Product Information

Overview

NeoEyes NE503 is an edge AI smart camera based on the Hailo-15H SoC, featuring a 20 TOPS NPU and a Sony IMX678 4K imaging system. NE503 completes the full closed loop from image capture and AI inference to event output and business linkage within a single device, significantly reducing the deployment complexity of edge intelligence solutions. It combines the professional imaging capabilities of an AI Camera with the open edge computing platform attributes—supporting containerized application deployment, multi-model concurrent inference, and RTSP / Event Bus protocol integration for visual application and edge AI secondary development scenarios.

Core Capabilities

• On-Device AI Inference Loop: 20 TOPS (INT8) NPU supports multi-model concurrent inference. Image capture, analysis, and structured output run entirely on-device with zero cloud dependency, meeting low-latency and data localization requirements.

• 4K Professional Imaging System: Sony IMX678 (1/1.8") + Gen2 AI-ISP + motorized zoom lens (F1.6), supporting 4K@30fps H.265 encoding and <0.01 LUX full-color night vision. Maintains image quality under HDR, low-light, and concurrent inference workloads, balancing wide-angle coverage and long-range recognition.

• Containerized Application Platform: Built on containerd runtime with OCI image deployment and sandbox isolation. Models and applications can be independently deployed and upgraded. Algorithm vendors, integrators, and OEMs build industry solutions on a unified platform, avoiding vendor lock-in.

• Industrial-Grade All-in-One Delivery: Imaging, inference, alarm linkage, protocol output, and operations management integrated in a single device. IP66 protection + PoE 802.3AT power + Web console, supporting the full lifecycle from development validation to commercial deployment.

• Full-Stack Developer Toolchain: Python / C++ / Go SDKs + aipc-cli + RESTful APIs for diverse integration approaches. Modular HAL decouples software from hardware, enabling smooth cross-SoC platform migration.

Product Specifications

NE503 core specifications are as follows:

Category	Item	Specification
Core Platform	SoC	Hailo-15H
	CPU	Cortex-A53 × 4 @ 1.3 GHz
	NPU	Hailo NPU, 20 TOPS @ INT8, supports 4-bit quantization extension
	Memory / Storage	8 GB LPDDR4 / 64 GB eMMC, supports TF Card and M.2 SSD expansion
	Video Encoding	H.264 / H.265 hardware encoding, 4K@30fps
	System Power	< 8W (typical load)
Imaging System	Image Sensor	Sony IMX678, 1/1.8" CMOS, 4K UHD
	Lens Module	Foctek AF0832D09, motorized zoom 10.2–29.5mm, F1.6–F1.7
	ISP	Gen2 AI-ISP, <0.01 LUX full-color night vision
Network & Protocols	Ethernet	100M LAN, supports PoE 802.3AT
	Video Protocol	RTSP / ONVIF (planned)
	Data Protocol	MQTT / Event Bus / RTMP (planned)
Deployment Environment	Power Supply	DC 12V or PoE 802.3AT
	Protection Rating	IP66
	Operating Temperature	-30°C to +60°C
External Interfaces	Alarm IO	Alarm IN × 2 + Alarm OUT × 2 (relay + level)
	Expansion Interfaces	RS-485 / Wiegand* / Audio I/O* / Radar* / Fill Light
Software Platform	Operating System	Embedded Linux (Yocto build), containerd container runtime
	Management	Web console + SSH + REST API + aipc-cli

* Planned feature, availability subject to future firmware updates.

Performance & Edge AI

AI Inference Capability

NE503 is powered by the Hailo-15H SoC with an integrated Hailo NPU delivering 20 TOPS (INT8) compute, complemented by a 350 GOPS DSP for pre-processing and post-processing tasks. The Zero-copy Pipeline achieves zero-copy data transfer via DMA/SHM direct transmission, avoiding memory copy overhead. AI Runtime manages model loading, inference scheduling, and multi-model parallel execution. Inference results are output as structured events via Event Bus, supporting both local hardware linkage and cloud integration.

Metric	Parameter
Inference Latency Target	< 50ms
Concurrent Inference	Supports multi-model simultaneous execution
Data Transfer	Zero-copy Pipeline (DMA/SHM direct)
Supported Tasks	Detection / OCR / Face Detection & Recognition / ReID / Pose Estimation / Behavior Analysis / Attribute Recognition, etc.
Pre-installed Models	Person Detection (YOLOv8n), Face Landmarks, CLIP Image Encoder
Event Output	Structured inference results + event messages + device status data

Video Encoding

The hardware encoder supports dual-format H.264/H.265 encoding at 4K@30fps, paired with Gen2 AI-ISP for <0.01 LUX ultra-low-light full-color night vision. The 12-bit AI denoising adapts to different scenes without retraining models.

Metric	Parameter
Encoding Format	H.264 / H.265 hardware encoding, supports CBR / VBR rate control
RTSP Streams	Main stream / Sub stream / Third stream
AI Denoising	12-bit AI denoising, adapts to different scenes without model retraining

Low-Light Imaging

AI-ISP delivers clear color images even in extremely low-light environments, with 12-bit AI denoising that adapts to varying illumination conditions. Combined with automatic IR-CUT filter switching and fill light control, it achieves 24/7 all-weather imaging.

Imaging System

The NE503 imaging system consists of a Sony IMX678 image sensor and a Foctek AF0832D09 motorized zoom lens. The 1/1.8" sensor matches the 1/1.8" lens target surface, balancing edge image quality with optical coverage for smart security, campus management, and long-range recognition scenarios.

Sensor

Parameter	Specification
Sensor Model	Sony IMX678-AAQR1-C
Target Surface	1/1.8 inch, diagonal 8.86mm
Effective Pixels	3856(H) × 2180(V), recommended recording pixels 3840 × 2160 (4K UHD)
Pixel Size	2.0μm × 2.0μm
Output Interface	MIPI CSI-2, RAW10 / RAW12
HDR	Digital Overlap HDR / Dual Gain HDR

Lens

Parameter	Specification
Lens Model	Foctek AF0832D09.ICR1(4K)
Focal Length	10.2mm (wide) – 29.5mm (telephoto)
Relative Aperture	F1.6 (W) – F1.7 (T)
Field of View	Horizontal 44.5° (W) / 14.5° (T); Diagonal 52° (W) / 16.6° (T)
Electromechanical	Zoom / Focus stepper motors, DC-Iris auto aperture, IR-Cut electromagnetic switching

• F1.6 large aperture combined with HDR and low-light capability improves imaging stability in dark and backlit scenes.
• Motorized zoom supports dual-mode deployment: "panoramic observation + remote target lock."
• Lens TV distortion: approximately -9.1% at wide end, 1.8% at telephoto end.

Lens Drive & Image Stabilization

NE503 uses the AN41908A driver IC, supporting MFZ (Manual Focus Zoom) / AF (Auto Focus) compatible lenses with an optical zoom range of 1x – 2.88x. Control modes support SoC SPI (default) or MCU SPI dual-version options. Independent MCU control ensures reliable lens homing and limit protection.

The onboard gyroscope LSM6DSR (I2C2) supports EIS electronic image stabilization. Combined with motorized zoom and auto focus, it maintains image stability even at the telephoto end.

Hardware Architecture

NE503 features a dual-board structure with a Processor Board and an AI-PC Interface Board, interconnected via board-to-board connectors. The Processor Board carries the SoC, NPU, memory, and imaging subsystem, handling all computing and AI inference tasks. The AI-PC Interface Board integrates an independent MCU, external IO, and power management circuitry. Even if the Processor Board fails, underlying functions such as lens homing, fill light control, and IO protection continue to operate normally.

Processor Board

The Processor Board integrates the SoC, NPU, memory, storage, video encoding, and camera interface, handling all computing and AI inference tasks:

Item	Specification
SoC	Hailo-15H, Cortex-A53 × 4 @ 1.3 GHz
NPU	Hailo NPU, 20 TOPS @ INT8, supports 4-bit quantization extension
DSP	256 MACs @ 700 MHz, 350 GOPS
Memory	8 GB LPDDR4
Storage	64 GB eMMC
Video Encoding	H.264 / H.265 hardware encoding, 4K@30fps
SPI Flash	8 MB (QSPI 4-bit)
TF Card	SDIO0, supports High Speed / UHS-I (J11 TF card slot + J12 FPC connector)
SSD Expansion	M.2 KEY M (PCIe 3.0, 2 Lanes)
Camera Interface	J3 FPC connector, MIPI CSI-2 (4 Lanes), I2C0 + GPIO
Onboard Devices	Gyroscope (LSM6DSR, I2C2)
Debug	SoC Debug UART1 (1.8V)

AI-PC Interface Board

The interface board manages all peripherals and communication interfaces through an independent MCU (Cortex-M4 × 2 @ 200 MHz), communicating with the Processor Board via UART0, and integrates the system power input and distribution circuitry.

External Interfaces

Item	Specification
Alarm IN × 2	J1/J2, MCU PB13/PB14, High/Open = 0, Low/Short = 1
Alarm OUT × 2	J2, Relay output (MCU PB15) + Level output (MCU PA8)
RS-485	J2 (ITS version), MCU UART3 (PC4/PC5), Enable PB1
Wiegand*	J1 (ITS version), Data0/Data1, MCU PC6/PC7
Audio*	Line-In / Line-Out, J1, NAU88C10 codec
Ethernet	100M LAN, supports PoE 802.3AT power supply
Fill Light	Standard: IR dual-channel PWM (J5); Enhanced: White + IR PWM (J6)
IR-CUT	J7, H-EN / L-OFF, MCU PB8, supports auto / day / night three modes
Light Sensor	J8, Photoresistor ADC sampling, MCU PA1
Radar Interface*	J4 (ITS radar version), 5V/12V selectable power + UART direct to Processor Board (SoC GPIO4/GPIO6)

* Planned feature, availability subject to future firmware updates.

MCU Management

Item	Specification
MCU	Cortex-M4 × 2 @ 200 MHz, communicates with Processor Board via UART0
Management Scope	Motorized lens, fill light, IR-CUT, heater, fan, Alarm IO, Wiegand*, RS-485, light sensor
EEPROM	AT24C02D (I2C1), stores configuration data
Temperature Sensors	TMP1075DSGR (I2C1, Processor Board) + LMT87DCK (Interface Board, MCU PB2 ADC)
Thermal Control	12V fan driver (MCU PB9, reserved) + 12V heater driver (MCU PA15, reserved)
RTC	MCU VBAT with external supercapacitor, MCU maintains RTC and syncs to Processor Board
Status LEDs	System status LED (blue, GPIO24) + Network status LED (green, PHY) + SYS-LED (MCU PD9)
Debug	MCU ST-LINK (J13) / UART (J14)

Power Supply

Item	Specification
Power Supply	DC 12V adapter or PoE 802.3AT (single-cable)
System Power	< 8W (typical load)

Software Architecture

NeoEyes NE503 adopts a four-layer architecture with clear separation from underlying hardware to the web management interface:

Layer	Components	Description
Web Management Console	React 19 + TypeScript + Vite	Dashboard, media settings, application management, system management
Platform Services (Go)	platform-api · app-manager · device-control · ai-runtime · event-bus	REST API gateway, container lifecycle, hardware control, AI inference, event bus
HAL & C++ Services	camera-daemon · libaipc_hal.so	Video capture and encoding, hardware abstraction layer
Hardware Layer	Hailo-15H SoC · Hailo NPU · MCU	AI acceleration, video processing, peripheral control

Applications

With 20 TOPS local computing power, containerized microservice architecture, and rich peripheral interfaces, NeoEyes NE503 transforms traditional IPCs into all-in-one edge computing devices for high-end smart security and AIoT scenarios that demand high image quality, computing power, and customization.

Smart Security

NE503 supports 24/7 all-weather complex security tasks. AI-ISP delivers clear color images in extremely low-light conditions, while multi-model concurrent inference enables person detection, license plate recognition, and perimeter intrusion detection. The event bus links hardware alarms (fill light, focus, Alarm output) and supports GenAI natural language retrieval of non-predefined targets.

Application Examples

Smart Perimeter Protection

Multi-model concurrent execution of person detection and CLIP visual encoder, supporting natural language target retrieval (e.g., 'person wearing a red jacket'), with automatic fill light, focus, and alarm linkage upon match.

License Plate Recognition

Containerized deployment of license plate recognition models for real-time video stream analysis. Recognition results are pushed to business systems via the event bus, suitable for parking lots, campus entrances, and similar scenarios.

Privacy-Compliant Monitoring

Dynamic Privacy Mask automatically pixelates irrelevant pedestrian faces for desensitization, meeting GDPR and other privacy compliance requirements before forwarding to the monitoring center.

Smart Industry

NE503's independent MCU peripheral control ensures industrial-grade reliability—even if containers crash, underlying hardware power-off and limit protection remain active. Rich IO interfaces support connecting various industrial sensors and actuators.

Application Examples

Safety Equipment Detection

Real-time detection of whether workers are wearing hard hats, protective clothing, reflective vests, etc. Violations immediately trigger Alarm output warning signals.

Production Line Quality Inspection

Containerized deployment of custom inspection models for real-time analysis of product appearance on production lines, supporting multi-angle zoom and focus for inspection, with automatic defect marking.

AIoT & Custom Applications

NE503's containerized microservice architecture and modular HAL design significantly lower the hardware deployment barrier for third-party algorithm companies. Based on the containerd runtime, custom AI applications can be deployed via standard OCI images, breaking hardware vendor lock-in.

Application Examples

VMS Integration

Run professional video management systems like NX Witness in containers. NE503 simultaneously serves as both a smart IPC and NVR, reducing system complexity and cost.

Natural Language Video Search

Deploy CLIP / VLM and other vision-language models to support free-text video content search, enabling 'non-predefined target retrieval' such as identifying persons carrying specific items.

Multi-Sensor Fusion

Connect external sensors via RS-485, Alarm IO, radar interfaces, and other channels. Combined with edge AI inference, achieve multi-dimensional environmental perception and linkage control.

Edge AI Box

In projects with existing standard IPC deployments, NE503 can pull RTSP streams from surrounding non-AI IPCs for centralized proxy inference, acting as an 'AI Box inside a camera' to upgrade legacy projects with minimal retrofit cost.

Application Examples

Legacy IPC AI Upgrade

NE503 simultaneously pulls multiple RTSP streams, centrally runs person detection, zone intrusion, and other AI models, pushing inference results to business systems—upgrading to smart surveillance without replacing existing cameras.

Resources

Developer Resources

• Python / C++ / Go SDK (MediaClient, InferenceClient, DeviceClient)
• aipc-cli command-line management tool
• RESTful API (Bearer Token authentication)
• Hailo Dataflow Compiler model compilation tool

Support

Join Developer Community

Chat with developers about technical issues Get the latest product updates and tutorials

GitHub Repository

Submit issues to report problems View source code and contribute