I need your expertise in this problem: I am currently processing an image and would like to extract the skeleton. So far by means of preprocessing I could reach a skeleton of 2 pixel thickness. However I would really like to minimize the size of the skeleton to end up with a thickness of 1. Therefore I propose the following algorithm,which makes sense to me. Before I start the whole code process, I would like to get rid of some suspicions.
Let me explain:
My algorithm is as follows:
Scour the image pixels (remember the ROI described acts as a sliding window)
for the first pixel (skipping boundary pixels) create a region of interest of 3x3 ( the pixel being the anchor(center) of the ROI)
does that pixel carry a maximum value ? (check this condition using pointers w.r.t its 8 neighbors)
take at the same time a second 3x3 ROI for the previous pixel's right neighbor
Is it also a maximum ?
Now create the following logic:
If the first ROI returns true and the second ROI returns true
take the center of the first ROI as true and skip 1 pixel to the right
If the first ROI return true and the other false
take the center of the first ROI true and continue to next pixel
Any other suggestions ? my idea is to get a skeleton of thickness 1.
Related
I'm working with OpenCV 3.4.8 with C++11 and I'm trying to blend images together.
In this example I have 2 images (thiers mask shown in the screen belowe). I have georeference, so I can easy calculate corners of this images in the final image.
The data outside the masks are black.
My code looks like something like that:
std::vector<cv::UMat> inputImages;
std::vector<cv::UMat> masks;
std::vector<cv::Point> corners;
std::vector<cv::Size> imgSizes;
/*
here is code where I load images, create thier masks
(like in the screen above) and calculate corners.
*/
cv::Ptr<cv::detail::SeamFinder> seamFinder = new cv::detail::DpSeamFinder();
seamFinder->find(inputImages, corners, masks);
cv::Ptr<cv::detail::Blender> blender = new cv::detail:: MultiBandBlender(false);
blender->prepare(corners, imgSizes);
for(size_t i = 0; i < inputImages.size(); i++)
{
blender->feed(inputImages[i], masks[i], corners[i]);
}
cv::UMat blendedImg, outMask;
blender->blend(blendedImg, outMask);
SeamFinder gives me result like in the screen above. Finded seam lines looks good and Im very satisied form them. But the other problem occurs in the next step. The MultiBandBlender is making strange white streaks when the seam line goes on the end of the data.
This is an example:
When I don't use blender, but just use masks to cut the oryginal images and just add (cv::add()) images together with additional alpha channel (made from masks) I get very good results without any holes and strange colors, but I need to have more smoothed transition :/
Can anyone help me? When I create MultiBand Blender with smaller num_bands the white streaks are smaller, and with the num_bands = 0 the results looks like with just adding images.
I looked at feed() and blend() methods in the MultiBandBlender and I think that it is connected with Gaussian or Laplacian pyramid and the final restoring images from Laplacian pyramid in the blend() method.
EDIT1:
When Gaussian and Laplacian pyramids are created the copyMakeBorder(), which prevents the MultiBandBlender from making this white streaks when images are fully filled with the data. So in my case I think that I need to create my blender almost the same like MultiBandBlender, but copyMakeBorder() method in the feed() method change to the something that will "extend" my image inside the mask, like #AlexanderKondratskiy suggested.
Now I don't know how to achive correct "extend" similar to BORDER_REFLECT or BORDER_REFLECT_101.
I suspect your input images contain white pixels outside those masks. The white banding occurs around the areas where the seam follows the mask exactly. For Laplacian for example, pixels outside the mask do influence the final result, as each layer of a pyramid is essentially some blurring kernel on the image.
If you have some kind of good data outside the mask, keep it. If you do not, I suggest "extending" your image beyond the mask to maintain a smooth transition.
Edit:
Here's two things you could try, unless someone with more experience with OpenCV comes along.
To prove/disprove my hypothesis, fill the black region with just the average or median color within the mask. This should make the transition to the outside region less sharp, and hopefully reduce the artefacts. If that does not happen, my answer is wrong.
In terms of what is probably a good generalization of "BORDER_REFLECT" when the edge is arbitrary, you could try something like this:
Find the centroid c of the mask polygon
For each pixel p outside the mask, think of the line between it and c
Calculate point p' along this line that is the same distance inside the mask area, as p is from the mask edge. (i.e. you're reflecting along the mask edge)
Linearly interpolate the color of from the neighbors of p' (as it's position may not fall exactly in the middle of a pixel). That's the color of pixel p
Is that possible to get the depth/disparity map from a moving camera? Let say I capture an image at x location, after I travelled let say 5cm and I capture another picture, and from there I calculate the depth map of the image.
I have tried using BlockMatching in opencv but the result is not good.The first and second image are as following:
first image,second image,
disparity map (colour),disparity map
My code is as following:
GpuMat leftGPU;
GpuMat rightGPU;
leftGPU.upload(left);rightGPU.upload(right);
GpuMat disparityGPU;
GpuMat disparityGPU2;
Mat disparity;Mat disparity1,disparity2;
Ptr<cuda::StereoBM> stereo = createStereoBM(256,3);
stereo->setMinDisparity(-39);
stereo->setPreFilterCap(61);
stereo->setPreFilterSize(3);
stereo->setSpeckleRange(1);
stereo->setUniquenessRatio(0);
stereo->compute(leftGPU,rightGPU,disparityGPU);
drawColorDisp(disparityGPU, disparityGPU2,256);
disparityGPU.download(disparity);
disparityGPU2.download(disparity2);
imshow("display img",disparityGPU);
how can I improve upon this? From the colour disparity map, there are quite a lot error (ie. the tall circle is red in colour and it is the same as some of the part of the table.). Also,from the disparity map, there are small noise (all the black dots in the picture), how can I pad those black dots with nearby disparities?
It is possible if the object is static.
To properly do stereo matching, you first need to rectify your images! If you don't have calibrated cameras, you can do this from detected feature points. Also note that for cuda::StereoBM the minimum default disparity is 0. (I have never used cuda, but I don't think your setMinDisparity is doing anything, see this anser.)
Now, in your example images corresponding points are only about 1 row apart, therefore your disparity map actually doesn't look too bad. Maybe having a larger blockSize would already do in this special case.
Finally, your objects have very low texture, therefore the block matching algorithm can't detect much.
What I need
I'm currently working on an augmented reality kinda game. The controller that the game uses (I'm talking about the physical input device here) is a mono colored, rectangluar pice of paper. I have to detect the position, rotation and size of that rectangle in the capture stream of the camera. The detection should be invariant on scale and invariant on rotation along the X and Y axes.
The scale invariance is needed in case that the user moves the paper away or towards the camera. I don't need to know the distance of the rectangle so scale invariance translates to size invariance.
The rotation invariance is needed in case the user tilts the rectangle along its local X and / or Y axis. Such a rotation changes the shape of the paper from rectangle to trapezoid. In this case, the object oriented bounding box can be used to measure the size of the paper.
What I've done
At the beginning there is a calibration step. A window shows the camera feed and the user has to click on the rectangle. On click, the color of the pixel the mouse is pointing at is taken as reference color. The frames are converted into HSV color space to improve color distinguishing. I have 6 sliders that adjust the upper and lower thresholds for each channel. These thresholds are used to binarize the image (using opencv's inRange function).
After that I'm eroding and dilating the binary image to remove noise and unite nerby chunks (using opencv's erode and dilate functions).
The next step is finding contours (using opencv's findContours function) in the binary image. These contours are used to detect the smallest oriented rectangles (using opencv's minAreaRect function). As final result I'm using the rectangle with the largest area.
A short conclusion of the procedure:
Grab a frame
Convert that frame to HSV
Binarize it (using the color that the user selected and the thresholds from the sliders)
Apply morph ops (erode and dilate)
Find contours
Get the smallest oriented bouding box of each contour
Take the largest of those bounding boxes as result
As you may noticed, I don't make an advantage of the knowledge about the actual shape of the paper, simply because I don't know how to use this information properly.
I've also thought about using the tracking algorithms of opencv. But there were three reasons that prevented me from using them:
Scale invariance: as far as I read about some of the algorithms, some don't support different scales of the object.
Movement prediction: some algorithms use movement prediction for better performance, but the object I'm tracking moves completely random and therefore unpredictable.
Simplicity: I'm just looking for a mono colored rectangle in an image, nothing fancy like car or person tracking.
Here is a - relatively - good catch (binary image after erode and dilate)
and here is a bad one
The Question
How can I improve the detection in general and especially to be more resistant against lighting changes?
Update
Here are some raw images for testing.
Can't you just use thicker material?
Yes I can and I already do (unfortunately I can't access these pieces at the moment). However, the problem still remains. Even if I use material like cartboard. It isn't bent as easy as paper, but one can still bend it.
How do you get the size, rotation and position of the rectangle?
The minAreaRect function of opencv returns a RotatedRect object. This object contains all the data I need.
Note
Because the rectangle is mono colored, there is no possibility to distinguish between top and bottom or left and right. This means that the rotation is always in range [0, 180] which is perfectly fine for my purposes. The ratio of the two sides of the rect is always w:h > 2:1. If the rectangle would be a square, the range of roation would change to [0, 90], but this can be considered irrelevant here.
As suggested in the comments I will try histogram equalization to reduce brightness issues and take a look at ORB, SURF and SIFT.
I will update on progress.
The H channel in the HSV space is the Hue, and it is not sensitive to the light changing. Red range in about [150,180].
Based on the mentioned information, I do the following works.
Change into the HSV space, split the H channel, threshold and normalize it.
Apply morph ops (open)
Find contours, filter by some properties( width, height, area, ratio and so on).
PS. I cannot fetch the image you upload on the dropbox because of the NETWORK. So, I just use crop the right side of your second image as the input.
imgname = "src.png"
img = cv2.imread(imgname)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
## Split the H channel in HSV, and get the red range
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
h,s,v = cv2.split(hsv)
h[h<150]=0
h[h>180]=0
## normalize, do the open-morp-op
normed = cv2.normalize(h, None, 0, 255, cv2.NORM_MINMAX, cv2.CV_8UC1)
kernel = cv2.getStructuringElement(shape=cv2.MORPH_ELLIPSE, ksize=(3,3))
opened = cv2.morphologyEx(normed, cv2.MORPH_OPEN, kernel)
res = np.hstack((h, normed, opened))
cv2.imwrite("tmp1.png", res)
Now, we get the result as this (h, normed, opened):
Then find contours and filter them.
contours = cv2.findContours(opened, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
print(len(contours))[-2]
bboxes = []
rboxes = []
cnts = []
dst = img.copy()
for cnt in contours:
## Get the stright bounding rect
bbox = cv2.boundingRect(cnt)
x,y,w,h = bbox
if w<30 or h < 30 or w*h < 2000 or w > 500:
continue
## Draw rect
cv2.rectangle(dst, (x,y), (x+w,y+h), (255,0,0), 1, 16)
## Get the rotated rect
rbox = cv2.minAreaRect(cnt)
(cx,cy), (w,h), rot_angle = rbox
print("rot_angle:", rot_angle)
## backup
bboxes.append(bbox)
rboxes.append(rbox)
cnts.append(cnt)
The result is like this:
rot_angle: -2.4540319442749023
rot_angle: -1.8476102352142334
Because the blue rectangle tag in the source image, the card is splited into two sides. But a clean image will have no problem.
I know it's been a while since I asked the question. I recently continued on the topic and solved my problem (although not through rectangle detection).
Changes
Using wood to strengthen my controllers (the "rectangles") like below.
Placed 2 ArUco markers on each controller.
How it works
Convert the frame to grayscale,
downsample it (to increase performance during detection),
equalize the histogram using cv::equalizeHist,
find markers using cv::aruco::detectMarkers,
correlate markers (if multiple controllers),
analyze markers (position and rotation),
compute result and apply some error correction.
It turned out that the marker detection is very robust to lighting changes and different viewing angles which allows me to skip any calibration steps.
I placed 2 markers on each controller to increase the detection robustness even more. Both markers has to be detected only one time (to measure how they correlate). After that, it's sufficient to find only one marker per controller as the other can be extrapolated from the previously computed correlation.
Here is a detection result in a bright environment:
in a darker environment:
and when hiding one of the markers (the blue point indicates the extrapolated marker postition):
Failures
The initial shape detection that I implemented didn't perform well. It was very fragile to lighting changes. Furthermore, it required an initial calibration step.
After the shape detection approach I tried SIFT and ORB in combination with brute force and knn matcher to extract and locate features in the frames. It turned out that mono colored objects don't provide much keypoints (what a surprise). The performance of SIFT was terrible anyway (ca. 10 fps # 540p).
I drew some lines and other shapes on the controller which resulted in more keypoints beeing available. However, this didn't yield in huge improvements.
I'm developing a software that detects boxers punching motion. At the moment i used color based segmentation using inRange function and set it to detect blue Minimum value and Blue Maximum value. The problem is that the range is quite wide and my cam at times picks out noise and segments objects of no interest. To improve the software i though of scanning image of a boxing glove and establishing exact Blue color Value before further processing.
It would make sens to me to store that value in a Vector and call it in inRange fiction
// My current function which takes the Minimum and Maximum values of Blue Color
Mat range_out;
inRange(blur_out, Scalar(100, 100, 100), Scalar(120, 255, 255), range_out);
So i would image the vector to go somewhere here.
Scan this above image compute the Blue value
Store this value in an array
recall the array in a inRange function
Could someone suggest a solution to this problem or direct me to a source of information where I can look for answers ?
since you are detecting the boxer gloves in motion so first use motion to separate it from other elements in the scene...use frame differentiation or optical flow to separate the glove and other moving areas from non moving areas...now in those moving area try for some colour detection...
Separe luminosity and cromaticity - your fixed range will not work very well in different light conditions. Your range is wide probably because you are trying to see "blue" in dark and on light at the same time. Convert your image to HSV (or La*b*) and discard V (or L), keeping H and S (or a* and b*).
Learn a color distribution instead a simple range - take some samples and compute a 2D
color histogram on H and S (a* or b*) for pixels on the glove. This histogram will be a model for the color distribution of your object. Then, use c2.calcBackProjection to detect the pixels of interest in your scene.
Clean the result using morphological close operation
Important: on step 2, play a little with different quantization values (ie, different numbers of bins).
Some details about my problem:
I'm trying to realize corner detector in openCV (another algorithm, that are built-in: Canny, Harris, etc).
I've got a matrix filled with the response values. The biggest response value is - the biggest probability of corner detected is.
I have a problem, that in neighborhood of a point there are few corners detected (but there is only one). I need to reduce number of false-detected corners.
Exact problem:
I need to walk through the matrix with a kernel, calculate maximum value of every kernel, leave max value, but others values in kernel make equal zero.
Are there build-in openCV functions to do this?
This is how I would do it:
Create a kernel, it defines a pixels neighbourhood.
Create a new image by dilating your image using this kernel. This dilated image contains the maximum neighbourhood value for every point.
Do an equality comparison between these two arrays. Wherever they are equal is a valid neighbourhood maximum, and is set to 255 in the comparison array.
Multiply the comparison array, and the original array together (scaling appropriately).
This is your final array, containing only neighbourhood maxima.
This is illustrated by these zoomed in images:
9 pixel by 9 pixel original image:
After processing with a 5 by 5 pixel kernel, only the local neighbourhood maxima remain (ie. maxima seperated by more than 2 pixels from a pixel with a greater value):
There is one caveat. If two nearby maxima have the same value then they will both be present in the final image.
Here is some Python code that does it, it should be very easy to convert to c++:
import cv
im = cv.LoadImage('fish2.png',cv.CV_LOAD_IMAGE_GRAYSCALE)
maxed = cv.CreateImage((im.width, im.height), cv.IPL_DEPTH_8U, 1)
comp = cv.CreateImage((im.width, im.height), cv.IPL_DEPTH_8U, 1)
#Create a 5*5 kernel anchored at 2,2
kernel = cv.CreateStructuringElementEx(5, 5, 2, 2, cv.CV_SHAPE_RECT)
cv.Dilate(im, maxed, element=kernel, iterations=1)
cv.Cmp(im, maxed, comp, cv.CV_CMP_EQ)
cv.Mul(im, comp, im, 1/255.0)
cv.ShowImage("local max only", im)
cv.WaitKey(0)
I didn't realise until now, but this is what #sansuiso suggested in his/her answer.
This is possibly better illustrated with this image, before:
after processing with a 5 by 5 kernel:
solid regions are due to the shared local maxima values.
I would suggest an original 2-step procedure (there may exist more efficient approaches), that uses opencv built-in functions :
Step 1 : morphological dilation with a square kernel (corresponding to your neighborhood). This step gives you another image, after replacing each pixel value by the maximum value inside the kernel.
Step 2 : test if the cornerness value of each pixel of the original response image is equal to the max value given by the dilation step. If not, then obviously there exists a better corner in the neighborhood.
If you are looking for some built-in functionality, FilterEngine will help you make a custom filter (kernel).
http://docs.opencv.org/modules/imgproc/doc/filtering.html#filterengine
Also, I would recommend some kind of noise reduction, usually blur, before all processing. That is unless you really want the image raw.