I have been testing background subtraction using gaussian state model. I am using opencv
2.1.0. I can generate binary image of foreground of the scene. Now all I want to do is Draw
countour bounding rectangle to highlight the moving object. I have used cvCountourBoundingRect
to obtain the rectangle covering countour. The issue I am facing is in case of multiple
countour, sometime nearby rectangle overlaps. Here, can anyone suggest me to prevent
overlapping of rectangle? In ideal case, two rectangle should not be overlapped. It rather
should be draw a bigger rectagle which covers all two rectangles.
Any suggetion will be greatful.
There's no ready possibility to do this in OpenCV. But actually the algorithm is very easy:
Cycle through all rectangles and check if two rectangles overlap each other. This topic will be useful: Determine if two rectangles overlap each other?
For every overlapped pair of rectangles create rectangle that contains both of them. To do this you should select one corner from first rectangle and another corner from second rectangle and these two corners will create rectangle for you. I don't think that it's a hard task - just simple math.
Related
I have images that contain transparent rectangular overlay similar to the following images: Image1 Image2. My goal is to detect if these rectangular boxes exist (location doesn't matter). These boxes will always have edges parallel to the sides of the image.
Assumptions:
The transfer function of how the transparent rectangles are drawn is now known
The sides of the rectangles will also be parallel to the image
Attempted Solution 1: Color Detection
So far, I've tried color detection via cv.threshold as well as using band-pass filters with the cv2.inRange() on multiple color spaces (HSV, LUV, XYZ etc). The issue with color detection is that I am also capturing too much noise to effectively just tune for the pixels for the transparent area. I tried laying the masks using cv2.bitwiseAnd but still can't tune the noise down to a negligible state. I tried only isolating for large groups of pixels using morphological transformations but this still fails.
Attempted Solution 2: Edge Detection + Edge Validation
My second try at detecting the box involved applying cv2.bilateralFilter and then generating hough lines via cv2.Canny,cv2.HoughLinesP. Although I am detecting a significant number of edges related to the transparent box, I also get many miscellaneous edges.
To filter out false edges, I take each line segment and check a few sample pixels to the left and right sides. By applying something something similar to what I believe the transfer function is (cv2.addWeighted) I checked to see if if I can reproduce the similar values. Unfortunately, this also doesn't work well enough to tell the difference between edges from the transparent box vs "real edges." Result From Edge Detection
Any thoughts on how I might detect these boxes is highly appreciated!
I'm interesting in detecting a triangular mesh fence present in the foreground of a sequence of images. I've included an example image below. Ideally I'd like to output the grid of intersection points; this would then provide me with the distance to and orientation of the mesh (since the dimensions of the mesh are known and fixed).
As in the example image, the mesh can be obscured (by the thick black bars going horizontally and vertically) or can be confused with the background (see the black-lines of the structure in the top-left of the image). But the mesh will always completely cover the image, i.e. the edges or the outside of the mesh are never in view.
Any ideas on how one might begin to tackle a vision problem like this?
Find edge pixels
Hough transform to find lines in the image
Use ransac to find a model that describes the homography of the lines to the triangle grid.
Without more examples, it's hard to tell how difficult it would be to do.
I want to be able to tell when 2 images collide (not just their frames). But here is the catch: the images are rotating.
So I know how to find whether a pixel in an image is transparent or not but that wont help in this scenario because it will only find the location in the frame relative to a non-rotated image.
Also I have gone as far as trying hit boxes but even those wont work because I can't find a way to detect the collision of UIViews that are contained in different subviews.
Is what I am trying to do even possible?
Thanks in advance
I don't know how you would go about checking for pixel collision on a rotated image. That would be hard. I think you would have to render the rotated image into a context, then fetch pixels from the context to check for transparency. That would be dreadfully slow.
I would suggest a different approach. Come up with a path that maps the bounds of your irregular image. You could then use CGPathContainsPoint to check to see if a set of points is contained in the path (That method takes a transform, which you would use to describe the rotation of your image's path.)
Even then though you're going to have performance problems, since you would have to call that method for a large number of points from the other image to determine if they intersect.
I propose you a simple strategy to solve that, based on looking for rectangles intersections.
The key for that is to create a simplified representation of your images with a set of rectangles laid out properly as bounding boxes of the different part of you image (like you would build your image with legos). For better performance use a small set of rectangles (a few big legos), for better precision use a biggest number of rectangles to precisely follow the image outline.
Your problem becomes equivalent to finding an intersection between rectangles. Or to be more precise to find wether at least one vertex of the rectangles of object A is inside at least one rectangle of object B (CGRectContainsPoint) or if rect intersects (CGRectIntersectsRect).
If you prefer the points lookup, you should define your rectangles by their 4 vertices then it is easy when you rotate your image to apply the same affine transform (use CGPointApplyAffineTransform) to your rectangle vertices to have the coordinates of your points after rotation. But of course you can lookup for frame intersections and represent you rectangle using the standard CGRect structure.
You could also use a CGPath (as explained in another answer below) instead of a set of rectangles and look for any vertex inside other path using CGPathContainsPoint. That would give the same result actually but probably the rectangles approach is faster in many cases.
The only trick is to take one of the objects as a reference axis. Imagine you are on object A and you only see B moving around you. Then if you have to rotate A you need to make an axis transform to always have B transform relatively to A and not to the screen or any other reference. If your transforms are only rotation around the object centre then rotating A by n radians is equivalent to rotating B by -n radians.
Then just loop through your vertices defining object A and find if one is inside a rectangle of object A.
You will probably need to investigate a bit to achieve that but at least you have some clues on how to solve that.
I am try to draw shapes in the window in real time. The shapes are like tangle ,rectangle ,circle , half or circle and "Z" in the screen using yellow color. The size and the shape may not be same to the original image. But Program know all the original shapes. Because they are predefined. I want to know how i can identify the correct shape. as an example,
is there possible way to do this? can I use template matching for this? Please help me with this..
You can use different methods to detect each shape. Check these:
Ellipse detection with OpenCV
Square detection doesn't find squares
I want to identify an object and draw a shape around it ...
I used previously the color identification but wasn't a good option since color change dramatically from place to place .. so I though why not identifying objects by features such as edges .. and I did that using this function in openCV
cvgoodfeaturesTotrack
it returns the (x,y)-coordinates of the points .. now I want to connect those points.. well not all of them but the one who are close to each other to draw a shape around the different objects. Any ideas ?
I don't think there is a free lunch in this case. You are trying to reconstruct a polygon if you only know the corner points of the polygon. There is no unique solution to this problem: you can draw all sorts of polygons through the corners. If you are certain the shape you are after is convex, then you can construct the convex span of the corner points, but the result will be horrible if you include any corners that were not part of the original object.
It seems to me that detecting corners is not the way to segment an object that is more or less delimited by lines. You probably want to try an edge detector instead, or a proper segmentation technique such as watershed.