I am using GPUImage to process incoming video, and each frame I would like to determine the average luminosity of many rectangular subregions of the incoming image for hit detection purposes in a game, but I am having trouble doing so in a way that doesn't kill FPS.
My current situation is to loop through the hit boxes of interest, crop the frame of said hit boxes with GPUImageCropFilter, do average luminosity on the cropped region and in its completion block call hit method on main thread if luminosity is high enough. This works okay if there are just a few hit boxes, but for the project I am working on there could be dozens at a time which kills the FPS.
Are there any recommended ways to modify the above approach to improve performance? I am thinking it might be possible to accomplish this by making a new filter with a custom shader that does a kind of localized pixelation effect (pixellating the rectangles of interest, so then I can just check any pixel in that region for the luminosity), but I am not sure if it is possible to pass in an array of areas of interest like this to a filter / shader. Thanks.
Related
How would one go about creating an algorithm that detects the unblurred parts of a picture? For example, it would look at this picture:
and realize the non blurred portion is:
I saw over here how to measure the blur of the whole picture. For this problem, should I just create a threshold for the maximal absolute second derivative for the pixels? And then whichever one exceeds, is considered a non blurred region?
A simple solution is to detect high frequency content.
If there's no high frequency content in an area, it may be because it is blurred.
How to detect areas with no high frequency content? You can do it in the frequency domain (for example, with DCT), or you can do it in the spatial domain.
First, I recommend the spatial domain method.
You'll need some kind of high-pass filter. The easiest method is to blur the image (for example, with a gauss filter), then subtract it from the original, then convert to grayscale:
Blurred:
Subtracted:
As you see, all the blurred pixels become dark, and high frequency content is bright. Now, you may want to blur this image, and apply a threshold, to get this:
Note: this process was done by hand, with gimp. Your algorithm can easily follow this, but need some parameters specified (like the blur radius, threshold value).
I have a game written with SpriteKit which uses a SKEffectNode with blur effect to blur a set of sprites, one of which has a fairly large texture, and which together cover a fairly large area of the screen. An iMac and Mac Book Pro cope quite happily with this but on a more humble Mac Book there is a notable drop in frame rate with the effect node added in. Since the effect isn't crucial to the functionality of the game, I could simply not add the SKEffectNode for machines with less powerful graphics capabilities.
So then the question: what would be a good programmatic check that I could make to determine the "power of the GPU" or "performance when applying texture effects" or [suggest better metric here] and via what API? Thanks for your suggestions!
You'll have to create a performance test using your actual blurring processes and some sample content to get an accurate idea of the time cost of it on each generation of hardware.
Blurs are really weird things, programmatically. A Box Blur can give you most of the appearance of a nice, soft gaussian blur for much less processing cost. A zoom or motion blur (that looks good) is surprisingly expensive, even on strong hardware.
And there's some amazingly effective "cheats" when doing blurs. Because there's no need for detail you can heavily optimise the operations, particularly if the blurs are strong.
Apple, it's believed, does something like this, for example, with its blurs:
Massively shrink the target image
Do a gaussian blur on this tiny image
Scale it back up, somewhat
Apply a cheap Box Blur to soften it
Fully scale back to the desired size
By way of terrible example benefitting from scaling well (with filtering set for good scaling)
This is the full sized image blurred:
And here's a version of the same image, scaled to a 16th of its original size, blurred, and then the blurred image scaled back up. As you can see, due to the good scaling and lack of detail, there's hardly any difference in the blurred image, but the blur takes MUCH less processing energy and time:
I am working on an image processing project. Faster I process the images, the better. However as I increase the fps of my camera, everything begin to appear darker, since the camera do not have enough time to receive light. I was wondering if I could find a way around of this issue, since I know what is causing it.
I am thinking of writing a code that will increase all pixel values proportionally with what camera returns. Since only difference is the time duration, I think there should be a linear proportion between pixel values and the time duration camera had while taking that picture.
Before trying this, I have searched if there is anything available online but failed to find any. It feels like this is a basic concept so I would be surprised if no one had done such a thing before, so I might be using wrong keywords.
So my question is, is there a filter or an algorithm that increases the "illumination" of a dark image (since shot at high fps). If not, does what I intend to do make sense?
I think you should use Histogram Equalization here, rather than increasing all the pixels by some constant factor. Histogram Equalization makes the the probability of all possible pixel intensity equal thus enhancing the image.
Read about it using the following links
http://www.math.uci.edu/icamp/courses/math77c/demos/hist_eq.pdf
https://en.wikipedia.org/wiki/Histogram_equalization
Read this article on how to do it in opencv,
http://docs.opencv.org/2.4/doc/tutorials/imgproc/histograms/histogram_equalization/histogram_equalization.html
If your image is too dark use more light. That would be the proper way.
Of course you can increase brightness values but the image by simply multiplying them with a factor or adding an offset. Or spreading the histogram.
Instead of a bad dark image you'll end up with a bad bright image.
Low contrast, low dynamic range, low signal to noise ratio, all of that won't change.
I have a web cam that takes a picture every N seconds. This gives me a collection of images of the same scene over time. I want to process that collection of images as they are created to identify events like someone entering into the frame, or something else large happening. I will be comparing images that are adjacent in time and fixed in space - the same scene at different moments of time.
I want a reasonably sophisticated approach. For example, naive approaches fail for outdoor applications. If you count the number of pixels that change, for example, or the percentage of the picture that has a different color or grayscale value, that will give false positive reports every time the sun goes behind a cloud or the wind shakes a tree.
I want to be able to positively detect a truck parking in the scene, for example, while ignoring lighting changes from sun/cloud transitions, etc.
I've done a number of searches, and found a few survey papers (Radke et al, for example) but nothing that actually gives algorithms that I can put into a program I can write.
Use color spectroanalisys, without luminance: when the Sun goes down for a while, you will get similar result, colors does not change (too much).
Don't go for big changes, but quick changes. If the luminance of the image changes -10% during 10 min, it means the usual evening effect. But when the change is -5%, 0, +5% within seconds, its a quick change.
Don't forget to adjust the reference values.
Split the image to smaller regions. Then, when all the regions change same way, you know, it's a global change, like an eclypse or what, but if only one region's parameters are changing, then something happens there.
Use masks to create smart regions. If you're watching a street, filter out the sky, the trees (blown by wind), etc. You may set up different trigger values for different regions. The regions should overlap.
A special case of the region is the line. A line (a narrow region) contains less and more homogeneous pixels than a flat area. Mark, say, a green fence, it's easy to detect wheter someone crosses it, it makes bigger change in the line than in a flat area.
If you can, change the IRL world. Repaint the fence to a strange color to create a color spectrum, which can be identified easier. Paint tags to the floor and wall, which can be OCRed by the program, so you can detect wheter something hides it.
I believe you are looking for Template Matching
Also i would suggest you to look on to Open CV
We had to contend with many of these issues in our interactive installations. It's tough to not get false positives without being able to control some of your environment (sounds like you will have some degree of control). In the end we looked at combining some techniques and we created an open piece of software named OpenTSPS (Open Toolkit for Sensing People in Spaces - http://www.opentsps.com). You can look at the C++ source in github (https://github.com/labatrockwell/openTSPS/).
We use ‘progressive background relearn’ to adjust to the changing background over time. Progressive relearning is particularly useful in variable lighting conditions – e.g. if lighting in a space changes from day to night. This in combination with blob detection works pretty well and the only way we have found to improve is to use 3D cameras like the kinect which cast out IR and measure it.
There are other algorithms that might be relevant, like SURF (http://achuwilson.wordpress.com/2011/08/05/object-detection-using-surf-in-opencv-part-1/ and http://en.wikipedia.org/wiki/SURF) but I don't think it will help in your situation unless you know exactly the type of thing you are looking for in the image.
Sounds like a fun project. Best of luck.
The problem you are trying to solve is very interesting indeed!
I think that you would need to attack it in parts:
As you already pointed out, a sudden change in illumination can be problematic. This is an indicator that you probably need to achieve some sort of illumination-invariant representation of the images you are trying to analyze.
There are plenty of techniques lying around, one I have found very useful for illumination invariance (applied to face recognition) is DoG filtering (Difference of Gaussians)
The idea is that you first convert the image to gray-scale. Then you generate two blurred versions of this image by applying a gaussian filter, one a little bit more blurry than the first one. (you could use a 1.0 sigma and a 2.0 sigma in a gaussian filter respectively) Then you subtract from the less-blury image, the pixel intensities of the more-blurry image. This operation enhances edges and produces a similar image regardless of strong illumination intensity variations. These steps can be very easily performed using OpenCV (as others have stated). This technique has been applied and documented here.
This paper adds an extra step involving contrast equalization, In my experience this is only needed if you want to obtain "visible" images from the DoG operation (pixel values tend to be very low after the DoG filter and are veiwed as black rectangles onscreen), and performing a histogram equalization is an acceptable substitution if you want to be able to see the effect of the DoG filter.
Once you have illumination-invariant images you could focus on the detection part. If your problem can afford having a static camera that can be trained for a certain amount of time, then you could use a strategy similar to alarm motion detectors. Most of them work with an average thermal image - basically they record the average temperature of the "pixels" of a room view, and trigger an alarm when the heat signature varies greatly from one "frame" to the next. Here you wouldn't be working with temperatures, but with average, light-normalized pixel values. This would allow you to build up with time which areas of the image tend to have movement (e.g. the leaves of a tree in a windy environment), and which areas are fairly stable in the image. Then you could trigger an alarm when a large number of pixles already flagged as stable have a strong variation from one frame to the next one.
If you can't afford training your camera view, then I would suggest you take a look at the TLD tracker of Zdenek Kalal. His research is focused on object tracking with a single frame as training. You could probably use the semistatic view of the camera (with no foreign objects present) as a starting point for the tracker and flag a detection when the TLD tracker (a grid of points where local motion flow is estimated using the Lucas-Kanade algorithm) fails to track a large amount of gridpoints from one frame to the next. This scenario would probably allow even a panning camera to work as the algorithm is very resilient to motion disturbances.
Hope this pointers are of some help. Good Luck and enjoy the journey! =D
Use one of the standard measures like Mean Squared Error, for eg. to find out the difference between two consecutive images. If the MSE is beyond a certain threshold, you know that there is some motion.
Also read about Motion Estimation.
if you know that the image will remain reletivly static I would reccomend:
1) look into neural networks. you can use them to learn what defines someone within the image or what is a non-something in the image.
2) look into motion detection algorithms, they are used all over the place.
3) is you camera capable of thermal imaging? if so it may be worthwile to look for hotspots in the images. There may be existing algorithms to turn your webcam into a thermal imager.
I'm trying to write a simple tracking routine to track some points on a movie.
Essentially I have a series of 100-frames-long movies, showing some bright spots on dark background.
I have ~100-150 spots per frame, and they move over the course of the movie. I would like to track them, so I'm looking for some efficient (but possibly not overkilling to implement) routine to do that.
A few more infos:
the spots are a few (es. 5x5) pixels in size
the movement are not big. A spot generally does not move more than 5-10 pixels from its original position. The movements are generally smooth.
the "shape" of these spots is generally fixed, they don't grow or shrink BUT they become less bright as the movie progresses.
the spots don't move in a particular direction. They can move right and then left and then right again
the user will select a region around each spot and then this region will be tracked, so I do not need to automatically find the points.
As the videos are b/w, I though I should rely on brigthness. For instance I thought I could move around the region and calculate the correlation of the region's area in the previous frame with that in the various positions in the next frame. I understand that this is a quite naïve solution, but do you think it may work? Does anyone know specific algorithms that do this? It doesn't need to be superfast, as long as it is accurate I'm happy.
Thank you
nico
Sounds like a job for Blob detection to me.
I would suggest the Pearson's product. Having a model (which could be any template image), you can measure the correlation of the template with any section of the frame.
The result is a probability factor which determine the correlation of the samples with the template one. It is especially applicable to 2D cases.
It has the advantage to be independent from the sample absolute value, since the result is dependent on the covariance related with the mean of the samples.
Once you detect an high probability, you can track the successive frames in the neightboor of the original position, and select the best correlation factor.
However, the size and the rotation of the template matter, but this is not the case as I can understand. You can customize the detection with any shape since the template image could represent any configuration.
Here is a single pass algorithm implementation , that I've used and works correctly.
This has got to be a well reasearched topic and I suspect there won't be any 100% accurate solution.
Some links which might be of use:
Learning patterns of activity using real-time tracking. A paper by two guys from MIT.
Kalman Filter. Especially the Computer Vision part.
Motion Tracker. A student project, which also has code and sample videos I believe.
Of course, this might be overkill for you, but hope it helps giving you other leads.
Simple is good. I'd start doing something like:
1) over a small rectangle, that surrounds a spot:
2) apply a weighted average of all the pixel coordinates in the area
3) call the averaged X and Y values the objects position
4) while scanning these pixels, do something to approximate the bounding box size
5) repeat next frame with a slightly enlarged bounding box so you don't clip spot that moves
The weight for the average should go to zero for pixels below some threshold. Number 4 can be as simple as tracking the min/max position of anything brighter than the same threshold.
This will of course have issues with spots that overlap or cross paths. But for some reason I keep thinking you're tracking stars with some unknown camera motion, in which case this should be fine.
I'm afraid that blob tracking is not simple, not if you want to do it well.
Start with blob detection as genpfault says.
Now you have spots on every frame and you need to link them up. If the blobs are moving independently, you can use some sort of correspondence algorithm to link them up. See for instance http://server.cs.ucf.edu/~vision/papers/01359751.pdf.
Now you may have collisions. You can use mixture of gaussians to try to separate them, give up and let the tracks cross, use any other before-and-after information to resolve the collisions (e.g. if A and B collide and A is brighter before and will be brighter after, you can keep track of A; if A and B move along predictable trajectories, you can use that also).
Or you can collaborate with a lab that does this sort of stuff all the time.