Edge Face Recognition Project

Supports Multi-Language Switching No Language Barriers — More Versatile for Communication, Learning, and Translation

4K Ultra-Low Power AI Image Processor
Built-in 0.5 TOPS NPU, supporting a rich set of vision algorithms
Leading image effects, enhanced night vision denoising, and support for Blacklight AI-ISP
Supports Super Encoding, High Image Quality, and Low Bit Rate
Product
Excellent audio effects, supporting AI noise reduction, howling suppression, and AI speech recognition
High performance, low memory, and ultra-low power consumption
Supports constant power and quick start

Multilingual Dialogue Support

Mandarin, Cantonese, Japanese, English, French, and more.

Multilingual Dialogue Support

Mandarin, Cantonese, Japanese, English, French, and more.

Customizable Personality Settings

Fiery, Calm and Dignified, Gentle, Shy and Reserved, Humorous, Frank and Innocent, and more.

Customizable Personality Settings

Fiery, Calm and Dignified, Gentle, Shy and Reserved, Humorous, Frank and Innocent, and more.

Image Recognition & Description

Supports image recognition via camera, providing vivid and detailed descriptions of visual content.

Image Recognition & Description

Supports image recognition via camera, providing vivid and detailed descriptions of visual content.

Compatible AI Models

Qwen3, DeepSeekV3, Doubao 1.5, Qwen2.5, and more.

Compatible AI Models

Qwen3, DeepSeekV3, Doubao 1.5, Qwen2.5, and more.

CPU:Single-core Cortex-A7 + MCU

Video Output Interface:Support SPI interface display

CPU:2D Graphics Engine

ISP:8M@20fps

NPU:0.5 TOPS, supporting int8 quantization

Audio Interface and Processing:Integrated Audio codec, 1*24-bit ADC and 24-bit DAC

Storage Interface:Built-in 512Mb ~ 2Gb DDR, eMMC 4.51

Peripheral Interface:USB2.0/ 3xUART/ SPI/ 5xI2C/ 12xPWM/ 2xSDIO3.0/ SARADC

Video Codec:Highest support for 4K H.264/H.265 25fps video encoding

Packaging:OFN88 9*9mm

Video Input Interface:Supports 2-channel 4-lane or 4-channel 2-lane MIPI-CSI interfaces

Software Features

Self-Adaptation Recognition for All Lighting Scenarios

Identification under backlight, night-time supplementary lighting, and Backlight Recognition, Night Fill Light Recognition, and Cloudy Day Recognition, covering all-day lighting conditions

Stable Multi-Person Tracking

Identification under backlight, night-time supplementary lighting, and Continuous multi-target tracking in complex scenarios with high trajectory retention rate

Algorithm Voting for Anti-Misrecognition

Identification under backlight, night-time supplementary lighting, and Multi-frame Fusion Voting Mechanism, Effectively Reducing Misrecognition Rate

Dynamic Real-Time Recognition

Identification under backlight, night-time supplementary lighting, and Supports real-time detection and recognition in motion, with rapid response

Hardware Features

HDR Wide Dynamic Range

100dB wide dynamic range, restores details in strong light/backlit scenes

Infrared Fill Light Enhancement

Supports infrared fill light at night, enabling continuous monitoring in zero-light environments

Ultra-low power consumption operation

Dual modes of constant power/quick start, suitable for long-term unattended deployment

To become a global leader in AloT vision system solution

Co-creating a smarter future across industries through inneovative AloT vision systems