I am trying to create a Panorama app for iPhone/iPad.
The image stitching bit is OK, I'm using openCV libraries and the results are pretty acceptable.
But I'm a bit stuck on developing the UI for assisting the user while capturing the panorama.
Most apps (even on Android) would provide user with some sort of a marker that translates/rotates exactly matching the movement of the user's camera.
[I'm using the iOS 7 - default camera's panorama feature as a preliminary benchmark].
However, I'm way off the mark till date.
What I've tried:
I've tried using the accelerometer and gyro data for tracking the marker. With this approach -
I've applied an LPF on the accelerometer data and used simple
Newtonian mechanics (with a carefully tuned damping factor) to
translate the marker on the screen. Problem with this approach: very erratic data. Marker tends to jump and wobble between points. Hard to tell between smooth movement and jerk.
I've tried using a complimentary filter between LPF-ed gyro and
accelerometer data to translate the blob. Problem with this approach: Slightly better than the first approach, but still quite random.
I've also tried using image processing to compute optical flow. I'm
using openCV's
goodFeaturesToTrack(firstMat, cornersA, 30, 0.01, 30);
to get the trackable points from a first image (sampled from camera
picker) and then using calcOpticalFlowPyrLK to get the positions
of these points in the next image.
Problem with this approach: However, the motions vectors obtained from tracking these points are too noisy to compute the resultant
direction of motion accurately.
What I think I should do next:
Perhaps compute the DCT matrix from accelerometer and gyro data and
use some algorithm to filter one output with the other.
Work on the image processing algorithms, use some different techniques
(???).
Use Kalman filter to fuse the state prediction from
accelerometer+gyro with that of the image processing block.
The help that I need:
Can you suggest some easier way to get this job done?
If not, can you highlight any possible mistake in my approach? Does it really have to be this complicated?
Please help.
Related
I am trying to differentiate between camera motion and tool motion in a surgical video.
I have tried optical flow using opencv farneback and pass the results to an ML model to learn but no success.a major issue is getting good keypoints in case of camera motion. Is there an alternate technique to distinguish between camera motion and tool/tissue movement? Note: camera motion happens only in 10% of the video
I wish I could add a comment (too new to be able to comment), as I don't have a good answer for you.
I think it really depends on the nature of the input image. Can you show some typical input images here?
What is your optical flow result look like? I thought you might get some reasonable results.
Have you tried some motion estimation method, to analyze if there is global movement across different frames, or there is only some local movements?
I'm trying to develop an algorithm for real time tracking moving objects with a single moving camera setup as a project, in OpenCV (C++).
My basic objectives are
Detect motion in an (initially) static frame
Track that moving object (camera to follow that object)
Here is what I have tried already
Salient motion detection using temporal differencing and Optical Flow. (does not compensate for a moving camera)
KLT based feature tracking, but I was not able to segment the moving object features (moving object features got mixed with other trackable features in the image)
Mean shift based tracking (required initialization and is a bit computationally expensive)
I'm now trying to look into the following methods
Histogram of Gradients.
Algorithms that implement camera motion parameters.
Any advice on which direction should I proceed forward to acheive my objective.
Type: 'zdenek kalal predator' to google.com and watch the videos, read the papers that came up. I think it will give you a lot of insight.
I am working on an app in iOS that will occur an event if camera detects some changes in image or we can say motion in image. Here I am not asking about face recognition or a particular colored image motion, And I got all result for OpenCV when I searched, And I also found that we can achieve this by using gyroscope and accelerometer both , but how??
I am beginner in iOS.So my question is , Is there any framework or any easy way to detect motion or motion sensing by camera.And How to achieve?
For Example if I move my hand before camera then it will show some message or alert.
And plz give me some useful and easy to understand links about this.
Thanx
If all you want is some kind of crude motion detection, my open source GPUImage framework has a GPUImageMotionDetector within it.
This admittedly simple motion detector does frame-to-frame comparisons, based on a low-pass filter, and can identify the number of pixels that have changed between frames and the centroid of the changed area. It operates on live video and I know some people who've used it for motion activation of functions in their iOS applications.
Because it relies on pixel differences and not optical flow or feature matching, it can be prone to false positives and can't track discrete objects as they move in a frame. However, if all you need is basic motion sensing, this is pretty easy to drop into your application. Look at the FilterShowcase example to see how it works in practice.
I don't exactly understand what you mean here:
Here I am not asking about face recognition or a particular colored
image motion, because I got all result for OpenCV when I searched
But I would suggest to go for opencv as you can use opencv in IOS. Here is a good link which helps you to setup opencv in ios.
There are lot of opencv motion detection codes online and here is one among them, which you can make use of.
You need to convert the UIImage ( image type in IOS ) to cv::Mat or IplImage and pass it to the opencv algorithms. You can convert using this link or this.
I'm trying to make my OpenCV-based fiducial marker detection more robust when the user moves the camera (phone) violently. Markers are ArTag-style with a Hamming code embedded within a black border. Borders are detected by thresholding the image, then looking for quads based on the found contours, then checking the internals of the quads.
In general, decoding of the marker is fairly robust if the black border is recognized. I've tried the most obvious thing, which is downsampling the image twice, and also performing quad-detection on those levels. This helps with camera defocus on extreme nearground markers, and also with very small levels of image blur, but doesn't hugely help the general case of camera motion blur
Is there available research on ways to make detection more robust? Ideas I'm wondering about include:
Can you do some sort of optical flow tracking to "guess" the positions of the marker in the next frame, then some sort of corner detection in the region of those guesses, rather than treating the rectangle search as a full-frame thresholding?
On PCs, is it possible to derive blur coeffiients (perhaps by registration with recent video frames where the marker was detected) and deblur the image prior to processing?
On smartphones, is it possible to use the gyroscope and/or accelerometers to get deblurring coefficients and pre-process the image? (I'm assuming not, simply because if it were, the market would be flooded with shake-correcting camera apps.)
Links to failed ideas would also be appreciated if it saves me trying them.
Yes, you can use optical flow to estimate where the marker might be and localise your search, but it's just relocalisation, your tracking will have broken for the blurred frames.
I don't know enough about deblurring except to say it's very computationally intensive, so real-time might be difficult
You can use the sensors to guess the sort of blur you're faced with, but I would guess deblurring is too computational for mobile devices in real time.
Then some other approaches:
There is some really smart stuff in here: http://www.robots.ox.ac.uk/~gk/publications/KleinDrummond2004IVC.pdf where they're doing edge detection (which could be used to find your marker borders, even though you're looking for quads right now), modelling the camera movements from the sensors, and using those values to estimate how an edge in the direction of blur should appear given the frame-rate, and searching for that. Very elegant.
Similarly here http://www.eecis.udel.edu/~jye/lab_research/11/BLUT_iccv_11.pdf they just pre-blur the tracking targets and try to match the blurred targets that are appropriate given the direction of blur. They use Gaussian filters to model blur, which are symmetrical, so you need half as many pre-blurred targets as you might initially expect.
If you do try implementing any of these, I'd be really interested to hear how you get on!
From some related work (attempting to use sensors/gyroscope to predict likely location of features from one frame to another in video) I'd say that 3 is likely to be difficult if not impossible. I think at best you could get an indication of the approximate direction and angle of motion which may help you model blur using the approaches referenced by dabhaid but I think it unlikely you'd get sufficient precision to be much more help.
i need to find a marker like the ones used in Augmented Reality.
Like this:
I have a solid background on algebra and calculus, but no experience whatsoever on image processing. My thing is Php, sql and stuff.
I just want this to work, i've read the theory behind this and it's extremely hard to see in code for me.
The main idea is to do this as a batch process, so no interactivity is needed. What do you suggest?
Input : The sample image.
Output: Coordinates and normal vector in 3D of the marker.
The use for this will be linking images that have the same marker to spatialize them, a primitive version of photosync we could say. Just a caroussel of pinned images, the marker acting like the pin.
The reps given allowed me to post images, thanks.
You can always look at the open source libraries such as ARToolkit and see how it works but generally in order to get the 3D coordinates of marker you would need to:
Do the camera calibration.
Find marker in image using local features for example.
Using calibrated camera parameters and 2D coordinates of marker do the approximation the 3D coordinates.
I've never implemented sth similar by myself but I think this is a general concept you should apply on your method.
Your problem can be solved by perspective n point camera pose estimation. When you can reasonably assume that all correspondences are correct, a linear algorithm should do.
Since the marker is planar, you can also recover the displacement from the homography between the model plane and the image plane (link). As usual, best results are obtained by iterative algorithms (link).