Tracking indoor movement

5 min readJun 11, 2021

Ways of tracking the movement of active participants using wheelchairs indoors. Considering both realtime and offline solutions with a mix of low resolution motion capture and indoor positioning.

Requirements

Identity is not essential when tracking since we are working with active participants.
Precision matters for movement but we can do post-corrections.
Not full skeletal tracking, wheel motion tracking.
Solutions must not be heavy or impeded wheelchair movement.
Tracking within large indoor venues, with multiple floors, lifts, walls and doors.
Function without complex indoor installation setup.

Solutions

Paper maps

With activate participants we can draw our journeys either during or after on a map. Journeys could also be recorded using portable cameras and used to manually reconstruct the routes and motion.

Misses subtle movement of the wheels during journey.
Extra requirement on participant might hinder the drawing experience?

Physical marking

Using sand, water or chalk, journeys could be marked physically indoors. Potential to use fabric or paper on the floor as a temporary surface to be marked by the motion of wheels.

Requires permission to mark indoors
Requires cleanup.
Challenges with setup, application and impeding normal wheeled movement.

Phone with Gps (assisted by network)

Using global positioning satellites on a phone. Tends to be inaccurate when indoors. The satellite signal is augmented by location information determined from the phone base station identity, distance and if more than one base station triangulation.

Top down view of a map showing two routes as coloured lines. One is a straight path through a tunnel, the other which is the gps tracked route varies wildly zigzagging all over the map. — Indoor gps tracking with windows. Red = actual route, Blue = tracked route.

5g introduces some new proposals on improving indoor location estimation. A faster communication speed also means more accurate location information. It’s unclear when this might be available.

Inaccurate indoors.
No guarantee of any signal at all.
GPS low resolution misses the naunces of wheel movements.

Phone based IMU & Camera

Most phones contain inertia measurement units (IMU) that use gyroscopes, magnetometers and accelerometers to record a phones absolute movement. Combined with a live camera view we can perform surface and depth estimation without a special depth camera. This combined sensor data is how Augmented reality applications provide viewing and drawing.

An augmented view of a pavement with computer graphics showing a curving line moving back and forth along the pavement. — Marking using Augmented reality

IMU Sensors drift over time with errors increasing.
Surface and depth estimation is highly affected by lighting conditions
Depth/Lidar sensors on phones are restricted to the most expensive devices.
Positioning of AR to real world is still rooted on GPS location and has the same inaccuracy.

Bluetooth

Bluetooth low energy (BLE) beacons are distributed around the perimeter of the space and using Bluetooth help track a device such as a phone with up to 3m accuracy.

Beacons allow 50 to 70 meters range.
Beacons are cheap.
Beacons run on small & long lasting battery.
Most phones support bluetooth.
Requires a significant number of beacons for large spaces.

Wifi

Multiple wifi routers are used by a device to measure the differential-time-of-arrival for a signal between device and router to identify location. Apple provide a closed service and app called “indoor survey” for this function.

Indoor Maps

Easily create detailed maps of your indoor spaces and let visitors see where they are right in your app. Organizations…

Requires regular surveying of existing wifi on site.
For accuracy usually have to control the wifi routers used.
Tends to suffer from lots of errors in calculations due to multipath signals (radio signals reaching the antenna by two or more paths).

Ultra Wideband (UWB)

Uses a high bandwidth, low power frequency to communicate. Multiple anchors are spread through a space to help identify and track a node. This is the technology used by Amazon warehouses and is being introduced by Apple with their AirTag product.

AirTag

Misplacing something like your wallet doesn't have to be a big deal when it has AirTag attached. You can play a sound…

www.apple.com

Provides extremely accurate (cm level) positioning
Supported by current Iphone range 11+.
Can penetrate thin walls.
Expensive (1k-3k) for a dev kit.

External, more open kits are available:

https://store.pozyx.io/product/50-001-0001-creator-kit-65

Computer Vision (without markers)

Post or realtime processing of camera feed to extract movement. There is a varying level of complexity based on multiple feeds, the amount of changing noise in the scene and occlusion. With developments in machine learning there have been lots of improvements in camera tracking without special markers.

Seems to require very controlled environments.
High level of complexity in hardware, software and training data.

Marker tracking

Placing special markers onto the device to be tracked. Markers can be:

Passive — coated in a reflective material and a separate device near the camera provides light.
Active — trackable LEDs (such as Infrared)

This is the industry standard for high precision motion capture. Used frequently in special effects and digital entertainment. There are many companies providing this technology for indoor and outdoor applications.