I don't understand what filterByInertia means... neither do I understand the documentation's little description :
By ratio of the minimum inertia to maximum inertia. Extracted blobs will have this ratio between minInertiaRatio (inclusive) and maxInertiaRatio (exclusive).
. The above image pretty much explains what the different filter parameters do. SimpleBlobDetector is happiest when it sees a circular blob, and different filters filter out different kids of deviations from the circular shape.
Inertia measures the the ratio of the minor and major axes of a blob.
The figure also shows the difference between circularity and inertia. I have copied this figure from Blob Detection Tutorial at LearnOpenCV.com
I've been wondering this for a while also; the OpenCV documentation isn't very helpful when it comes to blob detection.
Based on the descriptions of other blob analyzers, the inertia of a blob is "the inertial resistance of the blob to rotation about its principal axes". It depends on how the mass of the blob (I guess in this case the area) is distributed throughout the blob's shape.
There's a lot of mathy stuff involved -- most of which I don't remember how to do -- but the result at the bottom of this page on the properties of binary images sums it up fairly well (blob detection is done by converting the input image to a series of binary images):
The ratio gives us some idea of how rounded the object is. This ratio will be 0 for a line and 1 for a circle.
So basically, by specifying minInertiaRatio and maxInertiaRatio you can filter the blobs based on how elongated they are. An inertia ratio of 0 will yield elongated blobs (closer to lines) and an inertia ratio of 1 will yield blobs where the area is more concentrated toward the center (closer to circles).
Here's a physical intepretation:
If you cut the blob out on a piece of card, you could find its center of gravity, and then attach an axle to it, crossing this point (the axle being parallel to the card), and then spin it, and measure its moment of inertia. Depending on the shape, you may get different values according to how you place the axle. For an ellipse, you get the lowest value when the axle is attached along the long (major) axis, and the largest when the the axle is placed along the short axis (so that more of the card is far from the axle). For a circle the inertia is always the same, of course.
If there are different values, there will be always be a 'max' inertia at some orientation, and a 'min' with the axle placed 90 degrees away from the 'max'. The inertia ratio is simply the ratio between these intertias, min/max.
For shapes which are not ellipses, the metric tells you whether the overall shape is roughly elongated, or roughly the same size in all directions; without caring in particular about an uneven boundary or cuts and concavities (which roundness and convexity look at).
Mathematically, it does something like this:
Consider the set of points within the blob to be a population of (x,y) samples
Find the mean of these, and the covariance matrix x vs. y
Find the two eigenvalues of the covariance matrix (which are the same as its singular values, due to the nature of this matrix)
The inertia ratio is the ratio between these two values, smallest/largest.
Related
I hope you can give me some suggestions. I want to semantically segment the cyanobacteria image of the lake, and hope to calculate the cyanobacteria area in the image. How to preprocess the image due to the existence of a certain angle?It is not vertical. Make it more accurate to calculate the actual area through pixels. The image is as follows.
You can't make calibrated measurements (in true units of area) without knowing the scaling factors. So you should let a calibration target float on the water, wholly in the field of view*.
If the viewing distance is sufficiently large that the perspective effect can be neglected, the transformation is affine and it suffices to take the ratio of the apparent area of the cyanobacteria (in pixels) over the apparent area of the target (in pixels), times the true area of the target**.
If the perspective is strong, the transformation is an homography, and things get a little more complicated. From four points of the target (say corners), you can obtain the coefficients of the homography that maps the viewed points to undistorded space. Then you need to undistort the cyanobacteria area outline (as a polygon) and you can compute its area by the shoelace formula.
You can also completely straighten the image before segmentation, though this is not really necessary.
*You could think of obtaining the scaling factors by knowing viewing angles and distance, but that method will be unpractical to use in the field.
**Take a picture of a large square. If it appears like a parallelogram, you are good. If like a general quadrilateral, perspective must be corrected.
I have an array of data from a grayscale image that I have segmented sets of contiguous points of a certain intensity value from.
Currently I am doing a naive bounding box routine where I find the minimum and maximum (x,y) [row, col] points. This obviously does not provide the smallest possible box that contains the set of points which is demonstrable by simply rotating a rectangle so the longest axis is no longer aligned with a principal axis.
What I wish to do is find the minimum sized oriented bounding box. This seems to be possible using an algorithm known as rotating calipers, however the implementations of this algorithm seem to rely on the idea that you have a set of vertices to begin with. Some details on this algorithm: https://www.geometrictools.com/Documentation/MinimumAreaRectangle.pdf
My main issue is in finding the vertices within the data that I currently have. I believe I need to at least find candidate vertices in order to reduce the amount of iterations I am performing, since the amount of points is relatively large and treating the interior points as if they are vertices is unnecessary if I can figure out a way to not include them.
Here is some example data that I am working with:
Here's the segmented scene using the naive algorithm, where it segments out the central objects relatively well due to the objects mostly being aligned with the image axes:
.
In red, you can see the current bounding boxes that I am drawing utilizing 2 vertices: top-left and bottom-right corners of the groups of points I have found.
The rotation part is where my current approach fails, as I am only defining the bounding box using two points, anything that is rotated and not axis-aligned will occupy much more area than necessary to encapsulate the points.
Here's an example with rotated objects in the scene:
Here's the current naive segmentation's performance on that scene, which is drawing larger than necessary boxes around the rotated objects:
Ideally the result would be bounding boxes aligned with the longest axis of the points that are being segmented, which is what I am having trouble implementing.
Here's an image roughly showing what I am really looking to accomplish:
You can also notice unnecessary segmentation done in the image around the borders as well as some small segments, which should be removed with some further heuristics that I have yet to develop. I would also be open to alternative segmentation algorithm suggestions that provide a more robust detection of the objects I am interested in.
I am not sure if this question will be completely clear, therefore I will try my best to clarify if it is not obvious what I am asking.
It's late, but that might still help. This is what you need to do:
expand pixels to make small segments connect larger bodies
find connected bodies
select a sample of pixels from each body
find the MBR ([oriented] minimum bounding rectangle) for selected set
For first step you can perform dilation. It's somehow like DBSCAN clustering. For step 3 you can simply select random pixels from a uniform distribution. Obviously the more pixels you keep, the more accurate the MBR will be. I tested this in MATLAB:
% import image as a matrix of 0s and 1s
oI = ~im2bw(rgb2gray(imread('vSb2r.png'))); % original image
% expand pixels
dI = imdilate(oI,strel('disk',4)); % dilated
% find connected bodies of pixels
CC = bwconncomp(dI);
L = labelmatrix(CC) .* uint8(oI); % labeled
% mark some random pixels
rI = rand(size(oI))<0.3;
sI = L.* uint8(rI) .* uint8(oI); % sampled
% find MBR for a set of connected pixels
for i=1:CC.NumObjects
[Y,X] = find(sI == i);
mbr(i) = getMBR( X, Y );
end
You can also remove some ineffective pixels using some more processing and morphological operations:
remove holes
find boundaries
find skeleton
In MATLAB:
I = imfill(I, 'holes');
I = bwmorph(I,'remove');
I = bwmorph(I,'skel');
Suppose that the Canny edge detector successfully detects an edge in an image. The edge is then rotated by θ, where the relationship between a point on the original edge (x,y)(x,y) and a point on the rotated edge (x′,y′)(x′,y′) is defined as x′ = xcosθ; y′ = xsinθ;
Will the rotated edge be detected using the same Canny edge detector?
(I think we should find answer considering that the detection of an edge by the Canny edge detector depends only on the magnitude of its derivative.)
The answer is both yes and no, and which one you go for depends on how literally you take the question.
First of all, we're dealing with a rectangular grid, so given an integer location (x,y), the corresponding point (x',y') in a rotated image is highly likely not an integer location. And considering that the output of Canny is a set of points, and not a smooth function that can be interpolated, it would be difficult to establish a correspondence between the set resulting from the rotated and the one resulting from the original image.
Think for example about the number of pixels on a discrete line of a given length at 0 degrees and at 45 degrees. (Hint: the line at 45 degrees has sqrt(2) times fewer pixels.)
But if you take the question more generally and interpret it as "will an edge that is detected in the original image also be detected after rotating the image by θ degrees?" then the answer is yes, in theory.
Of course practice is always a bit different than theory. The details of the implementation matter here. And there is always numerical imprecision to contend with.
Let's start by assuming the rotation is computed correctly, with a precise interpolation scheme (cubic, Lanczos) and not rounded after to uint8 or something (i.e. we're computing using floating-point values).
If you read the original paper by Canny, you'll see he proposes using Gaussian derivatives as the best compromise between compact support and computational precision. I have seen few implementations that actually do. Typically I see a convolution with a Gaussian and then Sobel derivatives. Especially for smaller sigmas (less smoothing) the difference can be quite large. Gaussian derivatives are rotationally invariant, Sobel derivatives are not.
The next step in the algorithm is non-maximum suppression. This is where the continuous gradient is converted to a set of points. For each pixel, it checks to see if it is a local maximum in the direction of the gradient. Because this is done per pixel, a different set of locations are tested in the rotated image compared to the original. Nonetheless, it should detect points along the same ridges in both cases.
Next, a hysteresis threshold is applied. This is a two-threshold operation that keeps pixels above one threshold as long as at least one pixel above a second threshold is present in the same connected component. This is where the differences could occur between rotated and original image. Remember we're dealing with a set of pixels. We have samples the continuous gradient function at discrete points. There could be an edge that has one pixel above the second threshold in one version of the image, but not in the other. This would only occur for edges very close to the chosen threshold, of course.
Next comes a thinning. Because the non-maximum suppression can yield points along a thicker line, a thinning operation is applied that removes pixels from the set that are not needed to maintain connectivity of the lines. Which pixels are selected here will also differ between rotated and original images, but this does not change the geometry of the solution, so we still have the same set of points.
So, the answer is yes and no. :)
Note that the same logic applies to translation.
The application of Konolige's block matching algorithm is not sufficiantly explained in the OpenCV documentation. The parameters of CvStereoBMState influence the accuracy of the disparities calculated by cv::StereoBM. However, those parameters are not documented. I will list those parameters below and describe, what I understand. Maybe someone can add a description of the parameters, which are unclear.
preFilterType: Determines, which filter is applied on the image before the disparities are calculated. Can be CV_STEREO_BM_XSOBEL (Sobel filter) or CV_STEREO_BM_NORMALIZED_RESPONSE (maybe differences to mean intensity???)
preFilterSize: Window size of the prefilter (width = height of the window, negative value)
preFilterCap: Clips the output to [-preFilterCap, preFilterCap]. What happens to the values outside the interval?
SADWindowSize: Size of the compared windows in the left and in the right image, where the sums of absolute differences are calculated to find corresponding pixels.
minDisparity: The smallest disparity, which is taken into account. Default is zero, should be set to a negative value, if negative disparities are possible (depends on the angle between the cameras views and the distance of the measured object to the cameras).
numberOfDisparities: The disparity search range [minDisparity, minDisparity+numberOfDisparities].
textureThreshold: Calculate the disparity only at locations, where the texture is larger than (or at least equal to?) this threshold. How is texture defined??? Variance in the surrounding window???
uniquenessRatio: Cited from calib3d.hpp: "accept the computed disparity d* only ifSAD(d) >= SAD(d*)(1 + uniquenessRatio/100.) for any d != d+/-1 within the search range."
speckleRange: Unsure.
trySmallerWindows: ???
roi1, roi2: Calculate the disparities only in these regions??? Unsure.
speckleWindowSize: Unsure.
disp12MaxDiff: Unsure, but a comment in calib3d.hpp says, that a left-right check is performed. Guess: Pixels are matched from the left image to the right image and from the right image back to the left image. The disparities are only valid, if the distance between the original left pixel and the back-matched pixel is smaller than disp12MaxDiff.
speckleWindowSize and speckleRange are parameters for the function cv::filterSpeckles. Take a look at OpenCV's documentation.
cv::filterSpeckles is used to post-process the disparity map. It replaces blobs of similar disparities (the difference of two adjacent values does not exceed speckleRange) whose size is less or equal speckleWindowSize (the number of pixels forming the blob) by the invalid disparity value (either short -16 or float -1.f).
The parameters are better described in the Python tutorial on depth map from stereo images. The parameters seem to be the same.
texture_threshold: filters out areas that don't have enough texture
for reliable matching
Speckle range and size: Block-based matchers
often produce "speckles" near the boundaries of objects, where the
matching window catches the foreground on one side and the background
on the other. In this scene it appears that the matcher is also
finding small spurious matches in the projected texture on the table.
To get rid of these artifacts we post-process the disparity image with
a speckle filter controlled by the speckle_size and speckle_range
parameters. speckle_size is the number of pixels below which a
disparity blob is dismissed as "speckle." speckle_range controls how
close in value disparities must be to be considered part of the same
blob.
Number of disparities: How many pixels to slide the window over.
The larger it is, the larger the range of visible depths, but more
computation is required.
min_disparity: the offset from the x-position
of the left pixel at which to begin searching.
uniqueness_ratio:
Another post-filtering step. If the best matching disparity is not
sufficiently better than every other disparity in the search range,
the pixel is filtered out. You can try tweaking this if
texture_threshold and the speckle filtering are still letting through
spurious matches.
prefilter_size and prefilter_cap: The pre-filtering
phase, which normalizes image brightness and enhances texture in
preparation for block matching. Normally you should not need to adjust
these.
Also check out this ROS tutorial on choosing stereo parameters.
What is Distance Transform?What is the theory behind it?if I have 2 similar images but in different positions, how does distance transform help in overlapping them?The results that distance transform function produce are like divided in the middle-is it to find the center of one image so that the other is overlapped just half way?I have looked into the documentation of opencv but it's still not clear.
Look at the picture below (you may want to increase you monitor brightness to see it better). The pictures shows the distance from the red contour depicted with pixel intensities, so in the middle of the image where the distance is maximum the intensities are highest. This is a manifestation of the distance transform. Here is an immediate application - a green shape is a so-called active contour or snake that moves according to the gradient of distances from the contour (and also follows some other constraints) curls around the red outline. Thus one application of distance transform is shape processing.
Another application is text recognition - one of the powerful cues for text is a stable width of a stroke. The distance transform run on segmented text can confirm this. A corresponding method is called stroke width transform (SWT)
As for aligning two rotated shapes, I am not sure how you can use DT. You can find a center of a shape to rotate the shape but you can also rotate it about any point as well. The difference will be just in translation which is irrelevant if you run matchTemplate to match them in correct orientation.
Perhaps if you upload your images it will be more clear what to do. In general you can match them as a whole or by features (which is more robust to various deformations or perspective distortions) or even using outlines/silhouettes if they there are only a few features. Finally you can figure out the orientation of your object (if it has a dominant orientation) by running PCA or fitting an ellipse (as rotated rectangle).
cv::RotatedRect rect = cv::fitEllipse(points2D);
float angle_to_rotate = rect.angle;
The distance transform is an operation that works on a single binary image that fundamentally seeks to measure a value from every empty point (zero pixel) to the nearest boundary point (non-zero pixel).
An example is provided here and here.
The measurement can be based on various definitions, calculated discretely or precisely: e.g. Euclidean, Manhattan, or Chessboard. Indeed, the parameters in the OpenCV implementation allow some of these, and control their accuracy via the mask size.
The function can return the output measurement image (floating point) - as well as a labelled connected components image (a Voronoi diagram). There is an example of it in operation here.
I see from another question you have asked recently you are looking to register two images together. I don't think the distance transform is really what you are looking for here. If you are looking to align a set of points I would instead suggest you look at techniques like Procrustes, Iterative Closest Point, or Ransac.