Reading from the documentation, it feels like the calcOpticalFlowPyrLK function implements the Lucas-Kanade algorithm. However, browsing on the internet there are many mentions to the "OpenCV's KLT tracker" (like here).
It feels like LK and KLT denominations are used interchangeably, but shed confusion (at least to me) on what's actually implemented on OpenCV.
So, what is actually implemented?
Related
I am referring Google's machine learning DataPrep course, in this lecture https://developers.google.com/machine-learning/data-prep/construct/sampling-splitting/imbalanced-data about solving class imbalanced problem, the technique mentioned is to first downsample and then upweight. This lecture talks about the theory but I couldn't find its practical implementation. Can someone guide?
Upweighting is done to calibrate the probablities provided by probabilistic classifiers so that the output of the predict_proba method can be directly interpreted as a confidence level.
Python implementation of the two calibration methods is provided here - https://scikit-learn.org/stable/auto_examples/calibration/plot_calibration.html#sphx-glr-auto-examples-calibration-plot-calibration-py
More details about probablity calibration is provided here - https://scikit-learn.org/stable/modules/calibration.html
I am looking for implemented online learning time series algorithms. Does R, Python, MOA or any other tools have these kind of algorithms implemented?
TIA!
It's a little bit late, but in case someone is looking for the answer, I will share what I know:
PYTHON: sklearn clustering algorithms.
MiniBatchKMeans and Birch: both algorithm implementations have a partial_fit method allowing you to stream data through them in incremental updates (allowing online learning).
JAVA: MOA framework.
There are a lot of well known stream clustering algorithms implemented (CluStream, DenStream, etc ...). You can use it via:
terminal
user interface (see clustering demo)
code (Java API)
See the 'downloads' section in the MOA web, or check directly the source code on Github.
R: streamMOA: a R package that acts as a wrapper for the MOA [Java] classes. See the manual.
After it came up in a question, I realised, that up to this point I never stumbled upon any information about the computational complexity of the algorithms or methods openCV provides. Are there any articles or information about it? For example (as it came up in this question), the complexity of reading/accessing a video stream in Landau notation, or any of the algorithm implementation like SIFT/SURF (I only read that the openSURF library is supposed to be more efficient than the openCV implementation).
I'd say that most of the high-level algorithms are documented, at least with pointer to an academic article, where you can have hints about the complexity of the algorithm
I have made a videochat, but as usual, a lot of men like to ehm, abuse the service (I leave it up to you to figure the nature of such abuse), which is not something I endorse in any way, nor do most of my users. No, I have not stolen chatroulette.com :-) Frankly, I am half-embarassed to bring this up here, but my question is technical and rather specific:
I want to filter/deny users based on their video content when this content is of offending character, like user flashing his junk on camera. What kind of image comparison algorithm would suit my needs?
I have spent a week or so reading some scientific papers and have become aware of multiple theories and their implementations, such as SIFT, SURF and some of the wavelet based approaches. Each of these has drawbacks and advantages of course. But since the nature of my image comparison is highly specific - to deny service if a certain body part is encountered on video in a range of positions - I am wondering which of the methods will suit me best?
Currently, I lean towards something along the following (Wavelet-based plus something I assume to be some proprietary innovations):
http://grail.cs.washington.edu/projects/query/
With the above, I can simply draw the offending body part, and expect offending content to be considered a match based on a threshold. Then again, I am unsure whether the method is invariable to transformations and if it is, to what kind - the paper isn't really specific on that.
Alternatively, I am thinking that a SURF implementation could do, but I am afraid that it could give me false positives. Can such implementation be trained to recognize/give weight to specific feature?
I am aware that there exist numerous questions on SURF and SIFT here, but most of them are generic in that they usually explain how to "compare" two images. My comparison is feature specific, not generic. I need a method that does not just compare two similar images, but one which can give me a rank/index/weight for a feature (however the method lets me describe it, be it an image itself or something else) being present in an image.
Looks like you need not feature detection, but object recognition, i.e. Viola-Jones method.
Take a look at facedetect.cpp example shipped with OpenCV (also there are several ready-to-use haarcascades: face detector, body detector...). It also uses image features, called Haar Wavelets. You might be interested to use color information, take a look at CamShift algorithm (also available in OpenCV).
This is more about computer vision. You have to recognize objects in your image/video sequence, whatever... for that, you can use a lot of different algorithms (most of them work in the spectral domain, that's why you will have to use a transformation).
In order to be accurate, you will also need a knowledge base or, at least, some descriptors that will define the object.
Try OpenCV, it has some algorithms already implemented (and basic descriptors included).
There are applications/algorithms out there that you can "train" (like neural networks) and are able to identify objects based on the training. Most of them (at least, the good ones) are not very popular and can only be found in research groups specialized in computer vision, object recognition, AI, etc.
Good luck!
Does anybody here do computer vision work on Mathematica? I would like to know what external libraries are available for doing that. The built in image processing functions are not enough. I am looking for things like SURF, stereo, camera calibration, multi-view geometry etc.
How difficult would it be to wrap OpenCV for use in Mathematica?
Apart from the extensive set of image processing tools that are now (version 8) natively present in Mathematica, and which include a number of CV algorithms like finding morphologic objects, image segmentation and feature detection (see figure below), there's the new LibraryLink functionality, which makes working with DLLs very easy. You wouldn't have to change OpenCV much to be able to call it from Mathematica. Just some wrappers for the functions to be called and you're basically done.
I don't think such a thing exists, but I'm getting started.
It has the advantage that you can perform some analytic methods... for example rather than hacking in openCV or even Matlab endlessly, you can compute analytically a quantity, and see that the method leading to this matrix is numerically unstable as a function of input variables. Thus you do not need to hack, as it would be pointless.
As for wrapping opencv, that doesn't seem to make sense. The correct procedure would be to fix bad implementations in opencv based on your analysis in Mathematica and on paper.
Agreeing with Peter, I don't believe that forcing Mathematica to use OpenCV is a great thing.
All of the computer vision people that I've talked to, read about, and seen examples are using Matlab and the Imaging toolkit. Its either that, or go with a OpenCV compatible language + OpenCV.
Mathematica has a rich set of tools for image processing, but I'm uncertain about the computer vision capabilities.