- ✨ What's reCamera?
- 🔖 Product Series
- 🚀 Launch Notification--reCamera Gimbal
- ⚙️ Hardware Overview
- 💾 reCamera Softwares
- 🔩 Related Projects
- 🧱 Application Demo
- 🎳 reCamera Roadmap
reCamera is a combination of a processor and a camera sensor.
This combination makes reCamera a standalone system that can handle basic detection and control tasks on its own.
The first reCamera series - reCamera SG2002 is an open-source and tiny size AI camera, programmable and customizable, powered by an RISC-V SoC, delivering on-device 1 TOPS AI performance with video encoding 5MP @30 FPS. The modular hardware design and expandable interfaces offers the most versatile platform for developers building vision AI systems.
| reCamera Gimbal 2002w 8GB | reCamera Gimbal 2002w 64GB | reCamera 2002 8GB | reCamera 2002 64GB | reCamera 2002w 8GB | reCamera 2002w 64GB | |
|---|---|---|---|---|---|---|
| Core Board | Core 2002w 8GB | Core 2002w 64GB | Core 2002 8GB | Core 2002 64GB | Core 2002w 8GB | Core 2002w 64GB |
| Sensor Board | S101(OV5647) | S101(OV5647) | S101(OV5647) | S101(OV5647) | S101(OV5647) | S101(OV5647) |
| Base Board | B401 | B401 | B101 | B101 | B101 | B101 |
| Wireless (Wi - Fi/BT) |
✅ | ✅ | ✅ | ✅ | ||
| Mounting Method | Vertical | Vertical | Magnetic/Camera Bracket Mount | Magnetic/Camera Bracket Mount | Magnetic/Camera Bracket Mount | Magnetic/Camera Bracket Mount |
| Power Supply | DC Jack cable/XT30(2+2) | DC Jack cable/XT30(2+2) | Type - C cable | Type - C cable | Type - C cable | Type - C cable |
Today, as processors (both SOC and MCU) are becoming smaller and more powerful, it is now possible to combine the processor with camera sensors. In fact, many IPCs (IP cameras) are already using this design to accelerate AI detection on edge devices.
So today, we introduce reCamera, an open-source camera platform for everyone to play with. We have divided this project into 3 interchangeable parts:
- Core Board
- Sensor Board
- Base Board
This design allows you to easily change the interfaces and camera sensors to suit your needs. We hope that these components can be freely combined in any way.
By building this hardware platform and ecosystem, we enable other applications to grow on this platform without the need to worry about changing from one platform to another in the future.
The engineering focus on modularity, high performance, and ease of use ensures that reCamera serves as a powerful platform for developers and makers. This design streamlines complex hardware processes, allowing users to integrate vision AI capabilities into their systems efficiently and creatively.
We've taken care of the intricate hardware work, freeing up time for user innovation. The modular design enables users to rapidly switch cameras and customize interfaces, transforming development from months to weeks only!
We are excited to announce that the reCamera Gimbal will be released at the end of February! Stay tuned and follow the Seeed Studio official website for the latest updates.
The reCamera gimbal 2002 series is the first open-source camera control system, composed of one tiny AI camera - reCamera 2002w 8GB/64GB, and one compatible 2-Axis gimbal basement with 2 brushless motors. It is powered by an RISC-V SoC, providing 1 TOPS AI performance with video encoding at 5MP @ 30 FPS. It offers a Lego-like self-assembly package and integrates the Sensecraft AI platform and Node-RED platform for smooth graphical programming and pipeline construction, enabling rapid self-training, model conversion, and deployment of AI models such as Yolo v5/v8/11.
For more information, please visit reCamera Gimbal and User manual.
💡 Here is the introduction of reCamera SG2002 series. So far we launched reCamera SG2002, Click to have one!
| Board | Features | Version |
|---|---|---|
| C1_2002w | - eMMC - WiFi/BLE module - Onboard antenna - External antenna connector |
1.2 |
| C1_2002 | - eMMC - Extra SDIO to base board - Extra UART to base board |
1.2 |
| Top View | Bottom View |
|---|---|
 |
 |
💡 Sensor Driver Support List for Core Board C1 is provided for reference.
| Board | Features | Latest Version |
|---|---|---|
| S1_OV5647 | - 5MP - Rolling Shutter |
1.2 |
| S2_IMX335 | - 5MP - Rolling Shutter |
1.0 |
| S3_SC130GS | - 1MP - Global Shutter |
1.0 |
| Top View | Bottom View |
|---|---|
 |
 |
| Sensor | OV5647 | CMOS Size | 1/4" |
| Pixels | 5MP | Aperture | F2.8 |
| Focal Length | 3.46mm | Field of View | 65° |
| Distortion | <1% | Image | 2592 x 1944(still picture) |
| Video | 1920 x 1080p @30fps, 1280 x 720p @60fps, 640 x 480p @60fps, 640 x 480p @90fps | ||
| Interfaces | - 4 x LED fill lights - 1 x microphone - 1 x speaker - 3 x LED indicator |
||
| Top View | Bottom View |
|---|---|
 |
 |
| Sensor | IMX335 | CMOS Size | 1/2.8 inch |
| Pixels | 5MP | Focusing Mode | manually focusing |
| Focal Length | 3.91mm | Field of View | 106°(D) 92.6°(H) 48.6°(V) |
| Image | 2592 x 1944 still picture resolution | ||
| Video | 2592 × 1944p @20fps;1920 × 1080p @30fps;1280 × 720p @30fps | ||
| Top View | Bottom View |
|---|---|
 |
 |
| Sensor | SC130GS | CMOS Size | 1/2.7 inch |
| Pixels | 1.3MP | Output Format | RAW MONO/RGB |
| Package | 64 pin CLCC | Package Size | 13mm x 13mm |
| Image | 1280H x 1024 | ||
| Video | 1280H x 1024 @240fps | ||
| Board | Features | Version |
|---|---|---|
| B101_Default | - Single Port Transformer Module - SD card reader - Type-C port - UART |
1.2 |
| B201_Vertical-mounted Type-C | - Single Port Transformer Module - SD card reader - Type-C port - UART |
0.1 |
| B301_POE | - Power over Ethernet(POE) - UART |
0.1 |
| B401_CAN | - DC-DC converter - CAN port - UART |
0.1 |
| Top View | Bottom View |
|---|---|
 |
 |
- 1 x Type-C port for power input and communication.
- 1 x Single Port Transformer Module for Ethernet communication support.
- 1 x SD card reader for data storage and exchange.
| Top View | Bottom View |
|---|---|
 |
 |
- 1 x Type-C port for power input and communication.
- 1 x Single Port Transformer Module for Ethernet communication support.
- 1 x SD card reader for data storage and exchange.
💡 B3_POE
| Up | Bottom |
|---|---|
 |
 |
- 1 x RJ45 port for 802.3af PSE.
- 1 x UART port.
💡 B4_CAN
| Up | Bottom |
|---|---|
 |
 |
- 1 x CAN port.
- 1 x Gyroscope sensor.
- 1 x UART port.
The reCamera comes with a stable reCamera OS that supports firmware OTA updates. Additionally, Node-RED and Sensecraft AI platform is integrated in the device for easier deployment experience. This integration offers novice developers a modular programming experience based on Node-RED nodes. For advanced developers, the in-depth Linux-based development and python are also there for twist and play. We warmly welcome developers proficient in JavaScript, C/C++, Python, Linux OS, buildroot, as well as geeks, students, and beginners, to engage in further development and explore applications.
The architecture diagram is shown below
Below is a structured guide to its core software components and full-stack development resources.
Repository: OSHW-reCamera-Series
Here, developers can obtain hardware update information, learn about the improvements and new features of hardware components such as the core board, sensor board, and base board, as well as the application updates of the reCamera.
- Hardware Documentation: Specifications, revision history, and design files for core boards, sensor modules, and expansion baseboards.
- Application Templates: Pre-built Node-RED workflows (object detection, data logging, etc.) for rapid hardware validation.
- Community Contributions: Open hardware specifications for developers to submit custom module designs.
Repository: reCamera-OS
Provides detailed operation procedures for building, compiling, and flashing the image, as well as project dependency libraries.
- Custom OS: RISC-V optimized firmware with OTA updates and recovery mode.
- Cross-Platform Development: Ubuntu setup guides and pre-configured Docker images for streamlined compilation.
- Multi-Storage Deployment: Supports eMMC/SD card flashing with Windows/Linux/macOS compatible tools.
Repository: sscma-example-sg200x
This repository provides open-sourced the relevant codes of web and upper-layer application services.
- Model APIs: Standardized interfaces for vision AI models.
- Protocol Specifications: HTTP/MQTT communication guides with Python examples.
- Remote Deployment: OTA application updates via
scpandopkgpackage manager.
Repository: node-red-contrib-nodes
It includes multiple nodes such as node-red-contrib-sscma and node-red-contrib-seeed-canbus, which are respectively used for functions such as AI model deployment and CAN bus integration.
- AI Nodes: Drag-and-drop workflow components for model inference and result processing.
- Hardware Control: Integrated nodes for CAN bus, GPIO, and sensor interactions.
- Seamless Installation: One-click node installation via Node-RED UI or npm.
5. SenseCraft Workspace and SenseCraft AI
- Multi-Application management: Node-Red flow can be stored on SenseCraft Cloud Service. Super easy one click to deploy different application on the device.
- Technical Issues: Submit via repository Issues.
- Developer Community: reCamera Forum
- Email: https://www.seeedstudio.com/contacts
- Discord: https://discord.gg/eWkprNDMU7
Effortlessly transform your gimbal with AI-powered control by connecting this camera module. Gain precise, two-axis movement—up, down, left, right—without any coding to start. Using the intuitive Node-RED platform, you can easily integrate and fine-tune the system, allowing computer vision via YOLO v11 to enhance your gimbal's tracking capabilities. Just set up your preferred model in Node-RED, make a few adjustments, and experience the full potential of computer vision in your gimbal.
We are excited to announce that the reCamera Industrial is working in progress! This version will feature EVS cameras and infrared thermal camera modules, providing enhanced capabilities for industrial applications.
We are also working on compatibility with Neurala, a software that helps manufacturers automate visual quality inspection and control processes with vision AI. This integration will enable reCamera Industrial to offer advanced visual inspection and control features, making it an ideal solution for industrial scenarios.
Stay tuned for the release of reCamera Industrial and experience the power of vision AI in industrial applications.
Enhance your robotic arm’s capabilities with seamless AI integration through this advanced camera module. Featuring flexible interface expansion and the open-source reCamera OS, this module adds powerful computer vision to your robotics setup for precise control and intelligent object recognition. Tailor it to your specific needs, and let the versatile interface handle complex tasks with advanced vision and adaptability.
The reCamera offers a wide range of application demos, demonstrating its versatility and potential in various fields. Here are some of the application demos which we are working in progress:
| Dashboard | Support Devices | Version |
|---|---|---|
| reCamera Dashboard | reCamera 2002(w) 8GB/64GB | V1.0 |
| reCamera Gimbal Dashboard(coming soon) | reCamera Gimbal | V1.0 |
Node-Red dashboard2 Palette supports UI nodes to build a dashboard. With this integrated ability, You can change the Dashboard to any way of interactions at any time in node-red to customize the functionality of this stand-alone device. Preview Link
- When a target is detected, an email containing the detection frame is sent.
- When a target is detected, a sound is played.
- The reCamera can be integrated with Home Assistant, enabling seamless control and automation within a smart home environment.
- Multiple cameras can be used to transmit data.
- Data is automatically deleted after storage.
- Lights are turned on at night for detection purposes.
- When a specific condition is detected, the Arduino executes a corresponding action using MQTT.
- The reCamera can be used for posture detection, enabling applications such as fitness tracking and ergonomic analysis.
- The reCamera can be used for gesture detection, enabling intuitive user interfaces and interaction.
- (Pending camera node modification)
- When a target is detected, the video stream or photos are stored locally using the save node.
These application demos showcase the capabilities of the reCamera and provide a starting point for further development and customization.
If you have suggestions for improvements or bugs in the current system, please file an Issue. It will help us get feedback on the user experience and advancing project iterations.
| Firmware Version | Description | Iterative version |
|---|---|---|
| 0.1.4 | The node-red save node passes a parameter to save the video stream. | 0.1.5 |
| 0.1.4 | Node-red recamera nodes reference enabled camera on and off | WIP.. |
| 0.1.4 | The Node that adds CAN_Send, CAN_Receive, and CAN_Config for Gimbal | 0.1.6 |
| 0.1.4 | Add the Gimbal Dashboard Application | 0.1.6 |
| Board | Board Type | Description | Date |
|---|---|---|---|
| B401_CAN | Base Board | A base plate that provides a CAN communication interface | 2025/02 |
| S201_imx335 | Sensor Board | cmos = 1/2.8 inch sensor module | 2025/04 |
| S301_SC130GS | Sensor Board | A 100W pixel global shutter camera | 2025/04 |
| S401_GENX320 | Sensor Board | 320x320 Pixel EVS (Event-based Vision Sensor) | 2025/04 |
| B201_Vertical Type-C | Base Board | type-c back base plate | 2025/04 |
| B301_POE | Base Board | POE powered baseboard | 2025/04 |
| S_Thermal imaging camera | Sensor Board | Industrial thermal imaging camera | WIP.. |
| B_Thermal imaging screen | Sensor Board | Use with thermal imaging camera | WIP.. |