How to get a pixel movement when using "optical flow" - image-processing

I'm doing 2D-Image processing and I have a quick question:
does optical flow provide the movement detection for a given Pixel, or is it just working with this information (i.e. you need an additional method to get this data)?
For what I've seen I'm assuming, that you need to provide the movement in x and y on your own, but on the other hand it is working with a constant pixel intensity (from one image to the next), which I guess should be obsolete if you already got the movement information
Has anyone a hint? Since all the tutorials, literatures, lectures I've seen skip this important step

Optical flow calculates this movement for you. You need to specify the pixels coordinates in the first frame, and some parameters as to the target search region, and then it calculates the movement. The problem is that it's not always correct, and in some cases, not possible, when the pixel is not really distinguishable from its surroundings.
In OpenCV, the function goodFeaturesToTrack usually precedes optical flow, as it detects pixels that have higher likelihood of being processed correctly. Even then, you still need to do some extra processing to verify that the movement was correct.

Related

OpenCV - align stack of images - different cameras

We have this camera array arranged in an arc around a person (red dot). Think The Matrix - each camera fires at the same time and then we create an animated gif from the output. The problem is that it is near impossible to align the cameras exactly and so I am looking for a way in OpenCV to align the images better and make it smoother.
Looking for general steps. I'm unsure of the order I would do it. If I start with image 1 and match 2 to it, then 2 is further from three than it was at the start. And so matching 3 to 2 would be more change... and the error would propagate. I have seen similar alignments done though. Any help much appreciated.
Here's a thought. How about performing a quick and very simple "calibration" of the imaging system by using a single reference point?
The best thing about this is you can try it out pretty quickly and even if results are too bad for you, they can give you some more insight into the problem. But the bad thing is it may just not be good enough because it's hard to think of anything "less advanced" than this. Here's the description:
Remove the object from the scene
Place a small object (let's call it a "dot") to position that rougly corresponds to center of mass of object you are about to record (the center of area denoted by red circle).
Record a single image with each camera
Use some simple algorithm to find the position of the dot on every image
Compute distances from dot positions to image centers on every image
Shift images by (-x, -y), where (x, y) is the above mentioned distance; after that, the dot should be located in the center of every image.
When recording an actual object, use these precomputed distances to shift all images. After you translate the images, they will be roughly aligned. But since you are shooting an object that is three-dimensional and has considerable size, I am not sure whether the alignment will be very convincing ... I wonder what results you'd get, actually.
If I understand the application correctly, you should be able to obtain the relative pose of each camera in your array using homographies:
https://docs.opencv.org/3.4.0/d9/dab/tutorial_homography.html
From here, the next step would be to correct for alignment issues by estimating the transform between each camera's actual position and their 'ideal' position in the array. These ideal positions could be computed relative to a single camera, or relative to the focus point of the array (which may help simplify calculation). For each image, applying this corrective transform will result in an image that 'looks like' it was taken from the 'ideal' position.
Note that you may need to estimate relative camera pose in 3-4 array 'sections', as it looks like you have a full 180deg array (e.g. estimate homographies for 4-5 cameras at a time). As long as you have some overlap between sections it should work out.
Most of my experience with this sort of thing comes from using MATLAB's stereo camera calibrator app and related functions. Their help page gives a good overview of how to get started estimating camera pose. OpenCV has similar functionality.
https://www.mathworks.com/help/vision/ug/stereo-camera-calibrator-app.html
The cited paper by Zhang gives a great description of the mathematics of pose estimation from correspondence, if you're interested.

Extrinsic Camera Calibration Using OpenCV's solvePnP Function

I'm currently working on an augmented reality application using a medical imaging program called 3DSlicer. My application runs as a module within the Slicer environment and is meant to provide the tools necessary to use an external tracking system to augment a camera feed displayed within Slicer.
Currently, everything is configured properly so that all that I have left to do is automate the calculation of the camera's extrinsic matrix, which I decided to do using OpenCV's solvePnP() function. Unfortunately this has been giving me some difficulty as I am not acquiring the correct results.
My tracking system is configured as follows:
The optical tracker is mounted in such a way that the entire scene can be viewed.
Tracked markers are rigidly attached to a pointer tool, the camera, and a model that we have acquired a virtual representation for.
The pointer tool's tip was registered using a pivot calibration. This means that any values recorded using the pointer indicate the position of the pointer's tip.
Both the model and the pointer have 3D virtual representations that augment a live video feed as seen below.
The pointer and camera (Referred to as C from hereon) markers each return a homogeneous transform that describes their position relative to the marker attached to the model (Referred to as M from hereon). The model's marker, being the origin, does not return any transformation.
I obtained two sets of points, one 2D and one 3D. The 2D points are the coordinates of a chessboard's corners in pixel coordinates while the 3D points are the corresponding world coordinates of those same corners relative to M. These were recorded using openCV's detectChessboardCorners() function for the 2 dimensional points and the pointer for the 3 dimensional. I then transformed the 3D points from M space to C space by multiplying them by C inverse. This was done as the solvePnP() function requires that 3D points be described relative to the world coordinate system of the camera, which in this case is C, not M.
Once all of this was done, I passed in the point sets into solvePnp(). The transformation I got was completely incorrect, though. I am honestly at a loss for what I did wrong. Adding to my confusion is the fact that OpenCV uses a different coordinate format from OpenGL, which is what 3DSlicer is based on. If anyone can provide some assistance in this matter I would be exceptionally grateful.
Also if anything is unclear, please don't hesitate to ask. This is a pretty big project so it was hard for me to distill everything to just the issue at hand. I'm wholly expecting that things might get a little confusing for anyone reading this.
Thank you!
UPDATE #1: It turns out I'm a giant idiot. I recorded colinear points only because I was too impatient to record the entire checkerboard. Of course this meant that there were nearly infinite solutions to the least squares regression as I only locked the solution to 2 dimensions! My values are much closer to my ground truth now, and in fact the rotational columns seem correct except that they're all completely out of order. I'm not sure what could cause that, but it seems that my rotation matrix was mirrored across the center column. In addition to that, my translation components are negative when they should be positive, although their magnitudes seem to be correct. So now I've basically got all the right values in all the wrong order.
Mirror/rotational ambiguity.
You basically need to reorient your coordinate frames by imposing the constraints that (1) the scene is in front of the camera and (2) the checkerboard axes are oriented as you expect them to be. This boils down to multiplying your calibrated transform for an appropriate ("hand-built") rotation and/or mirroring.
The basic problems is that the calibration target you are using - even when all the corners are seen, has at least a 180^ deg rotational ambiguity unless color information is used. If some corners are missed things can get even weirder.
You can often use prior info about the camera orientation w.r.t. the scene to resolve this kind of ambiguities, as I was suggesting above. However, in more dynamical situation, of if a further degree of automation is needed in situations in which the target may be only partially visible, you'd be much better off using a target in which each small chunk of corners can be individually identified. My favorite is Matsunaga and Kanatani's "2D barcode" one, which uses sequences of square lengths with unique crossratios. See the paper here.

Determine movement/motion (in pixels) between two frames

First of all I'm a total newbie in image processing, so please don't be too harsh on me.
That being said, I'm developing an application to analyse changes in blood flow in extremities using thermal images obtained by a camera. The user is able to define a region of interest by placing a shape (circle,rectangle,etc.) on the current image. The user should then be able to see how the average temperature changes from frame to frame inside the specified ROI.
The problem is that some of the images are not steady, due to (small) movement by the test subject. My question is how can I determine the movement between the frames, so that I can relocate the ROI accordingly?
I'm using the Emgu OpenCV .Net wrapper for image processing.
What I've tried so far is calculating the center of gravity using GetMoments() on the biggest contour found and calculating the direction vector between this and the previous center of gravity. The ROI is then translated using this vector but the results are not that promising yet.
Is this the right way to do it or am I totally barking up the wrong tree?
------Edit------
Here are two sample images showing slight movement downwards to the right:
http://postimg.org/image/wznf2r27n/
Comparison between the contours:
http://postimg.org/image/4ldez2di1/
As you can see the shape of the contour is pretty much the same, although there are some small differences near the toes.
Seems like I was finally able to find a solution for my problem using optical flow based on the Lukas-Kanade method.
Just in case anyone else is wondering how to implement it in Emgu/C#, here's the link to a Emgu examples project, where they use Lukas-Kanade and Farneback's algorithms:
http://sourceforge.net/projects/emguexample/files/Image/BuildBackgroundImage.zip/download
You may need to adapt a few things, e.g. the parameters for the corner detection (the frame.GoodFeaturesToTrack(..) method) , but it's definetly something to start with.
Thanks for all the ideas!

obtaining 2d-3d point correspondences for pnp or posit

I am trying to estimate the pose and position of a satellite given an image of it. I have a 3D model of the satellite. Using either PnP solvers or POSIT works great when I pick out the point correspondences myself, however I need to to find a method to match the points up automatically. Using a corner detector (best one I found so far is based on the contour) I can find all the relevant points in the image in addition a few spurious points. However I need to match a given point in the image to the correct point in the 3D model. The articles I have read on the subject always seem to assume that we have found the point pairs without going into details about how to do so.
Is there any approach usually taken that can determine these correspondences based on some invariant features? Or should i resort to a different method not based on corner points?
You can have a look at the SoftPOSIT algorithm, which determines 3D-2D correspondences and then executes POSIT algorithm. As far as I know Matlab code is available for SoftPOSIT.
ou have to do PnP with RANSAC, see openCV code solvePnPRansac(). This method can tolerate a high percent of mismatches so you don't need to be precise with all your matches but just have a certain percent of correct ones (even as low as 30%). Of course the min number of right correspondences is 4.
Speaking of invariant features - if the amount of rotation between neighbouring frame is small you don't need to use invariant features. Even a small patch of with grey intensities would suffice to find a match. The only problem is that you have to update your descriptor or even choose a different feature point on your model depending on the model rotation. The latter may be hard to do since you have to know 3D coordinate of every feature.

Block Bundle Adjustment Flow

I am working on bundle block adjustment for finding
X,Y,Z values of image points
Corrected values of camera characteristics(extrinsic parameters etc..)
Corrected values of measurements
In my opinion BB Adjustment process is done by following these steps(camera intrinsics are given):
Gather tie points( x,y for each image pair ) and ground control points( x,y and related X,Y,Z positions for each image )
Calculate initial extrinsic parameters( camera pose ) for each view
Calculate each tie point's initial real world position by using camera pose
Execute sparse bundle adjustment step by using all these initial values and other parameters as inputs
Use output of sparse bundle adjustment as accurate results of real world position, extrinsic characteristics and measurements.
One thing i want to ask is if that flow is correct. There are lots of methods for structure and motion estimation from views so i can not be so sure about that.
As i search through various resources i found that there are libraries that does each part of the block bundle adjustment operation. For each step:
Image processing libraries like OpenCV may be used for automatic tie point collection
cvFindExtrinsicCameraParams2 may be used for space resection ( but it requires 4 points, for block bundle adjustment it is mentioned that 3 Ground control points are enough for each view. Should i use another method like pose estimation from stereo views? )
By using triangulation and projection methods of OpenCV, real world positions may be calculated
SBA or SSBA is suitable for this operation
N/A
One another question is that, if previously mentioned flow is right, is matched libraries are enough for implementing entire flow?( May be better advises for each part )
I am newbie in this field, so i appreciate any help in this subject, Thanks...
You have described the default approach to stereo photogrammetry. Rather than using computer vision terms (extrinsic, intrinsic) I suggest you search using the terms interior- and exterior-orientation. This is a good approach if you have finite numbers of overlapping images and it has the benefit of some well defined error estimation methods.
Here is some basic math:
http://itee.uq.edu.au/~elec4600/elec4600_lectures/1perpage/uq1.pdf
http://itee.uq.edu.au/~elec4600/elec4600_lectures/1perpage/uq2.pdf
.2. cvFindExtrinsicCameraParams2 may be used for space resection ( but it
requires 4 points, for block bundle adjustment it is mentioned that 3
Ground control points are enough for each view.
The reason four control points are required by cvFindExtrinsicCameraParams2 is that the equations are under-determined with only three. If you don't have enough control, you might have to use an alternate approach (or sensor) to estimate the initial camera pose vector.

Resources