19

It is important to understand that the only problem here is to obtain the extrinsic parameters. Camera intrinsics can be measured off-line and there are lots of applications for that purpose. What are camera intrinsics? Camera intrinsic parameters is usually called the camera calibration matrix, $K$. We can write $$K = \begin{bmatrix}\alpha_u&s&...


8

Image keypoints are a key feature in many Image and Video processing softwares, both industrial and academic. The principle behind is always the same: detect some meaningful points in some images; [optional] compute a stable description of the image part surrounding each keypoint; match keypoints from an image (the template) to another (the query). Now, ...


6

Alas, optical flow is a difficult problem too ;-) Well, to be more constructive, here are a few algorithms that should be worth trying (or have been tried on this particular sequence) : re-train your bags of features on a databse of vehicles more representative (in size and orientation) to your actual problem in order to obtain better results use the fact ...


5

So this is just the start of an answer. I'll have to keep updating it as I go. The first attempt is to say that the quantities you are interested in are the location of the center of the four LEDs, and the roll, pitch, and yaw (rotation angles) of the LEDs. That means your Kalman FIlter state will be: $$ \mathbf{x}_k = \left[x_k\ y_k\ \alpha_k\ \beta_k\ \...


4

There are two versions of optical flow(OF): Feature based (sparse) or dense. In the dense version OF is applied to all the image pixels, while in the sparse one, only certain characteristic feature points are tracked. However, both approaches depend on the tracking of pixel quantities. This is fundamentally different than tracking the whole patch, because in ...


3

In general, a kernel is a function that acts as a parameter to some algorithm. Filtering: For example, it's possible to call the impulse response of a filter $h[n]$ a kernel, so that it is the parameter that defines the filter operation: $$ y[n] = h[n] * x[n]. $$ The use of the term kernel in the filtering context is much more common in 2D filtering or ...


3

Object detection is relatively a heavy task as you've notice. Detecting the object (in your case human face) in every and each frame would be cumbersome and computationally immense. Therefore, you need to employ an object tracking technique. There are various tracking algorithms, of which, KLT and mean-shift are the two popular ones. KLT works based on ...


2

As you're probably starting to realise this is a very big field with a number of different methods which you can try. If you want to try to use colour, you can try transforming from RGB to HSV space, which attempts to decouple the colour from the "lightness", this may improve your lighting inconsistencies. The next problem is how to track your object. If ...


2

While explaining the two-dimensional case very well, the answer proposed by Jav_Rock does not provide a valid solution for camera poses in three-dimensional space. Note that for this problem multiple possible solutions exist. This paper provides closed formulas for decomposing the homography, but the formulas are somewhat complex. OpenCV 3 already ...


2

I don't think you have any choice other than to use the same number of bins for each observation. Otherwise not only will you not be able to average the histograms, you will also not be able to compare them. And you definitely need to change the histogram slowly, i. e. $$h = (1 - \alpha)h + \alpha h_{obs}$$ where $h$ is your "moving average" histogram, $h_{...


2

Well, that's a great answer by @sansuiso, so I'll just concentrate on various possible uses of detected keypoints, and describe some examples for you. There are certainly more uses, the ones listed are just based on what I came in touch with until now. Content based image retrieval (CBIR) You treat the features (the feature vectors you get after applying ...


2

This is clearly not an easy task. The problem is, if you want a more-or-less accurate count, then you need to turn to advanced algorithms (and maybe use 2 cameras, or a kinect). If you can't afford to take this path, then you need to try simpler options. Personally, I would try the following: detecting skin pixels, segmenting the image with respect to ...


2

Tracking objects can be simple to complex depending on what type of background you have, whether the background is static or moving, whether the object is clearly distinguishable or can share similar properties with background there by blending in the background, and whether we have unique object at hand or we are tracking multiple objects which may cross ...


2

Your problem falls into the category of problems known as $Multitarget\; Tracking$. Are there algorithms?, you Betcha there are algorithms. This is an active area of research. IEEE Explore returns 1,620 hits for (multitarget tracking) The optimal algorithm is known as Reid's Multi Hypothesis Tracker (MHT), which unfortunately requires the exhaustive ...


1

If the distinct contents/ingredients really have different colors than you just have to take a picture, always in the same location/distance, and then count the amount of pixels for each color. You can transform your RGB image to the HSV color space to make it easy to identify specific colors. Some pseudocode: image_hsv = rgb2hsv(image_rgb) greenmax = ...


1

Anuar Y, Welcome to the DSP community. What you're talking about is called smoothing. Let me explain, assume we have samples $ {\left\{ x \left[ n \right] \right\}}_{n = 0}^{N - 1} $ and we want to build estimator for $ x \left[ k \right] $ which we will define as $ \hat{x} \left[ k \right] $. Now, we have 3 types of estimation: The case $ k > N - 1 $ ...


1

I think I can come up with two suggestion to address this problem. First (simple) You can simply use HSV color space, and try to find right thresholds. It seems in HSV colour space, the car is pretty distinguishable from the background but the rail is the problem now. I=imread ( your image ); J=rgb2hsv(I); imshow(0.1<J(:,:,2) & J(:,:,2)<0.2 &...


1

Is image processing impacted by the lens or sensor size of the camera? Yes, since both affect the image that is processed. That was easy :) For the purposes of object detection and tracking, does it matter if the images being processed came from a camera with a large sensor (e.g., DSLR) or a small sensor (e.g., smartphone)? Sensor sizes have different ...


1

You can use opencv library with python for image processing. Use Videocapture object to capture video from video MPG file. Do cap.read() to read frame by frame. Convert your frame to grayimage by cvtColor(). Use threshold() function with threshold type-4(threshold with invert option) and with max-binary value as 1. Now you got Mat array with 1 for your ...


1

assuming you have a relative high frame rate video (the object is moving relatively slow between two consecutive images) some standard tracking algorithms can be applied. Mean shift [Wikepedia - Mean shift] Use some template of the object you are tracking to create a likelihood function for the object location and track the object. if you need more ...


1

You might consider a particle filter. Here's a link to a paper I wrote about tracking objects in video using a particle filter. The great thing about these is that objects can be tracked through temporary occlusions. The trick with using a Kalman filter here is dealing with the nonlinearity introduced by the edges of the video field, and casting your ...


1

However, in Matlab it seems that to implement this I would need to assume either constant acceleration or velocity which is not the case since the rodent is freely moving. First of all you can choose any dynamic model not only constant acceleration or velocity. Secondly, In Kalman filter you don't need to have exact dynamic model. consider state dynamic ...


1

If you can make the assumption that the two observations are independent then the the likelihood function you need is just the product of the two likelihood functions. If for particle x, the likelihood of it in terms of the colour distribution is p(z_c|x) and the likelihood of it in terms of the motion contour is p(z_m|x) then the likeliood of both ...


1

1) Matching lines across multiple views is a common research problem and is reasonably well studied: If you have the end points for example : http://cmp.felk.cvut.cz/~werner/software/lmatch/lmatch_memo.pdf Even tough this deals with more geometric properties, if your scenes are well conditioned, you could as well use the gradient/intensity information to ...


1

There is a website which will give you a lot of information about your queries: http://www.robots.ox.ac.uk/~vgg/research/affine/ It contains information about feature detectors and descriptor, their current performance and which one is best in which scenario. This field has still a lot to go on. For example when you want to go for stereo reconstruction ...


1

OpenCV is a open source computer vision library that is based and can be used in most languages. It provides a quick way to compute Computer vision. That being said, this problem is very complex, if you do not have any real experience in image processing and of course, programming! You want to identify how many people are in the room, so yes, foreground / ...


1

What I have so far: A Survey of Human-Sensing: Methods for Detecting Presence, Count, Location, Track, and Identity; Teixeira, Dublon and Savvides I just found the question People Detection and Tracking on SO which also has some good leads.


Only top voted, non community-wiki answers of a minimum length are eligible