EDGE Computer Series

Edge AI Vision Computer Series
AI-Powered Edge Image Processing and Video Analysis Platforms

ABOUT THE SERIES

The IBBVision Edge AI Vision Computer Series is a family of Edge Vision computers designed for the local ingestion and processing of IP camera footage and the on-site execution of IBBVision artificial intelligence applications. Employing an edge computing approach—where image processing and AI applications are performed directly near the data source—these systems eliminate the bandwidth, latency, and data privacy issues inherent in traditional centralized or cloud-based solutions.

This series comprises models capable of real-time video ingestion ranging from 4 to 64 channels, addressing image processing needs of various scales. Each model offers a scalable structure tailored to the size and requirements of the organization.

Models in the Series:

• EVS 04 – 4 Channels

• EVS 08 – 8 Channels

• EVS 16 – 16 Channels

• EVS 24 – 24 Channels

• EVS 32 – 32 Channels

• EVS 40 – 40 Channels

• EVS 48 – 48 Channels

• EVS 56 – 56 Channels

• EVS 64 – 64 Channels

Purpose of Use: To provide compact, cost-effective, enterprise-grade edge computing infrastructure for image processing needs of all scales—from small businesses to corporate facilities, branch offices to large campuses, stores to production sites, warehouses to shopping malls, apartment entrances to critical infrastructure—enabling the secure and efficient deployment of IBBVision AI solutions in the field.

Remember: The IBBVision Edge AI Vision Computer Series is not just a passive device for transmitting video. Delivered with IBBVision Core software, these systems are intelligent edge computing platforms on which IBBVision Deep Learning Surveillance software and IBBVision-developed custom AI Image Analysis Solutions are run. The systems ingest video streams from cameras, manage them through IBBVision Core, and provide the necessary infrastructure for licensed AI solutions to operate locally. All these operations are performed securely on-site, without sensitive video data leaving the facility.

Traditional centralized or cloud-based systems require all video streams to be transmitted to a central server. This introduces critical vulnerabilities such as high bandwidth requirements, system failures during connectivity loss, high latency, and the exposure of sensitive video data outside the facility. The Edge AI Vision Computer Series is designed to eliminate these problems.

SYSTEM ARCHITECTURE

The Edge AI Vision Computer Series consists of integrated layers, each performing a specific function. This layered architecture guarantees system reliability, efficiency, and scalability.

A. Hardware Layer

The platform is built on a high-performance Edge processor and NPU architecture.

• Camera Capacity: Support for 4 to 64 IP cameras, depending on the model.

• Protocol: RTSP/ONVIF compatibility, independent of camera brand.

• Video Display: Uninterrupted video display for up to 4 to 64 channels, depending on the model.

• Operating Temperature: Industrial design, -30°C to +70°C.

• Cooling: Fanless passive cooling.

• Connectivity: Gigabit Ethernet, PoE++, WiFi/4G/5G options.

• Mounting: 19" rack, wall, desktop.

• Storage: Internal + external storage support (for video and metadata storage).

B. IBBVision Core Software Layer (Included)

This is the foundational software layer delivered with the system.

• Video Ingestion: Real-time video ingestion for up to 4 to 64 cameras, depending on the model.

• Live Monitoring: Uninterrupted video display.

• Video Management: Operation of the core video infrastructure.

• AI Infrastructure: Provides the underlying layer required for IBBVision Deep Learning Surveillance and AI Image Analysis Solutions to operate.

• Note: Core software does not include any AI analysis capabilities.

C. IBBVision AI Layer (Purchased Separately)

This layer constitutes the system's artificial intelligence capabilities and is delivered through a modular software architecture.

• Deep Learning Surveillance: The licensed software infrastructure containing AI models developed by IBBVision. This layer provides the necessary framework for running AI analysis applications.

• AI Image Analysis Solutions: Person- or organization-specific AI image analysis solutions. Analyses such as object detection, facial recognition, license plate recognition, behavior analysis, zone intrusion, fall detection, and fire and smoke detection can be incorporated into the system through the licensing of the relevant IBBVision AI solutions.

• Note: All AI solutions are developed exclusively by IBBVision. Third-party software is not supported.

HOW IT WORKS

The working principle of the Edge AI Vision Computer Series is built upon a continuous and automated data flow cycle:

1. Video Ingestion: Video streams are received from IP cameras via RTSP/ONVIF protocols. Each channel is processed independently.

2. Core Software – Video Management: IBBVision Core software manages camera connections, receives live feeds, and operates the system's underlying video infrastructure. Video is displayed in real time. (No AI analysis is performed at this stage.)

3. Deep Learning Surveillance (When Purchased): The infrastructure layer required for running AI models is activated. This layer enables licensed AI analysis applications to run on the EVS.

4. AI Image Analysis Solutions (When Purchased): Real-time analysis is performed using the purchased models (object detection, facial recognition, license plate recognition, behavior analysis, etc.). Independent analysis engines running on each camera are activated.

5. Alarm Generation: Detected anomalies are compared against predefined rules and Regions of Interest (ROI). When thresholds are exceeded, alarms are generated and a prioritized alarm flow is created.

6. Notification and Intervention: Detected events are instantly communicated to the operator. Alarms can be delivered via visual marking, instant operator notification, and webhook integration with third-party systems.

7. Metadata Generation and Storage: Object feature vectors, timestamps, and event logs produced during analysis are securely stored alongside video. Analysis results, event information, and required metadata can be stored locally or transmitted to authorized central systems.

All these processes run 24/7 without requiring operator intervention and independently of an internet connection.

KEY FEATURES AND CAPABILITIES

Channel Capacity and Optimized Processing Architecture

The platform processes video streams from 4 to 64 IP cameras, depending on the model.

• Independent Video Queues: Independent video stream management for each camera.

• Dynamic Resource Allocation: Processing resources are allocated per camera.

• Adaptive Frame Processing: Frame processing frequency is balanced based on scene density.

• Low Latency: Lag-free, uninterrupted video streaming and analysis.

• Timely Alarms: Alarm generation without delay.

• Video Continuity: Video ingestion continues uninterrupted, regardless of analysis load.

• Modular Expansion: Gradual and cost-effective scaling from 4 to 64 channels.

IBBVision Core – Core Video Management Platform

• Video Ingestion: Real-time video ingestion for up to 4 to 64 cameras via RTSP/ONVIF, depending on the model.

• Live Monitoring: Uninterrupted video display.

• Video Management: Operation of the core video infrastructure.

• AI Infrastructure: Underlying layer for IBBVision Deep Learning Surveillance and AI solutions to operate.

• Note: Core software does not include any AI analysis capabilities.

IBBVision AI Software Architecture (Licensed Separately)

The AI capabilities of Edge AI Vision Computers are built upon a modular software architecture:

• Deep Learning Surveillance: The software layer developed by IBBVision for running AI-powered video analysis applications. This layer provides the infrastructure required for licensed AI analysis applications to run on the EVS.

• AI Image Analysis Solutions: Comprising applications and models that address specific analysis needs. Different analysis functions can be added to the system based on user requirements.

Real-Time AI-Based Video Analysis (When Licensed)

Independent analysis engines running on each camera provide the following capabilities:

• Object Detection: Detection of people, vehicles, and other objects.

• Multi-Target Tracking: Simultaneous tracking of multiple objects.

• Person-Based Tracking: Tracking specific individuals within the camera's field of view.

• Zone Intrusion Detection: Detection of unauthorized entry/exit.

• Density Analysis: Measurement of people/vehicle density in specific areas.

• Motion Analysis: Detection of abnormal or unexpected movement patterns.

• Face Recognition and Verification: Face detection and recognition (optional).

• License Plate Recognition (ANPR/LPR): Detection and reading of vehicle license plates (optional).

• Vehicle-Pedestrian Differentiation: Detailed traffic flow analysis.

• Behavior Analysis: Detection of anomalies, fights, falls, running, and other behaviors.

• Fire and Smoke Detection: Early detection of fire and smoke indications (optional).

Local Processing and Data Privacy

The edge architecture of the Edge AI Vision Computer Series enables local processing of video data:

• Data Security: Sensitive video data does not leave the facility.

• Privacy-Focused: Camera footage is not continuously sent to an external cloud platform.

• Corporate Data Policies: Operates in compliance with security, operational privacy, and corporate data policies.

• Local Control: Control of on-site video data remains with the organization.

• Independent Operation: Uninterrupted operation even without an internet connection.

Multi-Layered Security and Behavior Analysis (When Licensed)

The platform supports a wide range of security-focused analysis scenarios:

• Suspicious Object Detection: Detection of abandoned or suspicious objects.

• Abnormal Movement Detection: Detection of unusual running, fleeing, or directional changes.

• Unauthorized Area Access: Detection of entry/exit to restricted zones.

• PPE Compliance Check: Monitoring of safety equipment usage (helmets, vests, etc.) (optional).

• Wrong Direction Movement: Detection of objects moving in the wrong direction in one-way areas.

• Vehicle-Pedestrian Differentiation: Separate analysis of vehicle and pedestrian traffic.

• Density Analysis: Instant and periodic density measurements in specific areas.

• Risky Movement Detection: Detection of falls, fights, sudden movements, and other risky situations.

ROI (Region of Interest)-Based Prioritization (When Licensed)

• Region of Interest Definition: Critical and non-critical areas can be defined for each camera.

• Resource Optimization: Analysis density is increased at critical points, while processing load is reduced in less important areas.

• False Alarm Rate Reduction: Movements in non-critical areas do not trigger alarms.

• Sensitivity Settings: Different sensitivity levels can be defined per region.

Alarm and Event Management Layer (When Licensed)

Alarms generated by the system are supported by the following capabilities:

• Visual Marking: Visual marking of the moment the event occurred.

• Instant Operator Notification: Sending notifications to operators at the moment of an event.

• Audible Alerts: Sound alarms for critical events (optional).

• Event Logging: Recording of all alarms and associated metadata.

• Quick Rewind: Direct access to the moment of the alarm.

• Task Assignment: Distribution of alarms among operators (optional).

Storage and Data Management

• Video Storage: Continuous recording for all channels.

• Metadata Storage: Object feature vectors, timestamps, event logs.

• Flexible Storage: Internal + external storage support.

• Fast Access: Target querying in seconds via feature vectors.

• Data Security: Encryption and backup mechanisms.

Reporting and Analytics Dashboard (When Licensed)

The platform produces measurable data that supports decision-making:

• Camera-Based Analysis Densities: Analysis intensity for each camera.

• Alarm Distributions: Time-, zone-, and camera-based alarm analyses.

• Model Performance Metrics: Accuracy and performance measurements of AI models.

• Risk Density Maps: Visualization of risk distribution across the facility.

• Operational Planning: Use of generated data in business decisions.

TECHNICAL ARCHITECTURE AND PROCESSING PIPELINE

The system architecture is built upon the following components:

INTEGRATION AND SYSTEM COMPATIBILITY

The Edge AI Vision Computer Series offers the following integration capabilities:

• Camera Independence: Compatibility with all IP camera brands that support RTSP and ONVIF protocols.

• IBBVision Ecosystem: Optimized to work exclusively with Deep Learning Surveillance software and AI Image Analysis Solutions developed by IBBVision.

• VMS Integration: Integration with third-party Video Management Systems via REST-based service outputs and webhook support.

• CMS Integration: Integration with third-party Central Management Systems via REST-based service outputs and webhook support.

• REST Service Outputs: Exposure of system data via REST-based service outputs.

• Webhook Support: Webhook-enabled alarm integrations.

• Standard Protocol Support: Compliance with industry standards.

KEY USE CASES

The Edge AI Vision Computer Series enables the on-site deployment of IBBVision AI solutions in the following areas:

Small and Medium-Scale Solutions (EVS 04–24)

• Small and Medium-Sized Businesses: Cost-effective, enterprise-grade AI infrastructure.

• Retail Stores and Boutiques: AI solutions for customer behavior analysis, theft prevention.

• Branch Offices and Bank Branches: Personnel and visitor safety, unauthorized area supervision.

• Warehouses and Logistics Units: Personnel and vehicle tracking, occupational safety inspection.

• Residential and Apartment Entrances: Access control, suspicious person detection.

• Schools and Educational Institutions: Student and visitor safety, unauthorized area access control.

• Showrooms and Exhibition Areas: Visitor density analysis, valuable product security.

• Parking Entry/Exit Points: Vehicle tracking, license plate recognition (optional).

• Restaurants and Cafés: Customer density, security, personnel movements.

• Hotels: Customer experience analysis, security, personnel tracking.

Corporate and Large-Scale Solutions (EVS 32–64)

• Corporate Campuses and Large Facilities: Comprehensive security and operational analysis.

• Municipalities and Public Areas: City security, traffic analysis, crowd management.

• Multi-Entrance Buildings and Shopping Malls: Visitor management, security optimization.

• Production and Quality Control Lines: Occupational safety, production process monitoring.

• Energy Sites and Critical Infrastructure Areas: Hazardous area supervision, security monitoring.

• Airports and Ports: Terminal security, vehicle and pedestrian traffic management.

• Sports Facilities and Concert Venues: Crowd density, security risk detection.

• Hospitals and Healthcare Campuses: Personnel and patient monitoring, security supervision.

TECHNICAL SPECIFICATIONS

LICENSING INFORMATION

MODEL COMPARISON

FREQUENTLY ASKED QUESTIONS

Q1: What is the Edge AI Vision Computer Series?

A: The Edge AI Vision Computer Series is a family of Edge Vision computers developed by IBBVision, designed for the local ingestion and processing of IP camera footage and the on-site execution of IBBVision artificial intelligence applications. The series offers models with varying capacities from 4 to 64 channels.

Q2: Does the Edge AI Vision Computer come with AI analysis ready out of the box?

A: No. The EVS hardware is delivered with IBBVision Core software. AI analysis functions are licensed separately through Deep Learning Surveillance and the relevant AI Image Analysis Solutions. Core software does not include any AI analysis capabilities.

Q3: What software does the Edge AI Vision Computer run?

A: The EVS is designed exclusively to run Deep Learning Surveillance software and AI Image Analysis Solutions developed by IBBVision. Third-party software is not supported.

Q4: Which camera brands does it support?

A: The Edge AI Vision Computer Series supports all IP cameras that can stream video via RTSP and ONVIF protocols. It operates independently of camera brand.

Q5: Which model should I choose?

A: The choice depends on the size of your organization and the current or planned number of cameras. For a 4-camera system, EVS 04 is sufficient, while EVS 64 is suitable for a 64-camera corporate facility. Selecting the nearest higher model above your current camera count also provides an advantage for future expansion needs.

Q6: Is the Edge AI Vision Computer an NVR?

A: The Edge AI Vision Computer is not positioned solely as a traditional NVR. In addition to video ingestion and management functions, the product is an Edge Vision computer platform capable of running IBBVision AI software. Video recording functionality is provided through the system's storage infrastructure.

Q7: Does it work without an internet connection?

A: Yes. The system's core local functions and licensed AI analyses running on the device can operate without requiring a continuous internet connection. Features such as central management and remote access may require network connectivity.

Q8: Which AI analyses can be used with the Edge AI Vision Computer?

A: The available analyses depend on the licensed solution package and system configuration. Different analysis scenarios such as object detection, facial recognition, license plate recognition, zone intrusion, behavior analysis, fall detection, and fire and smoke detection can be implemented.

Q9: Can AI models be purchased separately?

A: Yes. Different IBBVision AI analysis solutions can be licensed independently of the EVS hardware. The AI functions to be used are determined according to the customer's needs. Deep Learning Surveillance provides the core software infrastructure required for AI analysis.

Q10: Can the capacity be increased later?

A: Edge AI Vision Computer models have fixed hardware capacities. If higher camera capacity is needed, it is necessary to upgrade to a higher model with the appropriate capacity.

Q11: Can third-party software be run?

A: Edge AI Vision Computer products are optimized exclusively to run software developed by IBBVision. The installation or use of third-party software may be considered outside IBBVision's standard product support scope.

Q12: How is data privacy ensured?

A: Since all models operate on an edge computing architecture, video data remains within the facility and is not sent to an external cloud platform. Analysis results and metadata can be stored locally or transmitted to authorized central systems, according to the organization's preference.

CONCLUSION

The IBBVision Edge AI Vision Computer Series is a scalable family of edge computing platforms that transforms the traditional centralized and cloud-based surveillance approach. It processes video locally and securely runs IBBVision artificial intelligence solutions on-site. With models ranging from 4 to 64 channels, it addresses image processing needs at every scale—from small businesses to corporate facilities. Delivered with IBBVision Core software, these systems provide the necessary infrastructure for running IBBVision Deep Learning Surveillance and AI Image Analysis Solutions. All of this is accomplished securely and with a focus on privacy, without sensitive video data leaving the facility.

The Edge AI Vision Computer Series is part of the Edge Vision System product family developed by IBBVision. The scope of hardware, software, and AI analysis features may vary depending on product configuration and the relevant licenses.

All models are proprietary hardware and software solutions developed by IBBVision. All rights reserved.