Seeed Studio’s reCamera AI camera is a modular RISC-V smart camera system for edge AI applications based on SOPHGO SG2002 SoC. The camera is made up of three boards: the Core board, the Sensor board, and the Baseboard. The Core board includes hosts the processor, storage, and optional Wi-Fi. The Sensor board consists of image choice of image sensors, and the Baseboard provides various connectivity options including USB Type-C, UART, microSD, and optional PoE port and CAN bus connectivity options.
At the time of writing the company has released the C1_2002w and C1_2002 core boards. The C1_2002w core board includes eMMC storage, Wi-Fi, and BLE modules, and the C1_2002 features extra SDIO and UART connectivity, but not WiFi. Both boards use the SOPHGO SG2002 tri-core processor and can be paired with various camera sensors for applications such as robotics, healthcare, smart home, as well as buildings and industrial automation.
Seeed Studio reCamera AI camera specifications:
- SoC – SOPHGO SG2002
- Main core – 1 GHz 64-bit RISC-V C906 or Arm Cortex-A53 core (selectable)
- Minor core – 700 MHz 64-bit RISC-V C906 core
- Low-power core – 25 to 300 MHz 8051 MCU core with 8KB SRAM
- NPU – 1 TOPS INT8, supports BF16
- Video Encode – 5MP @ 30fps
- Storage
- 8GB eMMC flash
- MicroSD card slot supports up to 2TB of storage
- Core boards C1_2002w/C1_2002 (one or the other)
- C1_2002w
- eMMC
- WIFI/BLE module
- OnBoard antenna and external IPEX antenna connector on-board
- C1_2002 (WIP)
- Extra SDIO to baseboard
- Extra UART to baseboard
- C1_2002w
- Interchangeable sensor boards (one of the other)
- 5MP OmniVision OV5647 camera board with rolling shutter
- Image – 2592 x 1944 still picture resolution
- VIDEO – 1920 x 1080p @30fps, 1280 x 720p @60fps, 640 x 480p @60fps, 640 x 480p @90fps
- 4x LED fill lights
- 1x microphone
- 1x speaker
- 3x LED indicator
- SmartSens 1MP SC130GS Global shutter CMOS image sensor (WIP)
- 5MP Sony IMX335 Sensor with rolling shutter (WIP)
- Image – 2592 x 1944 still picture resolution
- Video – 2592 × 1944p @20fps;1920 × 1080p @30fps;1280 × 720p @30fps
- 5MP OmniVision OV5647 camera board with rolling shutter
- Interchangeable Baseboards (B1_Defaul/B2_Vertical-mounted Type-C/B3_POE/B4_Gyro)
- B1_Default
- USB Type-C port for power input and communication.
- Ssingle port transformer module for Ethernet communication.
- SD card reader for data storage and exchange.
- B2_Vertical-mounted Type-C
- Vertically mounted Type-C port for power input and communication.
- Single port transformer module for Ethernet communication.
- SD card reader for data storage and exchange.
- B3_POE
- RJ45 port for 802.3af PSE.
- UART port.
- B4_Gyro
- CAN Bus port.
- Gyroscope sensor.
- UART port.
- B1_Default
- Networking – 100Mbps Ethernet RJ45 jack with PoE support with B3_POE board
- Misc – 1x Reset Button, 1x Boot Button on the baseboard
- Power Supply – 5V/1A USB Type-C port
- Dimensions – 35 x 35 x 36.5mm
- Temperature Range – 0°C ~ 50°C
Previously we have written about similar camera modules like the Sipeed MaixCAM, the SmartCam T1025, the ArduCam KingKong, and more. Feel free to check those out if you are interested in the topic.
In terms of software, the boards are managed using a Linux buildroot-based operating system which the company is calling reCamera OS, which has a user-friendly web interface. This interface lets you configure the network, view live footage, and even access a command-line shell directly within your web browser. The modular camera boards support popular machine learning frameworks like TensorFlow and PyTorch to access the AI features. More information about the hardware with clearer images of the boards and schematic can be found on their GitHub repository. The reCamera OS and other software are available on a separate repository. Seeed has also announced three related projects with this setup they are calling those the reCamera Gimbal, reCam Industrial, and reCamera Robot Arm.
Seeed Studio has launched the reCamera modular AI camera with two pricing options The non-WiFi/BLE version with 8GB eMMC flash costs around $34.90 and the Wi-Fi/BLE version with 64GB eMMC costs around $54.90 and can be purchased from their store page. At the time of writing, there is also an early bird offer going on where you get a 50% discount on the top-end model by purchasing a $5 coupon from the company store. Those interested in testing the device before its official launch can apply to become alpha testers.
Debashis Das is a technical content writer and embedded engineer with over five years of experience in the industry. With expertise in Embedded C, PCB Design, and SEO optimization, he effectively blends difficult technical topics with clear communication
Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress