MAR Component Classification Framework

7 MAR Component Classification Framework

This section uses the component classification framework provided in the previous section to describe several higher classes of MAR application or services. Each class focuses on parts of the system architecture and provides illustrations of how to use the reference model. The classes are defined as illustrated in Table 8.1. An instance of a MAR system can also be a combination of several classes.

The device detects the presence of target resources (images or their corresponding descriptors) in a video stream, optionally computes the transformation matrix (position, orientation and scaling) of the detected ones and augments the video stream with associated graphical objects. The video can be the result of a real time scene capture using a local camera, a remote video source or a video track stored in the device. The content specified in the Information viewpoint is:

• 
  URLs to target images (compressed, raw or corresponding descriptors).
  
• 
  URL to the video stream (a local camera, a local video track or a remote video resource).
  
• 
  Media used for the augmentation.
  
• 
  Optional: a 2d region (in the video frame) to be considered in the recognition process and delay constraints.
  

According to the MAR component classification scheme in Clause 7, this system class has the following characteristics:

• 
  Pure sensors – visual
  
• 
  Real world capturer – visual, 2D video
  
• 
  Recognizer – image patch, recognition event, local
  
• 
  Tracker – image patch , spatial event, local
  
• 
  Space mapper - spatial
  
• 
  Event mapper - visual
  
• 
  Execution engine – local, 2D + t
  
• 
  Renderer - visual
  
• 
  Visual display – 2D mono
  

The device sends the target resources (images or their corresponding descriptors) and the video stream sampled at a specified frame rate (provided by a local camera, a local video track or a remote video resource) to a Processing Server which detects and optionally tracks the target resources in the video stream. An ID mask and the computed transformation matrix of the detected resources are returned. The content specified in the Information viewpoint is:

• 
  URLs to target images (compressed, raw or corresponding descriptors).
  
• 
  URL to the video stream (a local camera, a local video track or a remote video resource) .
  
• 
  The format in which the video data is sent to the processing server (raw/compressed image or the corresponding video frame descriptors).
  
• 
  Media used for the augmentation.
  
• 
  URL to the Processing Servers.
  
• 
  Optional: a 2d region (in the video frame) to be considered in the recognition process and delay constraints.
  

In addition, a communication protocol has to be implemented between the MAR Execution Engine and the Processing Servers.