Model Tracking enables you to localize desired objects in the camera image with means of computer vision techniques. In order to do that, Model Tracking uses 3D (CAD) data of these real physical objects (also called tracking targets) as reference information to enable and “tell” the computer vision system about the objects it should find.

Because 3D data is used, there is no need to train or teach the computer vision system beforehand about the objects it should find.

Instead, and in contrast to other techniques including SLAM and feature tracking, there is no need for prior preparation or pre-acquisitions of the physical tracking targets anymore. Such techniques are good for spontaneous augmentations on-the-fly in almost unknown environments. But they are bad for localizing distinct objects and for “non-constant sceneries”, because they tend to break when objects move, or when lighting conditions change – typical computer vision obstacles.

Model Tracking, in contrast, enables you to precisely pin augmentations to referred objects, and you are thus truly connecting virtual and real domains. It masters the above mentioned obstacles. And, you can gain from a fast and robust object tracking with no further information required, except the 3D models.

Find more background on tracking techniques in the documentation.