ARToolKit 6: Image Tracking using FREAK - augmented-reality

I am completely new to AR and I have searched all my best in Internet to get some sample on ARToolKit 6 (Android) without any success. At this point, the questions I have are
How do I generate an image tracker database with ARToolKit 6?
How do I create an Image set (with FREAK - Retina Key points or Harris
Corners) and store in database? In ARToolKit 5.3 we used to create iset,
fset and then dat file. But I guess with 6 version we wont be needing
those.But I am not sure how to create those image sets and store in
database. I couldn't find any samples.
Hope someone could shed some light here :) Would highly appreciate if you could point me to some samples.
Thanks

Related

Photo editing app iOS

I am trying to make a photo editing application for iOS, but am not sure where to start looking. I have attached an image made in Word... that hopefully simply depicts what I am trying to achieve. It will involved manipulating individual pixels of a shape/image and masking/clipping. WHow should I start and what resources are available to me other than the developer docs?
Cheers
If you are not new to programming I would suggest a trial and run kind of approach. If it was me, I would follow a approach like this
Figuring out what to do/ what not to do
Do I need to develop the tech I want from scratch or can I use some pods ?
What are the good reads and example apps - (Try this)
Development approach
Build a photo gallery to pick images from
Build a EDIT mode screen
Get set of template overlay images
Figure out how to overlay them on top of each other
Export the final picture as one picture
The developer documentation is essential when it comes to learning new APIs, but sometimes it can be a little overwhelming. You can try reading raywenderlich.com tutorials on Core Image first to get an idea (link here) or find a book on computer graphics. It is essential to understand at least the underlying techniques to efficiently program image processing code. In many cases you'll find there is a more elegant technique than just looping on pixels and modifying one-by-one.
Then you can continue with reading on image compositing using core image for example.

Facial recognition iOS

I have to build an app to recognize person on photo and find if this person is stored in phone book. I made face detection, I know how to take photos from people stored in phone book but I stuck on recognizing if the person is the same..
I want to ask what would be the easiest way to do it - i saw that iOS 10 comes with facial recognition in Photos app - is there any API to use facial recognition in iOS 10?
or should I use Open CV?
Face detection can be performed natively, as you've already found out, but to identify the faces you'll have to use something like OpenCV as there's no API available to do this presently
There's some information about how OpenCV can be used to recognise faces here.
Information about how to use it with Xcode here.
I built something similar some years ago.
I would suggest you look into perceptual hashing as it's an easy and inexpensive way of matching images.
You can have a look at the documentation, but this way your app will work only on iOS 10 and future versions.
If you plan to support older iOS versions or make also an Android app go for OpenCV

Can augmented reality be realized in a website?

Nowadays, I wanna do some research of augmented reality technology.Especially, I would like to match a 2d image and a 3d model.And then, I will see the 3d model if scanning the 2d image. What's more, I know that there are a lot of SDKs(like metaio,and wikitude) and software can realize this in mobile app. However, what I want to do is realizing this in a website. I hope the people who use this don't need to download a particular mobile app, but just open a website and then scan a picture.
So, until now, I's like to know that,as the tile asked, can AR be realized in a website? If yes, how can I do it or is there any software like Metaio Creator to do this? If no, why?
Thank you for anyone who would like to answer my naive question.
May I recommend you our completely webbased AR & VR tool holobuilder.com by bitstars.com?
It supports 360 degree photospheres that can be enhanced with custom 3D models and then directly be embedded into your website as iframe, it has native support for stereoscopic view mode and much more.
For your use case you could have a look at the lower part of this blog post where you find information and an embedded example presentation with photosphere imagery containing 3D elements:
http://heyholo.com/google-pushes-vr-great-for-tools-like-holobuilder/
If you want to start creating I recommend the beginners guide:
https://medium.com/#maxspeicher/the-definite-guide-to-holobuilder-3b62a54d303e
The cv feature tracking you requested can not yet be realized without any apps/browser. But what you can do is realizing perspectively correct displaying 3D elements into the camera image and move with sensors. Should be as performant as within the player app.
We hope that it can somehow help you in pushing your research and we would love to read your feedback. In case of any questions please do not hesitate to ask, here or on any other contact channel!

Augmented Reality Mask using Facial Recognition on Xbox Kinect with Kinect for Windows SDK

I am using an XBox Kinect with the Kinect for Windows SDK. I want to make an application that will augment a 3D mask (a 3D model of a mask made in 3DS Max) onto the face of anyone using the application. The application will be used in an exhibit locally. I have not tried much because I don't know where to start. So what I want to know is, is it currently possible to augment a 3DS Max model onto a live video stream using the facial recognition and skeletal tracking features in the newest Kinect for Windows SDK, and if so, how/where should I start trying to do/implement this? Any point in the right direction would be great. Thank you! PS And yes, I have read the UI guidelines and the facial documentation. My problem is one of not knowing where to start programming, not one of not understanding the fundamental concepts. Thanks!
If you are serious about getting into developing for the Kinect I would recommend getting this book:
http://www.amazon.com/Programming-Kinect-Windows-Software-Development/dp/0735666814
This goes through developing with the Kinect for Windows SDK from the ground up. There is a face tracking and an augmented reality example so I'm pretty sure you will be able to achieve your goal quite easily.
All the code from the book is here:
http://kinecttoolbox.codeplex.com/
Alternatively, there is an example here which pretty much is what you want to achieve:
http://www.codeproject.com/Articles/213034/Kinect-Getting-Started-Become-The-Incredible-Hulk
It is developed using the Beta version of the SDK, but the same priciples apply.
You can also check out the quick start videos here:
http://channel9.msdn.com/Series/KinectQuickstart
In summary, based on my own experience, I would spend some time going through the beginner examples either in the vides or the book (I found the book very good) just to get familiar with how to setup a simple Kinect project and how the different parts of the SDK work.
When you have developed some throwaway apps with the Kinect, I would then try tackling your project (although, the Incredible Hulk project above should get you most the way there!)
Best of luck with your project

Creating 3D model using set of 2D images on Windows

I want to create a 3D model using set of 2D images on windows which can be send through webservice to iphone to display on it.
I know it can be done through Opengl but don't know how to start and also if I succeeded in creating it,is it compatible with iphone as iphone uses opengl es.
Thanks in advance.
What kind of transformation do you have in mind to create the 3D models? I once worked on an application using such a concept to create a model from three images of an object. It didn't really work well. The models that could be created were very limited.
OpenGL does not have a built in functionality to do such stuff. Are there any reasosns why you do not want to use a real 3D-model? It sounds as if you are looking for a fast solution for your problem. But I'm afraid if you do not have any OpenGL experience, you should prepare prepare for lots of stuff to learn.
If you want to create 3D models automatically from 2D photos, you're going to have a fair bit of work to do. AFAIK, this is not something where you can get a cheap pre-packaged solution. Autodesk charge a small fortune for ImageModeler.
MeshLab may be a good starting point, but even that can't automatically convert photos to a 3D model AFAIK.
Take a look at David Lowes site. I found the "Distinctive image features from scale-invariant keypoints" paper quite interesting, though I haven't re-read it in a while. If nothing else, this should give you some idea why this is far from a trivial problem.

Resources