Open area occupancy#
A single wall-mounted A212 radar sensor detects, counts and tracks the people in a defined part of an open space – a group standing and talking, and a passer-by walking through. This page shows how the Presence Tracking Wall Mount application was tested in this scenario, and the results.
Metrics and definitions
| Metric | Definition | Basis | Result |
|---|---|---|---|
| Presence detection The presence of one or more people in the area is detected. | |||
| Detection rate | Share of the time with people present in which presence was detected (recall). The first 1.1 s after someone enters the empty area (the mean detection latency) is not scored. | 7 min | 99.9% |
| False detection rate | Share of the time with the area empty in which presence was detected, scored on recordings of the empty room. | 10 h | 0.00% |
| Detection latency | Time from a person entering the empty area until presence is detected. Mean over entries. |
5 entries | 1.1 s |
| People counting The number of people in the area is counted. | |||
| Counting accuracy | Share of the time with people in the area in which the count matches the ground truth. The first 1.1 s after each entry (the mean detection latency) and 10.0 s after each exit are not scored. | 6 min | 85% |
| Counting accuracy (±1) | Like counting accuracy, but a count within one person of the ground truth is also right; counting 0 while people are present never is. | 6 min | 99.8% |
| Mean error | Mean of the counted minus the true number of people over the same time as counting accuracy: positive is overcounting, negative undercounting. | 6 min | +0.12 people |
| By-passing A person walking through the area is counted while there, and the people standing in it stay counted. | |||
| Passers-by counted | Share of the passers-by (people walking through the area while others stand in it) for whom the count went up while they were in the area. | 7 passers-by | 100% |
| Group stays counted | Share of the time a passer-by is in the area with the count at least the size of the standing group, which the passer-by may hide from the sensor. | 2 min | 100% |
| Counting latency | Time from a passer-by entering the area until the count goes up. Mean over passers-by. |
7 passers-by | 1.4 s |
How we tested
A212 sensor
Detection area
Exclusion zone
Person
Desk fan
Setup
| Room | Open lunch area with round tables and bench seating, opening onto the office and the kitchen: people come and go beyond the detection area. A desk fan runs on a table at (−0.95, 1.95) m. |
|---|---|
| Hardware | XE212 (A2 evaluation kit) |
| Ground truth | People in the detection area, annotated per radar frame from a synchronised camera video. |
| Software | Presence Tracking Wall Mount reference application in Exploration Tool v8.0.0. Default configuration (Exploration Tool preset) with the below modifications: |
| Sensor installation | 2 m above the floor, tilted 20° down. |
| Detection area | −3 to 3 m in x, 0.1 to 6 m in y; −80° to 80° azimuth, −30° to 30° elevation. We recommend a margin of about 10 cm between the detection area and the walls for best performance. |
| Exclusion zones | x = −0.95 m, y = 1.95 m, radius 0.5 m (desk fan position, detections inside this circle are ignored). Place an exclusion zone wherever a stationary object that moves is detected as a person, with a radius large enough to cover all of its detections. |
Test procedure
- Empty areaAbout 15 s, nobody in the area, desk fan running (it runs the whole test).
- Meet and talk2 or 3 people walk in one at a time, about 10 s apart, from different sides, and stand talking.
- Walk-byAfter 20 to 30 s, a passer-by walks in and lingers about 10 s or more, ≥ 1 m from the group.
- Group staysAbout 20 s more after the passer-by has left (in some runs, they pass by twice).
These are the results of this test, not a performance guarantee. In another room, or with another sensor mount, configuration or scenario, results may differ.