I have two closed curve stereo rectified edge images. Is it possible to find the disparity(along x-axis in image coordinates) between the edge images and do a 3D reconstruction since I know the camera matrix. I am using matlab for the process. And I will not be able to do a window based technique as it's a binary image since a window based technique requires texture. The question how will I compute the disparity between the edge images? The images are available in the following links. Left Edge image https://www.dropbox.com/s/g5g22f6b0vge9ct/edge_left.jpg?dl=0 Right Edge Image https://www.dropbox.com/s/wjmu3pugldzo2gw/edge_right.jpg?dl=0
For this type of images, you can easily map each edge pixel from the left image to its counterpart in the right image, and therefore calculate the disparity for those pixels as usual.
The mapping can be done in various ways, depending on how typical these images are. For example, using DTW like approach to match curvatures.
For all other pixels in the image, you just don't have any information.
#Photon: Thanks for the suggestion. I did what you suggested. I matched each edge pixel in the left and right image in a DTW like fashion. But there are some pixels whose y-pixel coordinate value differ by 1 or 2 pixels, albeit they are properly rectified. So I calculated the depth by averaging those differing(up to 2-pixel difference in y-axis) edge pixels using least squares method. But I ended getting this space curve (https://www.dropbox.com/s/xbg2q009fjji0qd/false_edge.jpg?dl=0) when they actually should have been like this (https://www.dropbox.com/s/0ib06yvzf3k9dny/true_edge.jpg?dl=0) which is obtained using RGB images.I couldn't think of any other reason why it would be the case since I compared by traversing along the 408 edge pixels.
Related
I am currently taking my first steps in the field of computer vision and image processing.
One of the tasks I'm working on is finding the center coordinates of (overlapping and occluded) circles.
Here is a sample image:
Here is another sample image showing two overlapping circles:
Further information about the problem:
Always a monochrome, grayscale image
Rather low resolution images
Radii of the circles are unknown
Number of circles in a given image is unknown
Center of circle is to be determined, preferably with sub-pixel accuracy
Radii do not have to be determined
Relative low overhead of the algorithm is of importance; the processing is supposed to be carried out with real-time camera images
For the first sample image, it is relatively easy to calculate the center of the circle by finding the center of mass. Unfortunately, this is not going to work for the second image.
Things I tried are mainly based on the Circle Hough Transform and the Distance Transform.
The Circle Hough Transform seemed relatively computationally expensive due to the fact that I have no information about the radii and the range of possible radii is large. Furthermore, it seems hard to identify the (appropriate) pixels along the edge because of the low resolution of the image.
As for the Distance Transform, I have trouble identifying the centers of the circles and the fact that the image needs to be binarized implies a certain loss of information.
Now I am looking for viable alternatives to the aforementioned algorithms.
Some more sample images (images like the two samples above are extracted from images like the following):
Just thinking aloud to try and get the ball rolling for you... I would be thinking of a Blob, or Connected Component analysis to separate out your blobs.
Then I would start looking at each blob individually. First thing is to see how square the bounding box is for each blob. If it is pretty square AND the centroid of the blob is central within the square, then you have a single circle. If it is not square, or the centroid is not central, you have more than one circle.
Now I am going to start looking at where the white areas touch the edges of the bounding box for some clues as to where the centres are...
I have two images(both are exactly same images) and I am trying to calculate the disparity between them using sum of squared distances and reconstruct disparity in 3D space.
Do I need to rectify the image before calculating disparity?
The following are the steps that I have done so far for disparity map computation(I have tried with rectification and without rectification but both are returning all zeroes disparity matrix).
For each pixel in the left image X,
Take the pixels in the same row in the right image.
Separate the row in right image to windows.
For each window,
Calculate the disparity for each pixel in that window with X
Select the pixel in the window which gives minimum SSD with X
Find the pixel with minimum disparity among all windows as the best match to X
Am I doing it correctly?
How can I visualise the 3D reconstruction of the disparity as scatter plot in matlab?
Rectification guarantees that matches are to be found in the same row (for horizontally separated cameras). If you have doubts about rectification of your images you can try to compare rows by drawing horizontal lines between horizontally separated images. If the lines hit the same features you are fine, see the picture below where images are NOT rectified. The fact that they are distorted means there was a lens distortion correction as well as attempted (but not actually performed correctly) rectification.
Now, let’s see what you meant by the same images. Did you mean the images of the same object that were taken from different viewpoints? Note that if the images are literally the same (the same viewpoints) the disparity will be zero as was noted in another answer. The definition of disparity (for horizontally separated cameras) is a value of shift (in the same row) between matching features. The disparity is related to depth (if optical axes of cameras are parallel) as disparity d=f*B/z, where z - depth, B - baseline or separation between cameras and f is a focal length. You can transform the formula above into disparity/B=f/z which basically says that disparity related to camera separation as focal length is related to distance. In other words, the ratios of horizontal and distance measures are equal.
If your images are taken with the cameras shifted horizontally the disparity (in a simple correlation algorithm) is typically calculated in 5-embedded loops:
loop over image1 y
loop over image1 x
loop over disparity d
loop over correlation window y
loop over correlation window x
Disparity, or D_best, gives you the best matching window between image1 and image2 across all possible values of d. Finally, scatterplots are for 3D point clouds while disparity can be rather visualized as a heat color map. If you need to visualize 3D reconstruction or simply saying a 3D point cloud calculate X, Y, Z as:
Z=fB/D, X=uZ/f, Y=v*Z/f, where u and v are related to column and row of wxh image as
u=col-w/2 and v=h/2-row, that is u, v form an image centered coordinate system.
If your two images are exactly the same, then the disparity would be 0 for every pixel. You either have to use two separate cameras to take the images, or take them with a single camera from two different locations. The best way to do 3D reconstruction is to use a calibrated stereo pair of cameras. Here is an example of how to do that using the Computer Vision System Toolbox for MATLAB.
I am doing a project on image forgery detection in MatLab software. But I am new to both image processing and matlab.
Now I have to calculate horizontal and vertical projection of an image. How to do it in matlab?
I have used
ver=imfilter(edge1,[1 0 -1])
and
hor=imfilter(edge1,[1 0 -1]')
where edge1 is an edge image.
But i am not sure if it is right or not. Edge detection algorithm is based on the standard deviation. I have not used built in edge detection function. I have implemented standard deviation based edge detection.Can anybody help me on this . I need to know this very immediately. Thanks. Expecting your answers........
What is image projection? I think using and edge detector is NOT correct.
If I remember correctly image project is an "histogram over horizontal or vertical way of grayscale level".
If you need a projection of the edges you developed the first step.
Then, I think you have to sum over rows or columns the grayscale of image.
sum(image,1)
sum(image,2)
here the projection of my photo (apologize fro my futility :)
I'm using the MNIST digit images for a machine learning experiment, and I'm trying to center each image based on position, rather than the center of mass that they are centered on by default.
I'm using the regionprops class, BoundingBox method to extract the images. I create a B&W copy of the greyscale, use this to determine the BoundingBox properties (regionprops works only B&W images) and then apply that on the greyscale original to extract the precise image rectangle. This works fine on ~98% of the images.
The problem I have is that the other ~2% of images has some kind of noise or errant pixel in the upper left corner, and I end up extracting only that pixel, with the rest of the image discarded.
How can I incorporate all elements of the image into a single rectangle?
EDIT: Further research has made me realise that I can summarise and rephrase this question as "How do I find the bounding box for all regions?". I've tried adjusting a label matrix so that all regions are the same label, to no avail.
You can use an erosion mask with the same size of that noise to make it totally disappear " using imerode followed by imdilate to inverse erosion ", or you can use median filter
I am looking for a method that looks for shapes in 3D image in matlab. I don't have a real 3D sample image right now; in fact, my 3D image is actually a set of quantized 2D images.
The figure below is what I am trying to accomplish:
Although the example figure above is a 2D image, please understand that I am trying to do this in 3D. The input shape has these "tentacles", and I have to look for irregular shapes among them. The size of the tentacle from one point to another can change around but at "consistent and smooth" pace - that is it can be big at first, then gradually smaller later. But if suddenly, the shape just gets bigger not so gradually, like the red bottom right area in the figure above, then this is one of the volume of interests. Note that these shapes have more tendency to be rounded and spherical, but some of them are completely arbitrary and random.
I've tried the following methods so far:
Erode n times and dilate n times: given that the "tentacles" are always smaller than the volume of interest, this method will work as long as the volume is not too small. And, we need to have a mechanism to deal with thicker portion of the tentacle that becomes false positive somehow.
Hough Transform: although I have been suggested this method earlier (from Segmenting circle-like shapes out of Binary Image), I see that it works for some of the more rounded shape cases, but at the same time, more difficult cases such that of less-rounded, distorted, and/or arbitrary shapes can slip through this method.
Isosurface: because of my input is a set of 2D quantized images, using an isosurface allow me to reconstruct image in 3D and see things clearer. However, I'm not sure what could be done further in this case.
So can anyone suggests some other techniques for segmenting such shape out of these "tentacles"?
Every point on your image has the property that it is either part of the tentacle, or part of the volume of interest. If it is unknown apriori what the expected girth of the tentacle is, then 1 wont work because we won't be able to set n. However, we know that the n that erases the tentacle is smaller than the n that erases the node. You can for each point replace it with an integer representing the distance to the edge. Effectively, this can be done via successive single pixel erosion, and replacing each pixel with the count of the iteration at which it was erased. Lets call this the thickness at the pixel, but my rusty old mind tells me that there was a term of art for this.
Now we want to search for regions that have a higher-than-typical morphological distance from the boundary. I would do this by first skeletonizing the image (http://www.mathworks.com/help/toolbox/images/ref/bwmorph.html) and then searching for local maxima of the thickness along the skeleton. These are points on the skeleton where the thickness is larger than the neighbor points.
Finally I would sort the local maxima by the thickness, a threshold on which should help to separate the volumes of interest from the false positives.