For computer-vision-based AR, we showed you how to build applications using a single target. However, there might be scenarios in which you need to use several markers at once. Just think of augmenting a room for which you would need at least one target on each wall, or you may want your application to be able to recognize and augment hundreds of different product packages. The former case can be achieved by tracking multiple targets that have a common coordinate frame, and the latter use case can be achieved by using the power of cloud recognition. We will briefly discuss both of them in the following sections.
Multi-targets are more than a collection of several individual images. They realize a single and consistent coordinate system where a handheld device can be tracked. This allows for continuous augmentation of the scene as long as even a single target is visible. The main challenges of creating multi-targets lie in defining the common coordinate...