Home » Store » AI Camera » NeoEyes NE301 Edge AI Camera

NeoEyes NE301 Edge AI Camera

(1 customer review)

Original price was: $199.90.Current price is: $159.90.

NE301 —— Tiny, ultra-efficient on-device AI camera that runs YOLO directly, wakes instantly, and powers real-world vision AI anywhere — modular, battery-powered, and fully open.

Read More

NE101 camera installed on base bracket
Mounting Brackets for NeoEyes Series
$8.91$40.50
ST-Link V2 Emulator for STM32/STM8 | Compatible with NE301
Original price was: $9.90.Current price is: $8.91.
Front view of CamThink NE101 AI Camera with black glass lens cover and compact housing
NeoEyes NE101 Modular Sensing Camera
$55.20$89.60
NeoEyes NE101 Dev Kit - Modular Vision Camera
Original price was: $59.90.Current price is: $47.92.
SKU: N/A Category:

Standard Wi-Fi Version First Release

No embedded experience needed / Web UI / Few clicks to deploy model

Overview

NeoEyes NE301 is a compact Edge Vision AI Camera built on STMicroelectronics STM32N6 MCU with an integrated NPU.

Delivering 0.6 TOPS compute with only 3 TOPS/W ultra efficiency, it performs on-device image inference such as object recognition, motion detection, and human pose estimation — all without relying on the cloud.

Its open firmware, rich I/O, and modular architecture make NE301 ideal for developers, makers, and researchers building custom vision-AI systems for IoT, robotics, and smart automation.

Key Features

Accelerated AI Vision

  • 800 MHz Cortex-M55 core with integrated NPU
  • 0.6 TOPS on-device inference for realtime vision tasks
  • Runs YOLOv8 models at 25 FPS
  • Builtin ISP, H.264, and JPEG encoder for efficient video streaming

Advanced Power Design

  • μs startup and ms response for instant triggering
  • Integrated STM32U073Kx power controller for ultra-low standby consumption
  • Intelligent sleep / standby / high-performance powermode switching
  • Supports MQTT / RTC / Bluetooth wake-up for flexible remote control

Open & Developer-Friendly

  • Open-source firmware and SDK for full customization
  • Supports STM32 Cube.AI, YOLOv8n, MobileNet, EfficientNet, ResNet, and more
  • Web-UI for model deployment, parameter tuning, and OTA firmware updates
  • Compatible with HTTP / HTTPS / MQTT / MQTTS communication protocols

Modular & Scalable

  • Supports MIPI CSI and USB camera inputs
  • I/O interfaces include RS-485, I²C, GPIO, UATR and audio interface
  • Expandable with PoE, Cat.1, and external sensor modules (PIR, radar, etc.)
  • SD Card storage for local data AI logging and analysis

Outdoor-Ready Design

  • IP67 housing with -20 °C to 50 °C operating range
  • supports 4× AA battery, USBC, or PoE power supply
  • Multiple mounting brackets for flexible deployment (sold separately)

Built for Developers

  • Train & Deploy AI Models

           Run YOLO, MobileNet, or EfficientNet directly on STM32N6 with real-time feedback.

  • Prototype Faster

          Test logic via Web UI or MQTT, validate AI behavior instantly.

  • Expand Freely

          Add communication boards, sensors, or custom modules through open I/O ports.

  • Scale Anywhere

          From lab projects to outdoor automation, NE301’s IP67 build and modular hardware adapt to any scenario.

Specification

Processor STM32N6 (Cortex-M55 + NPU 0.6 TOPS) + STM32U073Kx
Memory 4.2 MB SRAM + 64 MB PSRAM + 128 MB HyperFlash
AI Performance 600 GOPS
NPU Efficiency 3 TOPS / W
Camera Input MIPI CSI / USB
Connectivity Wi-Fi 6 / BLE 5.4
Storage SD Card (Excluded)
Operating Temp -20 °C ~ +50 °C
Protection IP67
Power Supply 4×AA battery / PoE / DC input
Dimensions 77 × 77 × 48 mm

Detail Datasheet 🔗

What’s in the Box?

  • 1× NeoEyes NE301 Camera

1 review for NeoEyes NE301 Edge AI Camera

  1. Dave

    Most so-called “AI cameras” on the market today are still constrained by a fundamental architectural flaw: they are essentially high-end IP cameras that offload the heavy computational work to distant cloud servers via a simple API. This design inevitably introduces operational bottlenecks — unacceptable latency for real-time applications, excessive bandwidth consumption, and, most critically, serious security concerns. Even the smallest processing tasks require uploading raw and sensitive video streams to an external server.

    The strength of this product lies in its ability to run all AI inference, image capture, and processing tasks entirely on-device. This local-first approach significantly enhances personal privacy and data security. What impressed me most, however, is the level of effort put into the documentation. The guides are complete and easy to follow, making it straightforward to get started.

    I plan to dig into the source code and explore possibilities for secondary development; training my own AI models also seems like an exciting direction. And by the way — they even provide references for model training, which is genuinely helpful.

Add a review

Your email address will not be published. Required fields are marked *

You may also like…

Welcome Offer