This was presented at Augmented World Expo in Santa Clara (#AWE2017). A video of the live Natural Feature Tracking demo will be uploaded and linked from here soon.
The key benefit of using AR in your web browser is how quick and easy it is to share. You can send a single web link through social media or email and the recipient can just tap on the link and it works. But up until recently this has not included Computer Vision based AR for a number of technical and market reasons. This presentation will position the web browser in the overall context of Computer Vision history, and we'll look at how this has evolved through developments including jsartoolkit.js, tracking.js and AR.js. We'll then dive deeper into the latest developments to show how OpenCV performs running in the browser and how this compares to native applications. This deep dive will compare the different feature detection/extraction algorithms and how they perform on some well known image data sets. The session will conclude with demos that show how this all works right now in over 2 Billion capable web browsers.