Only the purchase remains
Traffic and gaze in front of the piece do not appear anywhere in POS.
Product · saai ads insight · signage & display response
Real response,
in front of each ad.
Traffic, approach, attention, action. Measure response per piece.
No identification. Only gaze and response
saai product module · adopt on its ownOn the CCTV you already have
Why outcome data cannot value an ad spot
The spot has no evidence
Near-purchase placements should be evaluated by the response on the floor.
saai ads insight measurement
From people passing,
to gaze that stays.
Measure traffic, approach, attention, and action per piece. The next placement has evidence.
From traffic to gaze
Read passersby and sustained gaze together
Traffic shows scale. Gaze shows attention. Read both signals in the same scene before the next placement decision.
Traffic and approach
See who passed the piece and the share who turned toward it.
Attention
Read where gaze stopped and how long it stayed.
Action
Optionally connect a follow-up signal such as product pickup.
Example
Traffic counting
Only counts who passed
51
Traffic
51
Gaze analysis
Where gaze stopped, and for how long
No raw video stored
Attention
27%
Avg. gaze
2.8s
Outputs
What it measures
Four stages of response in front of a piece. What to check before the next placement.
Traffic
How many walked past the piece, hour by hour.
Approach
The share of those who turned and drew closer.
Attention
Where the gaze stopped, and for how long.
Action
Picked up or passed by. An optional signal.
38%
* Figures are illustrative.
Through detect, analyze and act
One measurement reads three ways
care detects the same piece, insight analyzes it, and agent connects it to the action.
- saai careSense
What needs attention?
Live gaze response in front of displays, POP and signage
- saai insightAnalyze
Why did it happen?
Attention per piece analysed (gaze→pick, approach conversion)
- saai agentThink
What should we do?
Golden-zone, placement and exposure priority suggested
Where it fits
For brand & retail advertising / VMD teams, and signage & shelf operators.
Drugstore tester zone
See which tester holds attention and signals a move toward try-out.
Convenience endcap
The real pull of endcaps and promo shelves, piece by piece.
Exhibition booth
Dwell and gaze in front of a booth or exhibit, along the visitor path.
What it looks like
Gangnam Stn. DOOH Dashboard·Today 09:41
ExampleTotal Footfall
1,160
+8% vs yesterday
Watchers
317
27% of passersby
Attention Rate
27%
3%p below 30% target
Avg Attention
2.8s
of 7.4s dwell
DOOH Audience Attention Funnel
Pass1,160 (100%)
Approach650 (56%)
Watch317 (27%)
Act121 (10%)
Screen Attention Performance Ranking
| Screen | Location | Avg Dwell | Avg Attention |
|---|---|---|---|
| Signage A | Wall display left of the entrance | 8.2s | 3.1s |
| Signage B | D · Aisle 3 | 7.1s | 2.6s |
| Wall POP C | Checkout side | 6.5s | 2.2s |
No facial video stored · Anonymized gaze vector data
Where it goes
01
Targeting
Review placement by daypart and customer mix. The mix is an anonymous estimate.
02
Objective results
See exposure, attention, and conversion as numbers. Use them in placement pricing discussions.
03
Bidding
Build toward a market for buying and selling shelf-front placement.
- 103 patents
- SOC 2 · PIPA certified
- 1,700+ cameras connected
- 8+ partner brands
Privacy by Design
Anonymization comes first. The SEAL engine
No video stored
Deleted after analysis, stats only
No originals kept
Source footage is never retained
No re-identification
Identity removed, flow only
CV reads the floor while SEAL removes identity. Every measurement uses anonymized spatial data, so no one is identified.
Where it leads
Connect traffic, approach, attention, and action around each piece to review the next placement.
All products