched for days and I couldn't find another method that returns the pairwise matches to pass to BPRefiner.
Hough Line Transform Detecting the lines in the first/second image and use that to align the images. Any thoughts on this? -- One thing might be, what if the images doesn't have any lines? I.e. empty wall?
Maybe I'm overkilling something so simple.. Or maybe I'm not? Basically, I'm trying to align a set of images so I can warp them without overlapping each-other. Drop a comment if it doesn't make sense :)
Update Aug 12:
After trying all kinds of combinations, the absolute best so far is CvLevMarq. The only problem with it is the mixed results shown in the images above. If anyone has any input, I'd be forever grateful.
It seems your parameter initialization is the problem. I would use a linear estimator first, i.e. ignore your noisy sensor, and then use this as the initial values for the non-linear optimizer.
A quick method is to use getaffinetransform, as you have mostly rotation.
Maybe you want to take a look at this library: https://github.com/ethz-asl/kalibr.
Cheers
If you want to stitch the images, you should see stitching_detailed.cpp. It will probably solve your problem.
In addition, I have used Graph Cut Seam Finding method with Canny Edge Detection for better stitching results in this code. If you want to optimize this code, see here.
Also, if you are going to use it for personal use, SIFT is good. You should know, SIFT is patented and will cost you if you use it for commercial purposes. Use ORB instead.
Hope it helps!
Related
I'm using OpenCV 3.3.1. I want to do a semi-dense optical flow operation using cv::calcOpticalFlowPyrLK, but I've been getting some really noticeable slowdown whenever my ROI is pretty big (Partly due to the fact that I am letting the user decide what the winSize should be, ranging from from 10 to 100). Anyways, it seems like cv::buildOpticalFlowPyramid can mitigate the slowdown by building image pyramids? I'm sorta familiar what image pyramids are, but in context of the function, I'm especially confused about what parameters I pass in, and how it impacts my function call to cv::calcOpticalFlowPyrLK. With that in mind, I now have these set of questions:
The output is, according to the documentation, is an OutputArrayOfArrays, which I take it can be a vector of cv::Mat objects. If so, what do I pass in to cv::calcOpticalFlowPyrLK for prevImg and nextImg (assuming that I need to make image pyramids for both)?
According to the docs for cv::buildOpticalFlowPyramid, you need to pass in a winSize parameter in order to calculate required padding for pyramid levels. If so, do you pass in the same winSize value when you eventually call cv::calcOpticalFlowPyrLK?
What exactly are the arguments for pyrBorder and derivBorder doing?
Lastly, and apologies if it sounds newbish, but what is the purpose of this function? I always assumed that cv::calcOpticalFlowPyrLK internally builds the image pyramids. Is it just to speed up the optical flow operation?
I hope my questions were clear, I'm still very new to OpenCV, and computer vision, but this topic is very interesting.
Thank you for your time.
EDIT:
I used the function to see if my guess was correct, so far it has worked, but I've seen no noticeable speed up. Below is how I used it:
// Building pyramids
int maxLvl = 3;
maxLvl = cv::buildOpticalFlowPyramid(imgPrev, imPyr1, cv::Size(searchSize, searchSize), maxLvl, true);
maxLvl = cv::buildOpticalFlowPyramid(tmpImg, imPyr2, cv::Size(searchSize, searchSize), maxLvl, true);
// LK optical flow call
cv::calcOpticalFlowPyrLK(imPyr1, imPyr2, currentPoints, nextPts, status, err,
cv::Size(searchSize, searchSize), maxLvl, termCrit, 0, 0.00001);
So now I'm wondering what's the purpose of preparing the image pyramids if calcOpticalFlowPyrLK does it internally?
So the point of your question is that you are trying to improve speed of optical flow tracking by tuning your input parameters.
If you want dirty and quick answer then here it is
KTL (OpenCV's calcOpticalFlowPyrLK) define a e residual function which are sum of gradient of point inside search window .
The main purpose is to find vector of point that can minimize residual function
So if you increase search window size (winSize) then it is more difficult to find that set of points.
If your really really want to do that then please read the official paper.
See the section 2.4
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.185.585&rep=rep1&type=pdf
I took it from official document
https://docs.opencv.org/2.4/modules/video/doc/motion_analysis_and_object_tracking.html#bouguet00
Hope that help
When using findHomography():
Mat H = findHomography( obj, scene, cv::RANSAC , 3, hom_mask, 2000, 0.995 );
Sometimes, for some image, the resulting H matrix stays empty (H is a UINT8, 1x0x0). However, there is clearly a match between both images (and it looks like good keypoint matches are detected), and just a moment before, with two similar images with similar keypoint responses, a relevant matrix was generated. Input parameters "obj" and "scene" are both a vector of Point2f containing various coordinates.
Is this a common issue? Or do you think a bug might lurk somewhere? Personally, I have processed hundreds of images where a match exists and while I have seen sometime poor matches, it is the first time I get an empty matrix...
EDIT : This said, even if my eyes think that there should be a match in the image pairs, I realize that it might confuses some portion of the image with an other one and that maybe there is indeed no "good" match.
So my question would be: How does findHomography() behave when it is unable to find a suitable Homography? Does it return an empty matrix or will it always give a homography, albeit a very poor one? I just want to know if I encounter standard behaviour or if there is a bug in my own code.
Well you see, cv::findHomography() function could return empty homography matrix (0 cols x 0 rows) starting approximately from 2.4.5 release.
According to some opinion this seems happen only when cv::RANSAC flag is passed.
See the issue reported here:
It likely happened because we put in new experimental version of
Levenberg-Marquardt solver, which does not work that well (maybe due
to some bugs)
I suggest to check the computed homography before using it anywhere:
cv::Mat h = cv::findHomography(...)
if (!h.empty())
{
// Use it
}
I've got the BumbleBee 2 stereo camera and two mentioned SDKs.
I've managed to capture a video from it in my program, rectify stereo images and get a disparity map. Next thing I'd like to have is a depth map similar to one, the Kinect gives.
The Triclops' documentation is rather short, it only references functions, without typical workflow description. The workflow is described in examples.
Up to now I've found 2 relevant functions: family of triclopsRCDxxToXYZ() functions and triclopsExtractImage3d() function.
Functions from the first family calculate x, y and z coordinate for a single pixel. Z coordinate perfectly corresponds to the depth in meters. However, to use this function I should create two nested loops, as shown in the stereo3dpoints example. That gives too much overhead, because each call returns two more coordinates.
The second function, triclopsExtractImage3d(), always returns error TriclopsErrorInvalidParameter. The documentation says only that "there is a geometry mismatch between the context and the TriclopsImage3d", which is not clear for me.
Examples of Triclops 3.3.1 SDK do not show how to use it. Google brings example from Triclops SDK 3.2, which is absent in 3.3.1.
I've tried adding lines 253-273 from the link above to current stereo3dpoints - got that error.
Does anyone have an experience with it?
Is it valid to use triclopsExtractImage3d() or is it obsolete?
I also tried plotting values of disparity vs. z, obtained from triclopsRCDxxToXYZ().
The plot shows almost exact inverse proportionality: .
That is z = k / disparity. But k is not constant across the image, it varies from approximately 2.5e-5 to 1.4e-3, that is two orders of magnitude. Therefore, it is incorrect to calculate this value once and use forever.
Maybe it is a bit to late and you figured it out by yourself but:
To use triclopsExtractImage3d you have to create a 3dImage first.
TriclopsImage3d *depthImage;
triclopsCreateImage3d(triclopsContext, &depthImage);
triclopsExtractImage3d(triclopsContext, depthImage);
triclopsDestroyImage3d(&depthImage);
I have mat with only one column and 1600 rows. I want to filter it using a Gaussian.
I tried the following:
Mat AFilt=Mat(palm_contour.size(),1,CV_32F);
GaussianBlur(A,AFilt,cv::Size(20,1),3);
But I get the exact same values in AFilt (the filtered mat) and A. It looks like GaussianBlur has done nothing.
What's the problem here? How can I smooth a single-column mat with a Gaussian kernel?
I read about BaseColumnFilt, but haven't seen any usage examples so I'm not sure how to use them.
Any help given will be greatly appreciated as I don't have a clue.
I'm working with OpenCV 2.4.5 on windows 8 using Visual Studio 2012.
Thanks
Gil.
You have a single column but you are specifying the width of the gaussian to be big instead of specifying the height! OpenCV use row,col or x,y notation depending on the context. A general rule is whenever you use Point or Size, they behave like x,y and whenever the parameters are separate values they behave like row,col.
The kernel size should also be odd. If you specify the kernel size you can set sigma to zero to let OpenCV compute a suitable sigma value.
To conclude, this should work better:
GaussianBlur(A,AFilt,cv::Size(1,21),0);
The documentation og GaussianBlur says the kernel size must be odd, I would try using an odd size kernel and see if that makes any difference
I have a bitmap image context and want to let this appear blurry. So best thing I can think of is a gauss algorithm, but I have no big idea about how this kind of gauss blur algorithms look like? Do you know good tutorials or examples on this? The language does not matter so much, if it's done all by hand without using language-specific API too much. I.e. in cocoa the lucky guys don't need to think about it, they just use a Imagefilter that's already there. But I don't have something like this in cocoa-touch (objective-c, iPhone OS).
This is actually quite simple. You have a filter pattern (also known as filter kernel) - a (small) rectangular array with coefficients - and just calculate the convolution of the image and the pattern.
for y = 1 to ImageHeight
for x = 1 to ImageWidth
newValue = 0
for j = 1 to PatternHeight
for i = 1 to PatternWidth
newValue += OldImage[x-PatternWidth/2+i,y-PatternHeight/2+j] * Pattern[i,j]
NewImage[x,y] = newValue
The pattern is just a Gauss curve in two dimensions or any other filter pattern you like. You have to take care at the edges of the image because the filter pattern will be partialy outside of the image. You can just assume that this pixels are balck, or use a mirrored version of the image, or what ever seems reasonable.
As a final note, there are faster ways to calculate a convolution using Fourier transforms but this simple version should be sufficent for a first test.
The Wikipedia article has a sample matrix in addition to some standard information on the subject.
Best place for image processing is THIS. You can get matlab codes there.
And this Wolfram demo should clear any doubts about doing it by hand.
And if you don't want to learn too many things learn PIL(Python Imaging Library).
"Here" is exactly what you need.
Code copied from above link:
import ImageFilter
def filterBlur(im):
im1 = im.filter(ImageFilter.BLUR)
im1.save("BLUR" + ext)
filterBlur(im1)