Product Details
Wiki & Learn
Reviews
Download PDF

Feature

reCamera:Your Shortest Pathway to Build a Market-ready AI Camera

From AI model deployment to real-world applications, reCamera provides an integrated edge AI platform that helps developers and system integrators build, customize, and deploy intelligent vision solutions faster.
 
Compared with the standard reCamera 2002, the HQ PoE version adds PoE connectivity and extended GPIO, while using a GC2053 sensor with interchangeable M12 lens support.

How does it Works?

reCamera transforms real-world data into intelligent actions through an edge AI pipeline.
 
 
SenseCraft AI is an all-in-one platform designed to empower developers and creators in building and deploying AI projects with ease. The website offers a wide range of tools and features to streamline the AI development process, making it accessible to users with varying levels of expertise.
 

Feature 1: One Cable to Power, Connect, and Deploy Edge AI

reCamera 2002 HQ PoE is designed for fixed AI vision deployments where reliable power and network connectivity matter.

One Cable for Power and Data

Power and network connectivity are delivered through a single Ethernet cable, reducing cabling complexity compared with separate USB power and Wi-Fi connections.
This makes it easier to deploy reCamera at fixed locations such as entrances, production lines, warehouses, equipment stations, and monitoring points.

Connect AI to Existing Equipment

Three GPIO pins (487, 488, 490) allow reCamera to interact with external hardware such as relay modules, microcontrollers, and other embedded devices.
AI detection results can trigger real-world actions including:
 - Alarms and warning lights
 - Door locks
 - Relay modules
 - Motors and actuators
 - External sensors and controllers

 

The extension cable is included:

 

 

Feature 2: Run AI Vision at the Edge

Powered by 1TOPS NPU computing, reCamera comes with pre-installed YOLO11 models for instant AI vision deployment:

- Object Detection
- Object Classification
- Pose Estimation
- Instance Segmentation

Licensing: reCamera does not include an Ultralytics commercial license. For commercial use of Ultralytics YOLO models, please visit Ultralytics YOLO Licensing page for available options.

 

Feature 3: Build AI Applications Faster with Visual Workflows

Connect AI models, devices, and actions through an intuitive visual workflow interface.
 
Powered by Node-RED, reCamera enables developers to build AI application logic with minimal coding — from model inference to real-world actions.
Simply connect nodes for:
 
- Camera input
- AI model inference
- Result processing
- Device control
- Data communication

 

Feature 4: Modular Design
Modular Hardware, Adaptable for Any Scenario
 
reCamera adopts a modular architecture that lets developers configure imaging, compute, storage, connectivity, and expansion options for different deployment needs. 

Sensor Board

Choose the imaging configuration that fits your application.
- OV5647 standard configuration
- GC2053 Sensor Board option
- Interchangeable M12 lenses for different FOV and working-distance requirements
More sensor boards are on the way - feel free to share your needs at GitHub

Core Board

Choose the compute and storage configuration for your application.
- RISC-V based SoC
- 1 TOPS INT8 NPU
- Wi-Fi connectivity options
- 8GB / 64GB eMMC configurations
- Standalone Core Board options for custom builds

Base Board

Choose how reCamera connects to networks, external hardware, and expansion modules.
- USB, Ethernet, and serial interfaces
- Standalone Base Board options for custom builds
- Available Base Board options include Wi-Fi HaLow and PoE with GPIO expansion
- Custom Base Boards can be developed for LoRa, Meshtastic-compatible, and other connectivity requirements
 

Feature 5:Adapt the View to Your Application

reCamera 2002 HQ PoE supports interchangeable M12 lenses for different fields of view and working distances.
1.8mm Fisheye Lens — 160° HFOV, 5MP, F1.8 Ultra-wide coverage for applications where minimizing blind spots matters, such as room monitoring, people counting, and warehouse observation.
2.5mm Wide Angle Lens — 140° HFOV, 3MP Wide field of view with less fisheye distortion, providing a balanced option for general-purpose AI vision.
16mm Telephoto Lens — 20° HFOV, 5MP Narrower field of view for capturing distant targets and focused areas such as entrances, production lines, or equipment.
22mm Ultra Telephoto Lens — 15° HFOV, 2MP Long-distance detail capture with a narrow field of view for remote inspection and small-target monitoring.

Switch lens tutorial:

Choose the Lens by What You Need to See

Detail Capture Pair reCamera with macro or short-focus lenses for close-range tasks such as material inspection and crack detection.
Target Focusing Use telephoto lenses for distant or localized targets such as infrastructure inspection or bird's nest detection.
Wide-area Monitoring Use wide-angle or short-focus lenses for applications such as pedestrian counting, vehicle flow monitoring, or warehouse recognition.

 
reCamera Ecosystem & Configuration Guide
Product Type
Imaging
 
Connectivity & Expansion
OV5647 Sensor Board
GC2053 Sensor Board (M12 Lens Support)
 
Wi-Fi HaLow Base Board
 
PoE + GPIO Expansion
 
Custom Expansion:
LoRa, Meshtastic-compatible options
Complete Camera
 
All 2002 series
 
 
✅
Modular Components
 
✅

 

Feature 6: Fully Open Hardware & Software Freedom

reCamera delivers end-to-end openness across hardware, AI, and software—empowering developers to modify, customize, and optimize their own vision solutions without proprietary lock-in.
 
Open-source resources cover the full stack:
Hardware – schematics, PCB, 3D files
System – Linux (Buildroot, kernel, drivers)
AI – NPU runtime, inference pipelines
Applications – Node-RED workflows, C++ SDK, APIs
 
From silicon to software, all source files, drivers, and models are public. No black boxes. Fork it, build it, and deploy it.
Click here: GitHub

 

 

Feature7: Seamlessly Integrate with Existing Systems

 
reCamera outputs data through standard protocols such as RTSP, HTTP, WebSocket, and TCP/UDP, virtually any online platform or application. Also, use MQTT to connect to other IOT devices.

It also works with Frigate.

 

Feature 8: Flexible Installation Options

Compact and adaptable, reCamera is designed for flexible deployment across different environments.
reCamera 2002 series: (40 × 40 × 36.5 mm)
reCamera HQ PoE: (40 × 40 × 53.1 mm)

 

Magnetic mounting
Tripod installation
IP66/IP67 enclosure options
Wall mounting(External case required (sold separately))
2002 ✔
2002 ✔
2002 ✔
2002 ✔
 
HQ PoE ✔
HQ PoE ✔
HQ PoE ✔
 

Extend reCamera 2002 HQ PoE to outdoor applications with a protective enclosure.

IP67-rated enclosure | Waterproof & Dustproof | Metal Housing | Outdoor & Industrial Applications
Add Enclosure tutorial

Note: Waterproof performance may vary depending on installation conditions. IP67 protection after installation is not guaranteed. This enclosure is recommended for POC validation and non-critical applications. For deployments requiring certified or strict waterproof protection at scale, please contact us for customization options.
 
Feature 9: Turn Vision Intelligence into Real-world Applications
  With reCamera, developers can quickly transform AI models into practical vision applications across industries.
 
  Smart Site Security


Deploy customizable AI vision across your entire site to monitor people, vehicles, and safety compliance in real time. reCamera enables on-device detection of specific objects and behaviors, triggering instant alerts or structured events without relying on cloud processing.
Perimeter Security | PPE Compliance | Vehicle Access Control | Restricted Area Monitoring
 
 Smart Warehouse Management

From conveyor lines to storage racks, reCamera brings flexible AI vision to every step of warehouse operations. Train custom models to recognize packages, monitor inventory status, and detect operational exceptions — all processed locally at the edge for faster decisions.
Custom Object Recognition | Quality Inspection | Inventory Tracking | Edge AI Automation
 
Smart Livestock Monitoring
  Every farm has unique management needs. With customizable AI models, reCamera helps farmers recognize specific livestock, track animal populations, and detect unusual behaviors — enabling automated monitoring without complex infrastructure.
Custom Animal Recognition | Population Tracking | Behavior Analysis | Smart Farm Automation

 

  • Object Classification: Classify the entire image
  • Parking Occupancy Detection: Identify available and occupied parking spaces
  • People Counting: Detect and count foot traffic in crowded areas such as subways and malls.
  • Restricted Area Intrusion Detection: Detect unauthorized entry into hazardous areas
  • PPE Detection: Verify whether workers are wearing required personal protective equipment
  • Object Tracking: Track targets and visualize their movement paths
  • Fall Detection: Detect falls using human pose estimation
  • Smart Fitness Assistant: Evaluate exercise form using pose estimation
  • Defect Detection: Segment surface defects on parts or equipment

More demos waiting to be explored, such as a turn your reCamera into a motion-sensing game controller.

 

 

Specification

  reCamera BasicreCamera Pro
 Product SeriesreCamera 2002 SeriesreCamera HQ POEreCamera Gimbal
 Mounting MethodMagnetic/Quarter-inch screw threadQuarter-inch screw thread/Quarter-inch screw thread
Core Processing & SystemAl Performance1TOPS@Int83TOPS @ INT8
SOCSG2002RV1126B
CPUC906@1GHz + C906@700MHzQuad-core Arm Cortex-A53 processor
MCU8051@8KB SRAMRISC-V MCU as Co-processor
Memory256MB2GB/4GB
eMMC8GB/64GB16GB
Operating SystemOS Type: Embedded Linux (Buildroot)
Kernel Version: 5.10.4 (RISC-V 64-bit)
Instruction Set: RV64IMAFDVC
Buildroot
Video Codec1080p @ 30FPS4k@30FPS
Imaging SensorCamera SensorOV5647GC2053OV5647SC850SL
Optical Format1/4" CMOS Sensor1/2.9inch1/4" CMOS Sensor1/1.8-inch, starlight-level
Pixels2MP2MP2MP8MP
Pixel Size1.4μm 1.4μm2.0μm
Resolution1920x10803840×2160
Max Frame rate30fps@full size4k30fps
Output FormatRAW 10 RAW 10RAW,MP4,JPG
Shutter TypeRolling Shutter
Optics & Lenslens mount/M12/M12 x 0.5mm
Focal Length3.46mm2.9mm ±0.5%3.46mm2.75mm
ApertureF2.8F2.4
FOV65°93°65°123°±5°
Minimum Focus Distance 39CM 0.6m ~ Infinity
Focus Distance(DOF) 50 CM 2.7m
Connectivity & InterfacesEthernet100Mbps1000Mbps
WirelessWi-Fi 2.4G/5G Bluetooth 4.2/5.0/Wi-Fi 2.4G/5G Bluetooth 4.2/5.0Wi-Fi 2.4G/5G WIFI 5.0 Bluetooth 5.4
USBUSB Type-C(2.0)USB Type-C(3.0)
Expansionremovable TF card (up to 512GB)//removable TF card (up to 512GB, not included)
CSI    Supports 2-channel 4-wire MIPI-CSI interfaces (One additional interface supports Raspberry Pi camera modules.)
Output Port/1 x RJ45 port for 802.3af PSE.
1 x UART port.
1 x Debug port.
3 x IO port.
CAN2 x CAN
2 x GPIO
1 x UART
1 x Debug UART
1 x MIPI DSI
HMI & PeripheralsButton1 Reset Button, 1 Boot ButtonA custom button
Status Light1 × Power Indicator, 2 × IO Programmable IndicatorPower indicator light*1, Status indicator light*1
Fill Light4 × 0.3W White Light/4 × 0.3W White Light/
MicOn-board Micmic * 2
SpeakerBuilt-in speakerBuilt-in speaker
Physical & EnvironmentalDimension40x40x36.5mm40x40x45.8mm, 40x40x53.1mm with lens68×112×71mm67*67*89.8mm
Power Supply5V 1A5V 1A12V DC Jack to XT30 connector12V 2A(DC),POE,TYPE-C,Battery(7.4V)
Power Consumption  12V, 185mA (static) 
Operation Temperature0~50°C 
EnclosurePolyamide (PA) Nylon 
Weight (Net)66g75g230g324g±1g
Motor SpecParameter/MS3008MS3506/
Turns5460
Rated Voltage (V)12
Max Speed (rpm)20002100
Rated Torque (N·m)0.040.05
Rated Speed (rpm)11601250
Rated Current (A)0.640.79
Max Power (W)4.66.4
Motor Poles14
Operating Temperature (℃)-25~60
Weight (g)4963
Drive Input Voltage (V)6~16
CommunicationCAN
Communication FrequencyCAN@1Mbps:2KHz
Encoder15-bit Magnetic Encoder
CAN Baud Rate100K、125K、250K、500K、1M
Control ModeOpen Loop(24KHz) / Speed Loop(4KHz) / Position Loop(2KHz)

Hardware Overview

Application

Integration of Real-time Heatmap with Grafana Data Dashboard

The project conducts target detection using the YOLO11n model built into reCamera. It performs fuzzy processing on personnel targets and displays a heat map effect. All of this is handled locally within reCamera! And reCamera will send the detected data to the locally running Influxdb database. Then, Grafana reads the data from the Influxdb database to display real-time data dashboards.

 

 

AI Remote Wireless Monitoring System Based on reCamera and Wifi Halow

An AI-based remote wireless monitoring system using Wi-Fi HaLow. It combines edge AI vision with long-range, low-power wireless communication to enable real-time detection, data transmission, and monitoring in remote or infrastructure-limited environments such as farms, factories, and outdoor sites.

Video link: https://www.linkedin.com/posts/seeedstudio_howtobuildanaicamera-outdoor-wifi-activity-7401880305940553729-R57w?utm_source=share&utm_medium=member_desktop&rcm=ACoAAGCDEqUBKdDsqK6EqGXClNocxAAtw3IA_T0

Tutorial: AI Remote Wireless Monitor System with Wifi HaLow | Seeed Studio Wiki

 

 

AI Parking Management with reCamera

This project uses Seeed's reCamera to detect parking slot occupancy in real-time. It features multi-frame stabilization to avoid flickering and displays results (free/occupied counts) directly on the video stream. The entire workflow runs automatically on the device via a pre-configured Node-RED setup.

Tutorial: AI Parking Slot Monitoring Demo with reCamera | Seeed Studio Wiki

 

 

Play Subway Surfers with reCamera HQ PoE

Using its built-in pose detection model, reCamera can recognize your hand and body movements in real time and convert them into game actions, no controllers, no wearables, just pure gesture play. Wave your hand to jump, raise your arm to attack, or lean left and right to dodge obstacles.

Video link: https://www.linkedin.com/posts/seeedstudio_howtobuildanaicamera-recamera-yolo11n-activity-7399730949401526272-UdZ4?utm_source=share&utm_medium=member_desktop&rcm=ACoAAGCDEqUBKdDsqK6EqGXClNocxAAtw3IA_T0

Tutorial: Play Subway Surfers with body sensor control | Seeed Studio Wiki

Certification

HSCODE8525891900
USHSCODE8525895050
UPC
EUHSCODE8517600000
COOCHINA

Part List

reCamera 2002x HQ PoE

x1

USB Type-C Wire

x1

Ethernet Wire

x1

User Manual

x1

6 Pin Cable

x1

reCamera 2002 HQ PoE 8GB - Your Shortest Pathway to Build a Market-ready AI Camera

SKU 100029708

reCamera PoE is a fully open-source, modular AI camera. It runs Linux on an embedded AI SoC, delivers 1 TOPS @ INT8 computing power, and comes with built-in YOLO models and Node-RED. Equipped with a 1/2.9'' CMOS sensor, replaceable M12 lenses (90° FOV by default), PoE and GPIO it is a network-ready smart eye for any system. reCamera is the go-to AI camera for YOLO at the edge.

Product Type
Wireless Capability
Memory
USD$101.11
$109.90
Save $8.79(8%)
Shipping and duties calculated at checkout.
  • Free Insurance Included On Us
  • Flexible Payments with PayPal Pay Later
  • Avoid Import Fees: Ship Tax-Free from Local Warehouses
  • 1 on 1 Support | 12-Month Warranty | 30-Day Return Policy