Success-story: Fueling ARBasketball up with NEON

img.pull-left.img-thumbnail(src=“arbasketball-logo.jpg”,alt=“ARBasketball”) p ARBasketball was one of the first augmented reality-based games in App Store. It has been published in 2010. In these days not many people have even heard about AR. I mean it wasn’t so popular as it became now. But there were people who saw the great potential in this growing market. One of them was Konstantin Tarovik, the author of ARBasketball. I must confess - I saw this application before, but had no idea it’s author lives in Ukraine, and in the same city as I am!

Maximizing performance of CV_BGRA2GRAY conversion using NEON and cv::parallel_for

I continue playing with powerful NEON engine in iPhone and iPad devices. Recently i bought iPhone 4S that replaced my HTC Mozart and i decided to check how to speed up BGRA to GRAY color conversion procedure using multithreading. Recently Itseez announced a minor release of OpenCV 2.4.3 with a lot of new major features: Added universal parallel_for implementation using various backends: TBB, OpenMP, GCD, Concurrency Improved OpenCV Manager, new Java samples framework, better camera support on Android, opencv2.

OpenCV Tutorial Part 7

After a long delay i’m happy to resume posting OpenCV tutorials in my blog. In Part 7 i will present you a new way of generation of icons for samples. Also i’ll show how to use NEON and assembly language to speed-up cv::transform function twice! Also there are three new samples i have to say few words about each. Interface improvements Default sample icons I think each sample has to have it’s own unique icon image.

A battle of three descriptors: SURF, FREAK and BRISK

I think developers and research guys who works with object recognition, image registration and other areas that uses keypoint extraction can find this post useful. Recently (from 2.4.2) a new feature descriptor algorithm was added to OpenCV library. FREAK descriptor is claimed to be superior to ORB and SURF descriptors, yet it’s very fast (comparable to ORB). Also people in comments on my blog mentioned BRISK descriptor which is also new and more efficient than SURF.

OpenCV Tutorial - Part 6

[toc] Hi folks! I’m glad to publish a sixth part of the OpenCV Tutorial cycle. In this post I will describe how to implement interesting non-photorealistic effect that makes image looks like a cartoon. It has numerous names: cartoon filter or simply “toon” also it known as rotoscoping. In addition we will refactor application interface and add tweeting feature to share your results across the web. According to the roadmap I promised to put the video recording module too, but due to lack of free time I decided to put it on hold for now.

OpenCV Tutorial - Part 5

Hello readers! The fifth part of the OpenCV Tutorial is here! In this post we will add options pane for our samples. In the end of this chapter our application will receive options interface as shown on screenshot. But first, let me remind you (if you came here for the first time) what is happening here. The “OpenCV Tutorial” is a open-source project maintained by me (Eugene Khvedchenya). My goal - create a iPhone/iPad application to demonstrate various image processing algorithms of OpenCV library and how to use them in iOS applications.

OpenCV Tutorial - Part 4

This is the fourth part of the OpenCV Tutorial. In this part the solution of the annoying iOS video capture orientation bug will be described. Of course that’s not all. There are some new features - we will add processing of saved photos from your photo album. Also to introduce minor interface improvements and I’ll show you how to disable unsupported API like video capture in your app and run in on iOS Simulator.

OpenCV Tutorial - Part 3

In Part 1 and Part 2 we created base application for our “OpenCV Tutorial” application. In this part we add video source to process frames using our samples and present the result to user. As usual, you can find source code for this application at github. Video capture in iOS At this moment (as far as i know) there OpenCV’s cv::VideoCapture does not support iOS platform. Therefore we have to use iOS AVFoundation API to setup video capture.

OpenCV Tutorial - Part 2

In the previous step we created Master-Detail XCode project and linked OpenCV library to it. Also we defined a base interface for all samples. Today we’ll write some UI logic to integrate our samples into the application. One ring to rule them all Since we are going to store a lot of samples (i hope so), we have to store them somewhere. I think for our application the ideal place to save them is our application delegate class.

OpenCV Tutorial - Part 1

As i recently mentioned, i decided to write a brand new OpenCV tutorial application for iPhone/iPad devies. This development is open-source and anyone can access it on repository page. Your help are welcome to write a UI for this app and help writing sample demonstration cases. Feel free to clone repository and make your contribution! OpenCV Tutorial The application startup screen will present master-detail view as a list of available samples.
1/2 »