Object recognition, multi-target tracking and SLAM: Track the world with SDK 7

Paula

Today augmented reality takes a giant step towards tracking the world. We are excited to reveal Wikitude SDK 7, the “all-in-one AR tool-kit” powered with object tracking, instant tracking (SLAM), multiple targets recognition, extended recognition range, and more. SDK 7 includes marker, markerless, and location-based augmented reality features in one kit for developers.

Wikitude’s CEO, Martin Herdina, states that “SDK 7 is another big milestone for AR developers, who can now utilize a single cross-platform SDK to build the complete spectrum of AR experiences existing in the market today.”

The latest version of our SDK is available for iOS, Android, and smart glasses and supports a wide range of development frameworks such as Unity, Phonegap, Titanium, and Xamarin. Users can also choose from Native Android/iOS APIs or a JavaScript API. The full-feature free trial of SDK 7 can be downloaded here.
In this post, we give you a glimpse of what’s new.

For a deeper technical insight into SDK 7, check out this detailed blog post.

Object Recognition

SDK 7 significantly expands Wikitude’s SLAM technology by adding object recognition and tracking capabilities to its feature set. These features enable brands and enterprises to build augmented reality experiences using a variety of real-world objects, such as toys, sculptures, architectural models, product packaging, industrial machines, and more.

The workflow is simple: take multiple pictures of your object, upload it to the Wikitude Studio Manager and create your AR experience as desired.

Object recognition technology creates an additional touchpoint to interact with users, allowing real-time and 360 degrees augmented reality experiences around real-world objects.

The practical applications are numerous, so whether you are building your next interactive marketing campaign, enhancing in-store experiences, or remotely assisting workers on a factory floor, object recognition will close the gap between the physical and digital worlds.

Multiple Image target recognition

SDK 7 introduces ‘Multiple Image Target’ tracking to Wikitude’s advanced image recognition technology. This feature enables the recognition of several images simultaneously. Once the images are recognized, developers will be able to layer 3D models, buttons, videos, images, and more on each target. Additionally, augmentations will be able to interact with each other based on the targets’ positions.

Multiple image target recognition can be used to bring interactivity to board and card games, empower consumers with information about different products in retail stores, assist workers with product organization on supermarket shelves, and more.

Hit-testing API for SLAM

Wikitude’s award-winning SLAM engine will help you further understand the world through SDK 7’s hit-testing API. This feature analyzes and understands the environment by detecting real-world points corresponding to specific areas in the camera frame. This means that SDK 7 will report the positions and depths of elements in the AR scenes to create more realistic experiences. Elements in the scene are identified and augmentations will be displayed accordingly with instant tracking (e.g. become bigger when positioned close to the camera, smaller when placed further away in the scene, etc.).

Instant tracking improvements

SDK 7 comes with an improved SLAM engine that recognizes environments faster and more precisely. Users will be able to fully go around augmentations to enjoy all angles of the AR experience. Additionally, developers will have the possibility to change the rotation of the initial plane, bringing Instant Tracking to walls and ceilings. For more details, see how The Washington Post is using this feature on their app.

Extended recognition range

As part of the several upgrades on Wikitude’s computer vision engine, SDK 7 has the ability to recognize target images from an extended range in distance. Target images in A4 format will now be recognized from over 2 meters away. This recognition distance is 2x superior to other SDKs available in the market. Extended recognition range works for on-device image recognition and HD devices.

Additional features and improvements

SDK 7 brings additional features and improvements to Wikitude’s technology. For further details, please check the technical insight of SDK 7 and the developer documentation.

– Android motion sensor for improved location-based AR experiences
– Faster and more accurate Instant Tracking and Extended Tracking
– Support for Metal graphics API (iOS Native only)
– Support for Bitcode build option
– Extensive sample for Swift (iOS)

Get a taste of the world’s ‘Best Developer Tool’, awarded at AWE USA 2017 in the Silicon Valley. We couldn’t be more excited with this update and are looking forward to receiving your feedback!

Start developing with Wikitude SDK 7

Getting started with SDK 7 has never been easier! Here’s how:

Help us spread the news on Twitter, Facebook, and Linkedin using the hashtag #SDK7 and #Wikitude.

Previous Article
Wikitude SDK 7: A developer insight
Next Article
Wikitude SDK 7: A developer insight