Existing Cameras Work

Any IP camera with an RTSP stream connects to reComputer

Video Stays in Store

The footfall backend stores numbers, not identities

No Retraining for New Items

Register a new product with 3–8 photos

Scenario details

Three tasks: foot traffic, product recognition, unmanned-store access.

Footfall & Heatmaps

Pain Points & Challenges

Traditional beam counters cannot separate turnarounds from dwell time; uploading raw video to the cloud incurs heavy bandwidth and GPU costs while triggering customer privacy issues.

Edge AI Solution

A high-angle camera detects and tracks people on the edge device so raw video stays inside the store, returning only structured counts and floor-plan heatmaps to your dashboard.


Core Advantages

  • Edge Footfall: Counts entries, exits, and shelf dwell time locally
  • Perspective: Four-point mapping projects heatmaps onto floor plans
  • Local Privacy: Outputs structured metadata only without exporting video

Entries & Exits

Counts people present, entering and leaving by zone; results feed your system.

Dwell at Shelves

Where shoppers stop and for how long, to place featured products.

Floor-Plan Hotspots

Four matching points calibrate each camera onto one store floor plan.

Smart Retail People Flow Heatmap

Ready to deploy
$npx -y @seeed-studio/solution-cli deploy recamera_heatmap_grafana
View full design & BOM →

Products & Shelves

Pain Points & Challenges

Manual barcode scanning causes slow checkout lines and high labor costs; visual shelf audits miss gaps in real time, while legacy AI requires retraining for every SKU update.

Edge AI Solution

An edge host recognizes whole-basket items and audits shelf slots on site. New products register from 3–8 photos without retraining, connecting to your POS via local APIs.


Core Advantages

  • Basket Items: Counts multi-item basket in one shot without barcode scans
  • Zero Retrain: Registers new SKUs with 3–8 photos via feature vectors
  • Slot Audit: Detects stockouts and misplaced items without manual walks

Whole Basket at Checkout

The till reads a basket and counts items, with no item-by-item scanning.

Shelf Gaps & Misplacements

Each slot reports OK, empty, wrong item or unknown, with no shelf walk.

New Products

Register each SKU with 3–8 photos, no retraining; the library can roll back.

Supermarket Product Recognition

Ready to deploy
$npx -y @seeed-studio/solution-cli deploy edge_retail_recognition
View full design & BOM →

Unmanned Store Access

Pain Points & Challenges

Physical keycards are easily lost or shared; phone QR code entry fails if the store internet drops; single-lens face readers can be spoofed by photos and videos.

Edge AI Solution

An AI camera with dual-lens liveness verification matches whitelists locally and controls electronic locks, operating reliably offline while keeping tamper-proof entry logs.


Core Advantages

  • Offline List: Matches 1,000 local profiles and unlocks in 0.66 seconds
  • Anti-Spoof: Dual-lens liveness and tamper-proof logs operate offline
  • Relay Link: Onboard relay directly triggers electromagnetic locks

Store & Back Doors

Unmanned storefronts and night-restock back doors open by face, no keys.

Access Records

Grants and denials logged by time, device and person; searchable, not editable.

People List

Staff list synced on a schedule; the last version is kept offline.

Unmanned Store Face Access

Ready to deploy
$npx -y @seeed-studio/solution-cli deploy unmanned_store_access
View full design & BOM →

Deployment & Selection

Determine the architecture based on new store points or existing camera reuse; edge hosts and all-in-one AI cameras close the loop on site.

Not sure which to choose? Read the Full Selection Guide →

Store Task

What do you want the cameras to do? Each task maps to one reference design.

Configure Your Setup

Pick the store task and your current cameras to get the matching devices

  • Footfall: reCamera All-in-One

    One reCamera 2002 per counted area, plus a reComputer R1125-10 as the dashboard backend; cameras added later publish to the same backend

    硬件/物料名称数量型号/SKU说明
    reCamera 20021102991895-
    reComputer R1125-10 (dashboard backend)1113991334-
  • Footfall: Existing IP Camera + reComputer RK3588

    Keep the existing IP cameras; reComputer RK3588 detects and tracks, and the dashboard backend can run on the same host. Measured 13.2 FPS on one stream; test your own camera count before sizing for several streams

    硬件/物料名称数量型号/SKU说明
    reComputer RK35881100071234-
    IP camera (customer-supplied, RTSP)1--
  • Checkout: reComputer J4012

    One camera above the checkout belt connects to reComputer J4012; the console (product registration and MQTT) needs a separate computer with Docker

    硬件/物料名称数量型号/SKU说明
    reComputer J40121110110145-
    Camera (customer-supplied, RTSP or USB)1--
  • Shelf: reComputer RK3588

    A camera facing the shelf connects to reComputer RK3588; the console (product registration and MQTT) needs a separate computer with Docker

    硬件/物料名称数量型号/SKU说明
    reComputer RK35881100071234-
    Camera (customer-supplied, RTSP)1--
  • Access: reCamera Pro

    One reCamera Pro per door, recognizing on the camera itself with its GPIO wired to a nearby relay; the relay, lock and lock power are configured by the installer

    硬件/物料名称数量型号/SKU说明
    reCamera Pro1100092895-
  • Access: Existing IP Camera + reComputer J3011

    The existing IP camera at the door connects to reComputer J3011, with recognition in a container on the host; one host can serve several doors. The relay, lock and lock power are configured by the installer

    硬件/物料名称数量型号/SKU说明
    reComputer J30111110110147-
    IP camera (customer-supplied, RTSP, at face height)1--

Architecture Topology

On-camera inference vs in-store edge host

Store vision is made of cameras, a compute host, and a dashboard or console. Stores without cameras use reCamera, which captures and recognizes in one device; stores with IP cameras keep them and add a reComputer host.


Core Advantages

  • Standalone: All-in-one camera executes footfall and access locally
  • Camera Reuse: Edge host aggregates existing IP camera RTSP streams
  • LAN Push: Analytics pushed to local dashboard over LAN in milliseconds
ImageProductStore TaskOpticsMeasured on Device
reCamera 2002reCamera 2002Footfall and heatmap (small nearby area)1080P—
reCamera ProreCamera ProUnmanned store access; footfall (large area)4KFace to unlock signal 0.66 s (1000-person library)

Store Cameras

All-in-one AI cameras and RTSP camera reuse

This block covers store capture. Points without cameras use reCamera 2002 / Pro, one device for capture and recognition; points with IP cameras keep them and send the stream to the compute host. Position sets quality: footfall sits high looking down, 3–5 m out, Pro (4K) for large or distant areas; checkout sits directly above the belt, items fully visible; shelf cameras face the shelf, sample full shelves by slot, 3+ photos per SKU; access sits at face height where people stop, away from backlit doorways and glare, calibrate after mounting.


Core Advantages

  • All-in-One: Smart camera captures and infers without extra video lines
  • Stream Reuse: Retains existing IP cameras and feeds RTSP directly to hosts
  • Sub-Second: Sub-second face unlock and multi-stream customer tracking
ImageProductStore TaskCamera InputMeasured on Device
R2135-12R2135-12Footfall and heatmapIP camera (RTSP)14.3 FPS tracking per camera (15 FPS source)
RK3588RK3588Shelf recognition; footfall and heatmapIP camera (RTSP)Shelf: detection to result 924 ms (p50); footfall 13.2 FPS per camera
RK3576RK3576Footfall and heatmapIP camera (RTSP)13.3 FPS tracking per camera
J4012J4012Checkout recognition; footfall (several cameras per host)IP camera (RTSP) or USBCheckout: detection to result 22.3 ms (p50), 0 dropped in 2956 frames
J3011J3011Unmanned store access (existing camera)IP camera (RTSP)—

Edge Compute Host

Multi-stream aggregation and local inference

This block pulls RTSP streams and runs detection and recognition. Footfall rates are single-stream; test before sizing a host for several cameras. Checkout and shelf figures come from the reference designs.


Core Advantages

  • Host Choice: RK3588 recommended for multi-stream traffic and shelf audit
  • High Load: Jetson Orin NX box handles intensive basket checkout tasks
  • Multi Stream: Single edge host ingests multiple RTSP streams for inference

FAQ

Didn't find your answer?
Contact Us
We Are Glad to Be Your Hardware Partner !
Next