CamThink NeoEyes NE301 is an ultra-low-power Edge AI camera built around the STM32N6 Arm Cortex-M55 MCU with Neural-ART NPU that “offers significantly enhanced features and performance” compared to the company’s earlier ESP32-S3-based NeoEyes NE101.

The camera ships with a 4MP MIPI CSI camera sensor by default, but USB camera sensors are also supported. It also features 64MB PSRAM, 128MB hyperflash, WiFi 6 and Bluetooth 5.4 wireless connectivity, optional support for a 4G LTE module (global or US), audio wafers, USB-C and UART debug, a 16-pin GPIO header, and support for either USB, battery power, or PoE.

CamThink NeoEyes 301 specifications:

• MCU – STMicro STM32N6

• MCU Core – Arm 32-bit Cortex-M55 CPU @ up to 800MHz with Arm Helium and Arm MVE

• GPU – Neo-Chrom 2.5D GPU, Chrom-ART Accelerator (DMA2D)

• NPU – ST Neural-ART accelerator @ 1 GHz, up to 600 GOPS; 3 TOPS/W enabling fanless operation

• BPU – Hardware-accelerated H.264 and JPEG encoders up to 1080p@30fps

• ISP – ISP with demosaicing, AWB

• Memory – 4.2MB SRAM

• Memory – 64MB PSRAM

• Storage

• 128 MB Hyperflash

• MicroSD card slot

• Camera

• MIPI CSI-2 connector fitted with a 4MP OS04C10 camera sensor with 51° (standard), 88° (wide-angle), or 137° (ultra-wide angle) field of view

• 4-pin USB/PIR connector for optional SC200AI camera sensor

• Built-in fill light

• Audio – Audio-IN and Audio-OUT wafers (not sure where on the board)

• Wireless

• WiFi 6 and Bluetooth 5.4

• 12-pin + 16-pin headers for optional Quectel EG912U‑GL (global, excluding North America) or EG915Q‑NA (North America) module with 4G LTE FDD/TDD and GSM support.

• USB – 1x USB-C port (480 Mbps)

• Expansion – 16-pin GPIO connector with 1x UART, 1x RS485, 1x I2C, 1x SPI, 2x GPIO, 5V, 3.3V and GND

• Debugging – USB-C port, 4-pin UART connector

• Misc

• Reset, Boot, and Snapshot/Recording buttons

• Power LED (PWR), Status LED (STS), and Debug LED

• 2-pin wafer for alarm inputs

• Boot / Wake Time – Microsecond boot, Millisecond wake-up

• Power Supply

• 5V via USB-C port

• 2-pin connector for battery on mainboard; 4x AA batteries supported.

• Optional PoE support via add-on

• STM32U073Kx MCU for independent power management

• Power Consumption

• Sleep – 7–8 μA (managed by STM32U0)

• Active power – 170–180 mA

• Dimensions – 77 x 77 x 48 mm

• Temperature Range – -20°C ~ 50°C

• Humidity – 0–95% RH (non-condensing)

• Certifications – CE / FCC / RoHS / SRRC

Target applications include Smart Cities (parking occupancy detection, smart advertising) , Smart Agriculture (crop growth and livestock monitoring), Smart Factory (e.g., safety gear inspection like helmet detection), and more.

The camera acts as a WiFi access point that allows the user to connect to a web interface used to configure the camera, switch between AI models, upload new models, and preview edge inference in real-time. The documentation provides further information, notably the “Model Training and Deployment” lists step-by-step instructions to run Yolov8n. Sadly, there are still many sections and tutorials showing as coming soon, and some parts have yet to be translated into English (still in simplified Chinese). The information is also a bit all over the place right now, and it was not straightforward to come up with the specifications above.

While the STM32N6 is relatively new, it’s not the first Edge AI camera based on the Cortex-M55 microcontroller, and a direct competitor to the NeoEyes NE301 is the OpenMV N6 board featuring a 1MB global shutter camera (up to 5MP sensors supported), MicroPython programming, and extensive documentation. It was launched for $100 in March via a Kickstarter campaign, and backers should get their rewards in December 2025. It’s not a complete product like the NeoEyes NE301, but you can print an enclosure if needed.

The NeoEyes NE301 can be pre-ordered for $159.99 with a choice a standard, wide, or ultra-wide angle cameras. Shipping is also scheduled to start in December 2025. Additional information may be found on the product page.

Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.

Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress. We also use affiliate links in articles to earn commissions if you make a purchase after clicking on those links.

Post navigation