Related
I want to remove background and get deer as a foreground image.
This is my source image captured by trail camera:
This is what I want to get. This output image can be a binary image or RGB.
I worked on it and try many methods to get solution but every time it failed at specific point. So please first understand what is my exact problem.
Image are captured by a trail camera and camera is motion detector. when deer come in front of camera it capture image.
Scene mode change with respect to weather changing or day and night etc. So I can't use frame difference or some thing like this.
Segmentation may be not work correctly because Foreground (deer) and Background have same color in many cases.
If anyone still have any ambiguity in my question then please first ask me to clear and then answer, it will be appreciated.
Thanks in advance.
Here's what I would do:
As was commented to your question, you can detect the dear and then perform grabcut to segment it from the picture.
To detect the dear, I would couple a classifier with a sliding window approach. That would mean that you'll have a classifier that given a patch (can be a large patch) in the image, output's a score of how much that patch is similar to a dear. The sliding window approach means that you loop on the window size and then loop on the window location. For each position of the window in the image, you should apply the classifier on that window and get a score of how much that window "looks like" a dear. Once you've done that, threshold all the scores to get the "best windows", i.e. the windows that are most similar to a dear. The rational behind this is that if we a dear is present at some location in the image, the classifier will output a high score at all windows that are close/overlap with the actual dear location. We would like to merge all that locations to a single location. That can be done by applying the functions groupRectangles from OpenCV:
http://docs.opencv.org/modules/objdetect/doc/cascade_classification.html#grouprectangles
Take a look at some face detection example from OpenCV, it basically does the same (sliding window + classifier) where the classifier is a Haar cascade.
Now, I didn't mention what that "dear classifier" can be. You can use HOG+SVM (which are both included in OpenCV) or use a much powerful approach of running a deep convulutional neural network (deep CNN). Luckily, you don't need to train a deep CNN. You can use the following packages with their "off the shelf" ImageNet networks (which are very powerful and might even be able to identify a dear without further training):
Decaf- which can be used only for research purposes:
https://github.com/UCB-ICSI-Vision-Group/decaf-release/
Or Caffe - which is BSD licensed:
http://caffe.berkeleyvision.org/
There are other packages of which you can read about here:
http://deeplearning.net/software_links/
The most common ones are Theano, Cuda ConvNet's and OverFeat (but that's really opinion based, you should chose the best package from the list that I linked to).
The "off the shelf" ImageNet network were trained on roughly 10M images from 1000 categories. If those categories contain "dear", that you can just use them as is. If not, you can use them to extract features (as a 4096 dimensional vector in the case of Decaf) and train a classifier on positive and negative images to build a "dear classifier".
Now, once you detected the dear, meaning you have a bounding box around it, you can apply grabcut:
http://docs.opencv.org/trunk/doc/py_tutorials/py_imgproc/py_grabcut/py_grabcut.html
You'll need an initial scribble on the dear to perform grabcu. You can just take a horizontal line in the middle of the bounding box and hope that it will be on the dear's torso. More elaborate approaches would be to find the symmetry axis of the dear and use that as a scribble, but you would have to google, research an implement some method to extract symmetry axis from the image.
That's about it. Not straightforward, but so is the problem.
Please let me know if you have any questions.
Try OpenCV Background Substraction with Mixture of Gaussians models. They should be adaptable enough for your scenes. Of course, the final performance will depend on the scenario, but it is worth trying.
Since you just want to separate the background from the foreground I think you do not need to recognize the deer. You need to recognize an object in motion in the scene. You just need to separate what is static in a significant interval of time (background) from what is not static: the deer.
There are algorithms that combine multiple frames from the same scene in order to determine the background, like THIS ONE.
You mentioned that the scene mode changes with respect to weather changing or day and night considering photos of different deers.
You could implement a solution when motion is detected, instead of taking a single photo, it could take a few ones with some interval of time.
This interval has to be long as to get the deer in different positions or out of the scene and at the same time short enough to not be much affected by scene variations. Perhaps you need to deal with some brightness variation, but I think it is feasible to determine the background using these frames and finally segment the deer in the "motion frame".
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 am hacking a vacuum cleaner robot to control it with a microcontroller (Arduino). I want to make it more efficient when cleaning a room. For now, it just go straight and turn when it hits something.
But I have trouble finding the best algorithm or method to use to know its position in the room. I am looking for an idea that stays cheap (less than $100) and not to complex (one that don't require a PhD thesis in computer vision). I can add some discrete markers in the room if necessary.
Right now, my robot has:
One webcam
Three proximity sensors (around 1 meter range)
Compass (no used for now)
Wi-Fi
Its speed can vary if the battery is full or nearly empty
A netbook Eee PC is embedded on the robot
Do you have any idea for doing this? Does any standard method exist for these kind of problems?
Note: if this question belongs on another website, please move it, I couldn't find a better place than Stack Overflow.
The problem of figuring out a robot's position in its environment is called localization. Computer science researchers have been trying to solve this problem for many years, with limited success. One problem is that you need reasonably good sensory input to figure out where you are, and sensory input from webcams (i.e. computer vision) is far from a solved problem.
If that didn't scare you off: one of the approaches to localization that I find easiest to understand is particle filtering. The idea goes something like this:
You keep track of a bunch of particles, each of which represents one possible location in the environment.
Each particle also has an associated probability that tells you how confident you are that the particle really represents your true location in the environment.
When you start off, all of these particles might be distributed uniformly throughout your environment and be given equal probabilities. Here the robot is gray and the particles are green.
When your robot moves, you move each particle. You might also degrade each particle's probability to represent the uncertainty in how the motors actually move the robot.
When your robot observes something (e.g. a landmark seen with the webcam, a wifi signal, etc.) you can increase the probability of particles that agree with that observation.
You might also want to periodically replace the lowest-probability particles with new particles based on observations.
To decide where the robot actually is, you can either use the particle with the highest probability, the highest-probability cluster, the weighted average of all particles, etc.
If you search around a bit, you'll find plenty of examples: e.g. a video of a robot using particle filtering to determine its location in a small room.
Particle filtering is nice because it's pretty easy to understand. That makes implementing and tweaking it a little less difficult. There are other similar techniques (like Kalman filters) that are arguably more theoretically sound but can be harder to get your head around.
A QR Code poster in each room would not only make an interesting Modern art piece, but would be relatively easy to spot with the camera!
If you can place some markers in the room, using the camera could be an option. If 2 known markers have an angular displacement (left to right) then the camera and the markers lie on a circle whose radius is related to the measured angle between the markers. I don't recall the formula right off, but the arc segment (on that circle) between the markers will be twice the angle you see. If you have the markers at known height and the camera is at a fixed angle of inclination, you can compute the distance to the markers. Either of these methods alone can nail down your position given enough markers. Using both will help do it with fewer markers.
Unfortunately, those methods are imperfect due to measurement errors. You get around this by using a Kalman estimator to incorporate multiple noisy measurements to arrive at a good position estimate - you can then feed in some dead reckoning information (which is also imperfect) to refine it further. This part is goes pretty deep into math, but I'd say it's a requirement to do a great job at what you're attempting. You can do OK without it, but if you want an optimal solution (in terms of best position estimate for given input) there is no better way. If you actually want a career in autonomous robotics, this will play large in your future. (
Once you can determine your position you can cover the room in any pattern you'd like. Keep using the bump sensor to help construct a map of obstacles and then you'll need to devise a way to scan incorporating the obstacles.
Not sure if you've got the math background yet, but here is the book:
http://books.google.com/books/about/Applied_optimal_estimation.html?id=KlFrn8lpPP0C
This doesn't replace the accepted answer (which is great, thanks!) but I might recommend getting a Kinect and use that instead of your webcam, either through Microsoft's recently released official drivers or using the hacked drivers if your EeePC doesn't have Windows 7 (presumably it does not).
That way the positioning will be improved by the 3D vision. Observing landmarks will now tell you how far away the landmark is, and not just where in the visual field that landmark is located.
Regardless, the accepted answer doesn't really address how to pick out landmarks in the visual field, and simply assumes that you can. While the Kinect drivers may already have feature detection included (I'm not sure) you can also use OpenCV for detecting features in the image.
One solution would be to use a strategy similar to "flood fill" (wikipedia). To get the controller to accurately perform sweeps, it needs a sense of distance. You can calibrate your bot using the proximity sensors: e.g. run motor for 1 sec = xx change in proximity. With that info, you can move your bot for an exact distance, and continue sweeping the room using flood fill.
Assuming you are not looking for a generalised solution, you may actually know the room's shape, size, potential obstacle locations, etc. When the bot exists the factory there is no info about its future operating environment, which kind of forces it to be inefficient from the outset.
If that's you case, you can hardcode that info, and then use basic measurements (ie. rotary encoders on wheels + compass) to precisely figure out its location in the room/house. No need for wifi triangulation or crazy sensor setups in my opinion. At least for a start.
Ever considered GPS? Every position on earth has a unique GPS coordinates - with resolution of 1 to 3 metres, and doing differential GPS you can go down to sub-10 cm range - more info here:
http://en.wikipedia.org/wiki/Global_Positioning_System
And Arduino does have lots of options of GPS-modules:
http://www.arduino.cc/playground/Tutorials/GPS
After you have collected all the key coordinates points of the house, you can then write the routine for the arduino to move the robot from point to point (as collected above) - assuming it will do all those obstacles avoidance stuff.
More information can be found here:
http://www.google.com/search?q=GPS+localization+robots&num=100
And inside the list I found this - specifically for your case: Arduino + GPS + localization:
http://www.youtube.com/watch?v=u7evnfTAVyM
I was thinking about this problem too. But I don't understand why you can't just triangulate? Have two or three beacons (e.g. IR LEDs of different frequencies) and a IR rotating sensor 'eye' on a servo. You could then get an almost constant fix on your position. I expect the accuracy would be in low cm range and it would be cheap. You can then map anything you bump into easily.
Maybe you could also use any interruption in the beacon beams to plot objects that are quite far from the robot too.
You have a camera you said ? Did you consider looking at the ceiling ? There is little chance that two rooms have identical dimensions, so you can identify in which room you are, position in the room can be computed from angular distance to the borders of the ceiling and direction can probably be extracted by the position of doors.
This will require some image processing but the vacuum cleaner moving slowly to be efficiently cleaning will have enough time to compute.
Good luck !
Use Ultra Sonic Sensor HC-SR04 or similar.
As above told sense the walls distance from robot with sensors and room part with QR code.
When your are near to a wall turn 90 degree and move as width of your robot and again turn 90deg( i.e. 90 deg left turn) and again move your robot I think it will help :)
I am thinking of implement a image processing based solution for industrial problem.
The image is consists of a Red rectangle. Inside that I will see a matrix of circles. The requirement is to count the number of circles under following constraints. (Real application : Count the number of bottles in a bottle casing. Any missing bottles???)
The time taken for the operation should be very low.
I need to detect the red rectangle as well. My objective is to count the
items in package and there are no
mechanism (sensors) to trigger the
camera. So camera will need to capture
the photos continuously but the
program should have a way to discard
the unnecessary images.
Processing should be realtime.
There may be a "noise" in image capturing. You may see ovals instead of circles.
My questions are as follows,
What is the best edge detection algorithm that matches with the given
scenario?
Are there any other mechanisms that I can use other than the edge
detection?
Is there a big impact between the language I use and the performance of
the system?
AHH - YOU HAVE NOW TOLD US THE BOTTLES ARE IN FIXED LOCATIONS!
IT IS AN INCREDIBLY EASIER PROBLEM.
All you have to do is look at each of the 12 spots and see if there is a black area there or not. Nothing could be easier.
You do not have to do any edge or shape detection AT ALL.
It's that easy.
You then pointed out that the box might be rotatated, things could be jiggled. That the box might be rotated a little (or even a lot, 0 to 360 each time) is very easily dealt with. The fact that the bottles are in "slots" (even if jiggled) massively changes the nature of the problem. You're main problem (which is easy) is waiting until each new red square (crate) is centered under the camera. I just realised you meant "matrix" literally and specifically in the sentence in your original questions. That changes everything totally, compared to finding a disordered jumble of circles. Finding whether or not a blob is "on" at one of 12 points, is a wildly different problem to "identifying circles in an image". Perhaps you could post an image to wrap up the question.
Finally I believe Kenny below has identified the best solution: blob analysis.
"Count the number of bottles in a bottle casing"...
Do the individual bottles sit in "slots"? ie, there are 4x3 = 12 holes, one for each bottle.
In other words, you "only" have to determine if there is, or is not, a bottle in each of the 12 holes.
Is that correct?
If so, your problem is incredibly easier than the more general problem of a pile of bottles "anywhere".
Quite simply, where do we see the bottles from? The top, sides, bottom, or? Do we always see the tops/bottoms, or are they mixed (ie, packed top-to-tail). These issues make huge, huge differences.
Surf/Sift = overkill in this case you certainly don't need it.
If you want real time speed (about 20fps+ on a 800x600 image) I recommend using Cuda to implement edge detection using a standard filter scheme like sobel, then implement binarization + image closure to make sure the edges of circles are not segmented apart.
The hardest part will be fitting circles. This is assuming you already got to the step where you have taken edges and made sure they are connected using image closure (morphology.) At this point I would proceed as follows:
run blob analysis/connected components to segment out circles that do not touch. If circles can touch the next step will be trickier
for each connected componet/blob fit a circle or rectangle using RANSAC which can run in realtime (as opposed to Hough Transform which I believe is very hard to run in real time.)
Step 2 will be much harder if you can not segment the connected components that form circles seperately, so some additional thought should be invested on how to guarantee that condition.
Good luck.
Edit
Having thought about it some more, I feel like RANSAC is ideal for the case where the circle connected components do touch. RANSAC should hypothetically fit the circle to only a part of the connected component (due to its ability to perform well in the case of mostly outlier points.) This means that you could add an extra check to see if the fitted circle encompasses the entire connected component and if it does not then rerun RANSAC on the portion of the connected component that was left out. Rinse and repeat as many times as necessary.
Also I realize that I say circle but you could just as easily fit an ellipse instead of circles using RANSAC.
Also, I'd like to comment that when I say CUDA is a good choice I mean CUDA is a good choice to implement the sobel filter + binirization + image closing on. Connected components and RANSAC are probably best left to the CPU, but you can try pushing them onto CUDA though I don't know how much of an advantage a GPU will give you for those 2 over a CPU.
For the circles, try the Hough transform.
other mechanisms: dunno
Compiled languages will possibly be faster.
SIFT should have a very good response to circular objects - it is patented, though. GLOHis a similar algorithm, but I do not know if there are any implementations readily available.
Actually, doing some more research, SURF is an improved version of SIFT with quite a few implementations available, check out the links on the wikipedia page.
Sum of colors + convex hull to detect boundary. You need, mostly, 4 corners of a rectangle, and not it's sides?
No motion, no second camera, a little choice - lot of math methods against a little input (color histograms, color distribution matrix). Dunno.
Java == high memory consumption, Lisp == high brain consumption, C++ == memory/cpu/speed/brain use optimum.
If the contrast is good, blob analysis is the algorithm for the job.
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.