Background subtraction.
MOG and MOG2 turned out to be unhelpful because they assume the first frame is the background.
So I did frame by frame subtraction. like this
My problem is to now paint the only the detected object white.
Btw, I did try out The inbuilt FindContours() method & obtained thousands of contours in the image.
for findContours() you may are mislead. The method assumes a binarized image as input, if it is not quite binary, it treats non-zero pixel as 1, regardless which color or grayscale the are. findContours
So your image is nearly binarized and you observe black and white regions. The black regions are treated as background and the not-black ones (non-zero) are treated as foreground pixels respektivly regions. findContours() does nothing more or less than "marking" coherent foreground pixels (yes the regions). So you get a List of vectors (a vector of points for each detected region).
For detecting the whole bus as object, you may want to lookup on: convexHull
This is (if I recall correctly) a list of vertrices too, that describes a region where all (previously found) regions are inside. So you may need to substract outliers first (like the piece of street or shadow on the bottom of your image).
also interesting: convexityDefects
and: approxPolyDP
Related
As a follow-up question to finding contiguous black pixels in image, I use OpenCV's findContours() to detect shapes of black on white (I invert the colors for the function to work better). In the images below, OpenCV detects the outer shape of the "g" and the inner bowl as different shapes:
I could use the hierarchy to discard shapes inside other shapes, but I would rather avoid it in case OpenCV detects an overarching contour around the whole image. Does findContours have some tuning that cause it to find only contiguous pixels and not the inside negative shape?
Light Field captures the scene from slightly different points. This means I would have two images of the same scene with a slight shift, as shown in the following figure:
Assuming the red squares in the images above are pixels. I know that the spatial difference between those two pixels is a shift. Nevertheless, what other information do these two pixels give us in terms of scene radiance? I mean is there a way to find (or compute) the difference in image irradiance values between those two points?
Look for color space representations other than RGB. Some of them have explicit channel(s) carrying luminance information of a pixel.
A varaiant of the same idea is to convert to a Black and White image and examine the pixel values.
I have an image with a gentle gradient background and sharp foreground features that I want to detect. I wish to find green arcs in the image. However, the green arcs are only green relative to the background (they are semitransparent). The green arcs are also only one or two pixels wide.
As a result, for each pixel of the image, I want to subtract the average color of the surrounding pixels. The surrounding 5x5 or 10x10 pixels would be sufficient. This should leave the foreground features relatively untouched but remove the soft background, and I can then select the green channel for further processing.
Is there any way to do this efficiently? It doesn't have to be particularly accurate, but I want to run it at 30Hz on a 1080p image.
You can achieve this by doing a simple box blur on the image and then subtracting that from the original image:
blur(img,blurred,Size(15,15));
diff=img-blurred;
I tried this on a 1920x1080 image and the blur took 25ms and the subtract took 15ms on a decent spec iMac.
If your background is not changing fast, you could calculate the blur over the space of a few frames in a second thread and keep re-using it till you recalculate it again a few frames later then you would only have 15ms subtraction to do for each of your 30fps rather than 45ms of processing.
Depending on how smooth the background gradient is, edge detection followed by dilation might work well for you.
Edge detection will output the 3 lines that you've shown in the sample and discard the background gradient (again, depending on smoothness). Dilating the image then will thicken the edges so that your line contours are more significant.
You can superimpose this edge map on your original image as:
Mat src,edges;
//perform edge detection on src and output in edges.
Mat result;
cvtColor(edges,edges,cv2.COLOR_GRAY2BGR);//change mask to a 3 channel image
subtract(edges,src,result);
subtract(edges,result);
The result should contain only the 3 lines with 3 colours. From here on you can apply color filtering to select the green one.
I'm new to image processing and I'm working on detecting lines in a document image. I read the theory of Hough line transform but I can't see why I must use Canny before calling that function in opencv like being said in many tutorials. What's the point of finding edges in this case? The fact is that if I don't use Canny or threshold before HoughLines() the results will be very messy. I hope someone will explain for me the reason why.
2 of the tutorials I've read:
Imgproc Feature Detection
Hough Line Transform
Short Answer
cvCanny is used to detect Edges, as well as increase contrast and remove image noise.
HoughLines which uses the Hough Transform is used to determine whether those edges are lines or not. Hough Transform requires edges to be detected well in order to be efficient and provide meaning results.
Long Answer
The Limitations of the Hough Transform are described in more detail on Wikipedia.
The efficiency of the Hough Transform relies of the bin of acculumated pixel being distinct, e.g. a direct contrast between a pixel and its surrounding neighbours or if using a mask region a pixel region and its surrounds regions. If all pixels had similar acculumated values nothing would stand out as a line or circle. This leads to the reduction of colour (colour to grayscale, grayscale to black and white) in order to increase contract.
The number of parameters to the Hough Transform also increase the spread of votes in the pixel bins and increase the complexity of the transform, which mean that normally only lines or circles are reliably detected using it as they have less than 3 parameters.
The edges need to be detected well before running the Hough Transform otherwise its efficiency suffers further. Also noisy images don't work well with Hough transform unless the noise is removed before hand.
First of all, to detect lines you need to work on a boolean matrix image (or binary), I mean: the color is black or white, there's no grayscale.
HoughLines()'s requirement to work properly is to have this kind of image as input. That's the reason you have to use Canny or Treshold, to convert the colored image matrix into a boolean one.
Hough transformation
A line in one picture is actually an edge. Hough transform scans the whole image and using a transformation that converts all white pixel cartesian coordinates in polar coordinates; the black pixels are left out. So you won't be able to get a line if you first don't detect edges, because HoughLines() don't know how to behave when there's a grayscale.
Theoretically, you are correct. Finding edges is not absolutely required for the Hough Line algorithm to work.
The way the Hough works is basically it takes every point and connects it to every other point, and whatever points have the most lines going through them, those lines stay. For this, we need points. The Canny creates those points. Theoretically you could use any sort of filter - isolate all blue or purple points and connect them, whatever - but edges works well.
The Hough also does not weight its lines or points. To the Hough, an image is binary - made up of either 1s or 0, points or not points. There is no need for greyscale, and the canny conveniently returns binary images.
Thus is the Canny always part of the Hough.
all is about processing binary data,
complex data -> (a binary data, b binary data, c binary data, ..) (using canny(),sobel(), etc)
a binary data -> function1() (using houghlines())
b binary data -> function2()
c binary data -> function3() ..
a binary data -X-> function2() ..
complex data -X-> function1() ..
HTH
When we look at a photo of a group of trees, we are able to identify that the photo is predominantly green and brown, or for a picture of the sea we are able to identify that it is mostly blue.
Does anyone know of an algorithm that can be used to detect the prominent color or colours in a photo?
I can envisage a 3D clustering algorithm in RGB space or something similar. I was wondering if someone knows of an existing technique.
Convert the image from RGB to a color space with brightness and saturation separated (HSL/HSV)
http://en.wikipedia.org/wiki/HSL_and_HSV
Then find the dominating values for the hue component of each pixel. Make a histogram for the hue values of each pixel and analyze in which angle region the peaks fall in. A large peak in the quadrant between 180 and 270 degrees means there is a large portion of blue in the image, for example.
There can be several difficulties in determining one dominant color. Pathological example: an image whose left half is blue and right half is red. Also, the hue will not deal very well with grayscales obviously. So a chessboard image with 50% white and 50% black will suffer from two problems: the hue is arbitrary for a black/white image, and there are two colors that are exactly 50% of the image.
It sounds like you want to start by computing an image histogram or color histogram of the image. The predominant color(s) will be related to the peak(s) in the histogram.
You might want to change the image from RGB to indexed, then you could use a regular histogram and detect the pics (Matlab does this with rgb2ind(), as you probably already know), and then the problem would be reduced to your regular "finding peaks in an array".
Then
n = hist(Y,nbins) bins the elements in vector Y into 10 equally spaced containers and returns the number of elements in each container as a row vector.
Those values in n will give you how many elements in each bin. Then it's just a matter of fiddling with the number of bins to make them wide enough, and with how many elements in each would make you count said bin as a predominant color, then taking the bins that contain those many elements, calculating the index that corresponds with their middle, and converting it to RGB again.
Whatever you're using for your processing probably has similar functions to those
Average all pixels in the image.
Remove all pixels that are farther away from the average color than standard deviation.
GOTO 1 with remaining pixels until arbitrarily few are left (1 or maybe 1%).
You might also want to pre-process the image, for example apply high-pass filter (removing only very low frequencies) to even out lighting in the photo — http://en.wikipedia.org/wiki/Checker_shadow_illusion