Tracking

Here, we will be explaining the necessity of 6DoF tracking for AAR, and the challenges we have faced with indoor tracking systems in our multi-room space with low ceiling. We'll go through the tracking systems we have tested as well as the current solution. We will also discuss the next step of using inside-out tracking.

This page is still a work in progress.

Our current solution.

Advantages

1. Enables kinesthetic interaction by tracking e.g. arm movements
2. Modular camera system with WiFi enables setup in delicate and complex indoor environments
3. No need for multisensor fusion; one camera per area is enough, although multiple cameras improve redundancy e.g. in case of occluded view

Challenges

1. Identification of different persons difficult
   1. Fiducial markers (ArUco); our current solution
   2. Face recognition; tested, but not good results with OpenCV; better results with Visage, but expensive; also, users' privacy concerns must be respected
   3. Feature recognition (clothes colours, etc); tested with bad results
2. Cameras + computers become rather expensive
3. Requires certain amount of light (doesn't work in dim or dark conditions)
4. Generates latency due to intensive computing

Advantage

1. Accurate
2. Tracks head orientation + other objects
3. Small latency

Challenges

1. Expensive
2. Trackable objects need to be equipped with optical markers
3. Not very discrete
4. Potentially not suitable for venues with complex multi-room layout
5. Potentially not possible to install in delicate buildings

Advantages

1. Accurate
2. Tracks orientation
3. Inexpensive

Challenges

1. Limited tracking area when using four base stations
2. More than four base stations not officially supported
3. Potential issues with setting up and interface
   

—-

Advantages

1. Scalable system
2. Orientation tracking (IMU) integrated into the tag

Challenges

1. Potentially inaccurate, especially 3D tracking (although examples of well-working solutions exist, too)
2. Sensitive to environmental interference leading to unpredictable tracking
3. Expensive when expanding the system

Advantages

1. Scalable system

Challenges

1. Doesn't work with low ceilings
2. 2D tracking only

Advantages

1. Relatively accurate

Challenges

1. Makes audible tick sounds
2. Very picky with LOS

-

Advantages

1. Self-sufficient without a need for external base stations
2. Rather accurate
3. Small latency

Challenges

1. Limited tracking area
2. Integration with non-HMD solutions still in beta
3. Setting up potentially difficult and buggy
   

—-

Such as Apple Vision Pro, Microsoft Hololens, Meta Quest, Varjo, etc…

Advantages

1. Rather accurate tracking
2. Built-in processor capacity

Challenges

1. Distract vision
2. Heavy and bulky
3. Some are expensive

Advantages

1. Self-sufficient without a need for external base stations
2. Quite accurate
3. Opens up many extra tracking features

Challenges

1. Expensive units
2. Rigging may be challenging on headphones (shape and weight)

Head-mounted camera(s) connected to an onboard SBC – or camera feed streamed wirelessy to an external computer – for visual odometry calculation. Not tested yet, but has some potential.

Advantages

1. Accurate
2. No need for external sensors

Challenges

1. Drifting issues when magnetometer cannot be used (often the case indoors)