Small Retailer
In-store behavioural analytics
Multi-zone, wide-area coverage
Advanced path tracking & interaction modelling
Behavioural Language Model (BLM)
Vision-Language Models (VLM)
Multi-device support (Pro1 / IP CCTV Cameras)
Designed for Large Spaces
Standard deployments require one device per zone or per door. Pro3 is built to operate across large areas by connecting multiple cameras to one device, enabling full-store analysis without increasing system complexity.
One Device. Up to 8 Cameras.
Pro3 operates as a central processing unit that connects to multiple Pro1 or IP cameras. A single device can support up to 7 additional cameras, extending coverage across large areas without adding processing units.
Complete People Counting Metrics
Pro3 remains a full-featured people counting system. It uses stereo 3D counting with AI processing to deliver accurate results and supports up to eight metrics, including demographics, staff filtering, group counting, and visitor classification.
Eight Metrics. One System.
Pro3 measures activity across the entire store, from entry points to interior zones, using a single system. This ensures all counting outputs are aligned and comparable across different areas and conditions.
Behaviour Classification
Pro3 uses Vision-Language Models (VLM) to classify shopper behaviour into discrete, machine-defined states. Each detection is categorised consistently based on posture, movement, and interaction signals, enabling structured analysis of engagement across the store.
Phone Distraction
VLM Output: Person stationary, attention directed to mobile device. No product interaction.
Not Engaged
Casual Glance
VLM Output: Brief visual attention towards products, no hand interaction
Lvl1:Light engagement
Active Browsing
VLM Output: Sustained visual focus on products with exploratory behaviour.
Lvl2: Browsing
Deep Product Interaction
VLM Output: Direct product handling and evaluation behaviour.
Lvl3: High Engagement
Talking to Friend
VLM Output: Conversation detected, not related to product interaction
Not Engaged
Talking About Product
VLM Output: Shared attention towards product with discussion behaviour.
Lvl4: Staff Engagement
AI-generated illustrations only; no real customer data, surveillance footage, or personal information is used or captured.
Flow Analytics
Pro3 measures how visitors move between areas of the store by linking zone-level detections into continuous paths. This allows identification of high-traffic routes, drop-off points, and area-to-area transitions.
Complete Store Measurement
Pro3 measures traffic, engagement, and flow across all areas of the store. Data is captured and structured at the space level, enabling comparison between zones and across time. This allows consistent evaluation of how visitors move, where they spend time, and how activity is distributed throughout the space under different conditions and time periods.
Specifications
|
Device Dimension (mm) |
148 (W) x 118 (D) x 28 (H) |
|
Weight |
Device: 0.55 kg Packing: 1.24 kg |
|
Camera |
2x 5MP, 160°, 5MP omni-vision 5647 camera modules |
|
Illumination |
Minimum 1 lux (with external Infrared light source) |
|
Frame Rate |
25 fps (Live Stream of counting will only display 1024x780 resolution to reduce bandwidth sent to database for verification purpose) |
|
Indicator |
RGB LED status indicator |
|
CPU |
ARM Cortex Octa-core Processor |
|
Casing |
Full Aluminium Enclosure with ABS Front Cover |
|
Storage |
Built-in, 32 GB eMMC Storage |
Technical Integrity
Pro3 uses multi-processor architecture and partitioned systems to maintain continuity during software or hardware faults. It supports graceful degradation and preserves analytics reliability in demanding retail environments.
FAQs
Learn More