i am trying to subtract 2 image using the function cvAbsDiff(img1, img2, dest);
it working but sometimes when i bring my hand before my head or body the hand is not clear and background comes into picture... the background image(head) overlays my foreground.(hand)..
it works correctly on plain surfaces i.e when the background is even like a wall.
please check out my image...so that you can better understand my problem...!!!!
http://www.2shared.com/photo/hJghiq4b/bg_overlays_foreground.html
if you have any solution/hint please help me.......
There's nothing wrong with your code . Background subtraction is not a preffered way for motion detection or silhoutte detection because its not very robust.The problem is coming because both the background and the foreground are similar in colour at many regions which on subtractions pushes the foreground to back . You might try using
- optical flow for motion detection
- If your task is just detecting silhoutte or hand try training a HOG classifier over it
In case you do not want to try a new approach . You may try around playing with the threshold value(in your case 30).So when you subtract similar colour image there difference is less than 30 . And later you threshold with 30 so it just blacks out. Also you may try HSV or some other colourspace as well .
Putting in the relevant code would help. Also knowing what you're actually trying to achieve.
Which two images are you subtracting? I've done subtracting subsequent images (so, images taken with a delay of a fraction of a second), and the background subtraction generally results in the edges of moving objects, for example the edges of a hand, and not the entire silhouette of a hand. I'm guessing you're taking the difference of the current frame and a static startup frame. It's possible that parts aren't different enough (skin+skin).
I've got some computer problems tonight, I'll test it out tomorrow (pls put up at least the steps you actually carry thorough though) and let you know.
I'm still not sure what your ultimate goal is, although I'm guessing you want to do some gesture-recognition (since you have a vector called "fingers").
As Manpreet said, your biggest problem is robustness, and that is from the subjects having similar color.
I reproduced your image by having my face in the static comparison image, then moving it. If I started with only background, it was already much more robust and in anycase didn't display any "overlaying".
Quick fix is, make sure to have a clean subject-free static image.
Otherwise, you'll want to have dynamic comparison image, simplest would be comparing frame_n with frame_n-1. This will generally give you just the moving edges though, so if you want the entire silhouette you can either:
1) Use a different segmenting algorithm (what I recommend. Background subtraction is fast and you can use it to determine a much smaller ROI in which to search, and then use a different algorithm for more robust segmentation.)
2) Try to make a compromise between the static and dynamic comparison image, for example as an average of the past 10 frames or something like that. I don't know how well this works, but would be quite simple to implement, worth a try :).
Also, try with CV_THRESH_OTSU instead of 30 for your threshold value, see if you like that better.
Also, I noticed often the output flares (regions which haven't changed switch from black to white). Checking with the live stream, I'm quite certain it because of the webcam autofocusing/adjusting white balance etc.. If you're getting that too, turning off the autofocus etc. should help (which btw isn't done through openCV but depends on the camera. Possibly check this: How to programatically disable the auto-focus of a webcam?)
Related
I have an image that I removed the background (making it transparent) with this.
But now, it has dark contour that I would like to be smoothly integrated with the background I am adding to it.
I am having a hard time to find a way to smooth just the image contour.
The answer is actually quite simple.
The result wont be 100%, but will be MUCH better than doing nothing.
Just do all work in very high resolution; the most your machine can handle in a affordable time.
The last thing you will do is shrink (scale) the image to the final size you intend to use; that shrinking did the contour smooth integration. I understand the scale options you use may provide good results if you try hard.
PS.: I think this technique is used on 3D games for the same reason; not sure tho; couldn't find yet the proper explanation about it.
I am working on project in C#/Emgu CV, but answer in any language with OpenCv should be ok.
I have following image: http://i42.tinypic.com/2z89h5g.jpg
Or it might look like this: http://i43.tinypic.com/122iwsk.jpg
I am trying to do automatic calibration and I would like to know how to find corners of the field. They are marked by LEDs, but I would prefer to find it by color tags. If need I can replace all tags by same color tags. (Note that light in room is changing so the colors might be bit different next time)
Edge detection might be ok too, but I am afraid that I would not find the corner correctly.
Please help.
Thank you.
Edit:
Thanks aardvarkk for advice, but I think I need to give you little bit more info.
I am already able to detect and identify robots in field and get their position and rotation. But for that I have to set corners of field manually first. So I was looking for aa automatic way, but I was worried I would not be able to distinguish color tags from background because light in the room is changing quite often.
And as for the camera angle. Point of this is that camera can be every time from different (reasonable) angle.
I would start by searching for the colours. The LEDs won't be much help to you as they're not much brighter than anything else in the scene. I would look for the rectangular pieces of coloured tape. Try segmenting the image based on colour. That may allow you to retrieve the corner tape pieces directly without needing to know their exact colour in advance. After that, you may look for pairs of the same colour blob that are close to each other to define the corners where the pieces of tape are the same. Knowing what kinds of camera angles you are going to have to solve is also very important -- if you need this to work when viewing from the side, then this approach certainly won't work. If it's almost top down, this would probably be a good start. Nobody will be able to provide you with a start to finish solution, but this might be a good base to begin with.
I would like to extract out all the slides from a video lecture, using OpenCV. Here is an example of a lecture: http://www.youtube.com/watch?v=-hxOpz9c0bY.
What approaches would you recommend? So far, I've tried:
Comparing the change in grayscale intensity from frame to frame. This can have problems when an object in the foreground moves around. For example, in this lecture, there's a hand that moves around: http://www.youtube.com/watch?v=mNzu42FrlHo#t=07m00s.
Using SURF features and doing comparisons frame by frame. This approach seems kind of slow.
Does anyone have other ideas?
Most of this work is most likely already done by video encoder. You just need to extract key-frames and check how well compressed are frames between them.
It should be also fairly easy to distinguish still images. You can save lot of time by examining just the key-frames. Slides are likely to have high contrast, solid shapes, solid background. Lecture hall has blurry shapes and low contrast.
What you need is a scene change detection. After that, you'll have to classify scenes as "lecture hall" or "presentation". As for the problem with hands - you could use background subtraction with an adaptive background (just make sure you mask the foreground... you don't want the foreground to become a part of the background).
You could try an edge detection and look for a rectangular object - the slides (above a certain area threshold). You could further reduce FPs by looking for some text within the rectangle.
There are several reasons to extract slides/frames from a video presentation, especially in the case of education or conference related videos. It allows you to access the study notes without watching the whole video.
I have faced this issue several times, so I decided to create a solution for it myself using python. I have made the code open-source, you can easily set up this tool and run it in few simple steps.
Refer to this for a youtube video tutorial. Steps on how to use this tool.
Clone this project video2pdfslides
Set up your environment by running "pip install -r requirements.txt"
Copy your video path
Run "python video2pdfslides.py <video_path>"
Boom! the pdf slides will be available in the output folder Make notes and enjoy!
iam working in a project that i take a vedio by a camera and convert this vedio to frames (this part of project is done )
what iam facing now is how to detect moving object in these frames and differentiate them from the background so that i can distinguish between them ?
I recently read an awesome CodeProject article about this. It discusses several approaches to the problem and then walks you step by step through one of the solutions, with complete code. It's written at a very accessible level and should be enough to get you started.
One simple way to do this (if little noise is present, I recommend smoothing kernel thought) is to compute the absolute difference of two consecutive frames. You'll get an image of things that have "moved". The background needs to be pretty static in order to work. If you always get the abs diff from the current frame to the nth frame you'll have a grayscale image with the object that moved. The object has to be different from the background color or it will disappear...
I have 35 pictures taken from a stationary camera aimed at a lightbox in which an object is placed, rotated at 10 degrees in each picture. If I cycle through the pictures quickly, the image looks like it is rotating.
If I wished to 'rotate' the object in a browser but wanted to transmit as little data as possible for this, I thought it might be a good idea to split the picture into 36 pictures, where 1 picture is any background the images have in common, and 35 pictures minus the background, just showing the things that have changed.
Do you think this approach will work? Is there a better route? How would I achieve this in photoshop?
Hmm you'd probably have to take a separate picture of just the background, then in the remaining pictures, use Photoshop to remove the background and keep only the object. I guess if the pictures of the background have transparency in the place where the background was this could work.
How are you planning to "rotate" this? Flash? JavaScript? CSS+HTML? Is this supposed to be interactive or just a repeating movie? Do you have a sample of how this has already been done? Sounds kinda cool.
If you create a multiple frame animated GIF in Photoshop you can control the quality of the final output, including optimization that automatically converts the whole sequence to indexed color. The result is that your background, though varied, will share most of the same color space, and should be optimized such that it won't matter if it differ slightly in each frame. (Unless your backgrounds are highly varied between photos, though by your use of a light box, they shouldn't be.) Photoshop will let you control the overall output resolution, and color remapping, which will affect the final size.
Update: Adobe discontinued ImageReady in Photoshop CS3+, I am still using CS2 so I wasn't aware of this until someone pointed it out.
Unless The background is much bigger than the gif in the foreground i doubt that you would benefit greatly from using separate transparent images. Even if they are smaller in size,
Would the difference be large enough to improve the speed, taken into consideration the average speed with which pages are loaded?