- redefining indoor positioning
System Performance
Results
3.2 m
1.5 m
4 081
13 min
64
409
Average distance
Median distance
Total nr. ofmeasurements
Total nr. ofmeasure-ments
Unique test users
Average session duration
Nr. of test sessions
Test information
* We are constantly recording new test sessions and developing our positioning system. The date shows when the latest update of our accuracy occurred.1. The median indicates the most common experience for the user. The median is typically a more representative metric for data with skewed distributions containing outliers, as is the case here.2. The average distance is significantly impacted by some sessions with large errors, due to unique/extreme use cases, thus the higher scores compared to the median.
Accuracy as of 2024-09-04*
2
1
Methodology for System Accuracy Measurements
Recording of Measurement Data
Our accuracy tests were mainly designed to give insight in how well the system works in a hypermarket environment. To get the most representative demographic of the population, the chosen test persons were mostly hired from a third-party company. The tests were performed using mobile devices such as self-scanners and mobile phones running Android or iOS.
The aim of the test was to mimic natural shopping behaviour as closely as possible. Each test person conducted a series of “sessions” – mock shopping rounds. Each session starts at the entrance of the store, then the user walks to and scans various products before ending their session in the checkout area. A product list of items randomly scattered throughout the store was provided for each session.
At each product scan we measure the distance from the item’s location, according to a planogram, to the output of the tt2 system. To test different use cases of the tt2 system, the provided device either displayed an empty screen or a blue dot on top of the map of the venue.
The data was recorded at 7 different hypermarket venues in 4 different countries. The data provided for the system to use is limited to:
● Signals from internal sensors● Accelerometer- and gyroscope-sensors● Magnetometer sensor when available
● A start location and horizontal device direction relative to the floor plan.
● A floor plan.
In Environments with Scanning Opportunities
2.5 m
1.3 m
3.2 m
1.5 m
4 081
409
Avg. distance
Avg. distance
Median distance
Median distance
Nr. of measurements
Nr. of test sessions
Utilizing scan information
Without utilizing scan information
Test information
* We are constantly recording new test sessions and developing our positioning system. The date shows when the latest update of our accuracy occurred.
1. The median indicates the most common experience for the user. The median is typically a more representative metric for data with skewed distributions containing outliers, as is the case here.2. The average distance is significantly impacted by some sessions with large errors, due to unique/extreme use cases, thus the higher scores compared to the median.
Accuracy as of 2024-09-04*
2
2
1
1
The ability to know where certain products are located can be used as an enhancing factor for our system. This allows the tt2 system to recalibrate if it detects any errors. Reliability of scan locations varies between venues, depending on product exposure points of purchase, incorrect planograms, etc. The tt2 system can dynamically determine the usefulness of a scan and make appropriate adjustments if necessary.
Terminology
Self scanner● A handheld shopping device for scanning retail products, in our tests manufactured by Zebra Technologies. Mobile phone● A smartphone manufactured within the last 5 years. Either an Android or iOS device.
Median distance● The median distance of all measure points between delivered position and ground truth.● Less prone to outlier bias.
Average distance● The average distance of all measure points between delivered position and ground truth.
Nr of test sessions● A session is one shopping round. A session starts at the entrance, consists of a handful of scans and is the ended at the checkout location of that specific store. This measurement gives how many shopping rounds have been conducted in this test set.
Average session duration● The average duration of all test sessions given in minutes.
Total nr. of measurements (scans)● The total number of measurements/scans that have been recorded.