Small Retailer
From Vision to Behavioural Understanding
Traditional video analytics measure where people are and how long they stay. This creates useful signals, but they remain interpretations. A person standing in front of a shelf for twenty seconds may be browsing, waiting, distracted, or not engaged at all.
FootfallCam introduces a new generation of video analytics that understands context - what people are doing, how they interact, and what it means for your business.
Business Usefulness in Retail
Instead of relying on time thresholds or proximity alone, the system interprets behaviour - body orientation, hand movement, interaction patterns, and situational context. It distinguishes between a shopper actively considering a product, a casual glance, a staff member restocking, or a person simply passing time. The result is not a guess, but a classified outcome aligned to real-world behaviour.
Area |
Applications |
Value to Business |
|
Customer Engagement |
Detects real interactions between customers and staff |
Evaluate service quality and staff responsiveness |
|
Merchandising Impact |
Understand browsing patterns and dwell intensity |
Measure true product engagement beyond footfall |
|
Checkout Service |
Classifies greeting, serving, upselling, and handover moments |
Measure service quality in a consistent, auditable way |
|
SOP Adherence |
Monitors defined service behaviours and process steps |
Improve operational discipline and training |
|
Validation & Coaching |
Stores reviewable event clips and classified outcomes |
Turn observations into evidence, coaching, and improvement |
How It Works in Practice
Metrics: Contextual, Not Just Movement
Contextual Categorisation
VLM refines what a person is doing within a detected zone or interaction:
- Shelf zone: glance, browse, active product interest
- Staff interaction: asking, being served, upsell interaction
- Checkout: payment, completion, handover
This turns a simple “20 seconds in front of shelf” into a defined behaviour category.
Built-in Validation
The same mechanism verifies whether an observed action is genuinely meaningful:
- Distinguishes shopper engagement vs staff restocking
- Filters out idle or irrelevant presence
- Confirms whether interaction actually occurred
This removes ambiguity from traditional metrics and increases trust.
Why This Matters
Moves from assumption → evidence
Reduces false interpretation of dwell time and presence
Provides verifiable context, not just positional data
Enables consistent measurement of real-world behaviour
Classifying Shopper Behaviour
The system identifies and distinguishes subtle differences in posture, attention, and interaction to classify behaviour types, from non-engagement to active product interaction and staff engagement, enabling structured interpretation of shopper movement and intent.
AI-generated illustrations only; no real customer data, surveillance footage, or personal information is used or captured.
Engagement metrics:
Phone Distraction
Engagement metrics:
Casual Glance
Engagement metrics:
Active Browsing
Engagement metrics:
Deep Product Interaction
Engagement metrics:
Talking to Friend
Engagement metrics:
Talking About Product
The Future of In‑Store Understanding
After visitors enter, zone counting shows where people actually go inside the mall.
Zones are commonly defined as:
- Major wings (for example, East / West)
- Atriums
- Key corridors between anchors
