Sogo & Seibu Co., Ltd.
Sogo & Seibu wanted visibility not only into customers who bought something, but into the number, demographics and movement of everyone who visited — so that floor initiatives and tenant strategy could be based on evidence.
The challenge Idein solves
We installed edge AI cameras in the ceilings of the sales floors to estimate visitor counts and attributes (gender, age group). In later phases we added ReID — vectorizing facial features to judge whether two sightings are the same person — so movement across floors could be followed. Because the AI analysis runs entirely on devices costing a few thousand yen, deploying many cameras across large floors does not inflate the cost. Footage is converted to metadata on the spot, and no personally identifiable information is sent to the cloud.
What we did
- 29 AI cameras at Seibu Ikebukuro (B1 and 2F) and 13 at Sogo Omiya (B1 and 2F), capturing visitor counts and attributes (gender, age group)
- A follow-up study at Sogo Omiya (19 cameras across B1, 2F and 7F) used ReID to analyze movement between floors
- About 70% of visitors in their twenties reached the food floor by way of the upper floors, versus 30–50% for those in their thirties to sixties — confirming with data that younger visitors tend to buy on the way
- Analysis completes on the edge; only metadata that cannot identify individuals is collected
- Related release: Idein begins AI camera–based customer analysis at Sogo & Seibu stores (Idein, PR TIMES)