System

Main Processor

Two 16 C/32 T X86 processors, 2.4 GHz

GPU

One AIX3300-A intelligent analysis card is pre-installed in the device. Up to five AIX3300-A intelligence analysis cards or five AIC5000 comparison cards can be installed. The following functions are available with the intelligent analysis card and relevant software license.

Operating System

Linux OS

Memory

Four 32 GB DDR4 memory modules with up to 32 slots

Disk

Two 2.5" 480 GB SSD and four 3.5" 4 TB HHD with up to 8 slots.

Face Analytics Function

Face Detection

Detects and analyzes face image streams by gender, age, expression, glasses, mustache, face mask, opened and closed eyes, and opened and closed mouths.

Face Modeling

Supports extracting attributes from face images.

Face Arm

Compares the face snapshot against a designated face database to get information on the first person that exceeds the arming threshold.

History Alarm Records Query

Quickly search for history records on arming alarms to review information on alarms that were previously triggered.

Management of Registered Database

Manage and use multiple types of registration databases such as the blocklist database, and static database. You can add, delete and modify these databases and their members.

Search in Registered Database

Quickly search for members in the registration database by name, gender and date of birth.

Search by Image in Registered Database

Images can be used to search for information. The results are compared with data on humans in the registration database, and the matches are displayed based on their similarity level.

Search in Snapshot Database

Conveniently search for history records of passing persons in the snapshot database.

Search by Image in Snapshot Database

Images can be used to search for information, and the search results can be filtered by time and channel. The results are compared with data on humans in the snapshot database, and the matches are displayed based on their similarity level.

1V1

Supports 1V1 face comparison, and returns similarity result.

Cluster

Supports clusters (when it is set to work with the video cloud platform)

Face Analytics Performance

Image Stream Analysis Capability

One AIX3300-A card supports processing up to 200 face images per second.

Blocklist Database Arm

AIC5000 card (The following information is for a single card)
• Supports processing a blocklist database with up to 5 million pieces of data, and can trigger real-time alarms for 240 face attributes/sec.
• Supports processing a blocklist database with up to 10 million pieces of data, and can trigger real-time alarms for 180 face attributes per second.
• Supports processing a blocklist database with up to 30 million pieces of data, and can trigger real-time alarms for 100 face attributes per second.
• Supports processing a blocklist database with up to 50 million pieces of data, and can trigger real-time alarms for 80 face attributes per second.
• The arming threshold is higher than 80%.

Search by Image

When performing search by image in the face database, each AIC5000 card has the ability to process up to 100 million pieces of data in seconds. Of this 100 million, 30 million are allocated for the registration database and 70 million for the snapshot database.

1V1

One AIX3300-A card supports processing data up to 75 times/sec.

Vehicle Analytics

Vehicle Recognition Mode

Recognizes the front and back of vehicles. Supports recognition of license plates from Brazil and the Middle East, and configuring license plate recognition for other countries.

License Plate Color Recognition

White, black, yellow, blue, and green

Vehicle Color Recognition

Recognizes a variety of colors such as white, orange, pink, black, red, yellow, gray, blue, green, silver, brown and purple

Vehicle Type Recognition

Supports large bus, heavy truck, medium truck, sedan, van, truck, medium bus, SUV, MPV and pickup

Vehicle Attributes Recognition

Recognizes vehicle attributes such as tissue boxes, sunshields, pendants, perfume, cards and permits.

Safe Driving Behavior Detection

For drivers, it detects when they are not wearing their seatbelt, calling while driving and smoking.
For co-drivers, it detects when they are not wearing their seatbelt and carrying a baby.

Target Detection

Supports vehicle recognition of incomplete snapshot

Image Stream Analysis Capability

One AIX3300-A card supports processing up to 3 million images/day in 2 MP to 9 MP.

Vehicle Brand/Logo Recognition

147 kinds

License Plate Recognition

License plate recognition with a minimum of 50 x 13 pixels is supported.

License Plate Recognition Rate

The license plate is clear and distinguishable when the width of the resolution is ≥120 and the environment has normal lighting in the daytime and a fill light at night.
License plate recognition accuracy: ≥96%.
This figure is subject to actual testing.

Vehicle Type Recognition Rate

The vehicle type is clear and distinguishable when the resolution is ≥240 × 240 and the environment has normal lighting in the daytime and a fill light at night.
Vehicle type recognition accuracy: ≥92%.
This figure is subject to actual testing.

Vehicle Color Recognition Rate

The vehicle color is clear and distinguishable when the resolution is ≥240 × 240 and the environment has normal lighting in the daytime and a fill light at night.
Vehicle color recognition accuracy: ≥95%.
This figure is subject to actual testing.

Safety Belts Recognition Rate

When the vehicle glass is clear, the recognition rate for safety belts is ≥85%. This figure is subject to actual testing.

Recognition Rate of Driver and Passenger Phone Calling

When the vehicle glass is clear, recognition rate of driver and passenger phone calling is ≥85%. This figure is subject to actual testing.

Search by Vehicle Picture

Images can be used to search for information, and the search results can be filtered by time and channel. The results are compared with data on motor vehicles in the database, and the matches are displayed based on their similarity level.

Search by Vehicle Picture Performance

Vehicle Search

When performing search by image in the snapshot database, each AIC5000 card has the ability to process up to 100 million pieces of data in seconds.

Metadata Analytics

Target Classification

Classifies targets including faces, bodies, motor vehicles, and non-motor vehicles. It generates metadata analyses for live videos and historical videos when used with the platform, as well as for video files uploaded offline. Additionally, it extracts metadata from moving targets. However, face images are generated without metadata.

Motor Vehicle Detection

Detects motor vehicles by a wide range of attributes such as type, color, brand and plate number. Supports recognition of license plates from Brazil and the Middle East, and configuring license plate recognition for other countries. Detects sunshield, not wearing seatbelt, calling, and ornaments such as pendants and tissue boxes.

Non-motor Vehicle Detection

Detects riders by a wide range of attributes such as gender, age, hair style, their top and bottom clothes and color, non-motor vehicle type and color wearing a hat, hat color, umbrella (canopy), umbrella (canopy) color, bag, bag color, shoe type and color, vest, mask color, raincoat, rearview mirror, truck, basket and direction.

Pedestrian Detection

Detects pedestrians by a wide range of attributes such as gender, age, hair style, their top and bottom clothes and color, wearing a hat, hat color, umbrella, umbrella color, bag, bag color, shoe type and color, vest, mask color, raincoat, cart, whether they are riding, and direction.

Real-time Display

Displays the analysis results in real time, and display humans, motor vehicles and non-motor vehicles in real time with tracking boxes.

Search by Attribute

Intelligent search of human, motor vehicles and non-motor vehicles by their attributes.

Search by Image

Images can be used to search for information, and the search results can be filtered by time and channel. The results are compared with data on humans, motor vehicles and non-motor vehicles in the database, and the matches are displayed based on their similarity level.

Video Recording Task

Generates metadata analyses of historical videos when used with the platform. It extracts metadata on moving targets, and automatically accelerates the analysis tasks of video recordings.

Local Task

Generates the metadata analysis of the local video files uploaded offline. It extracts metadata on moving targets, and automatically accelerates the analysis tasks of local videos.

Display Tracks on the Map

Yes (when using with the platform)

Computing Node Cluster

Supports clusters (when it is set to work with the video cloud platform)

Metadata Analytics Performance

Intelligent Video Stream

Supports real-time display of structured intelligent video streaming, including target attributes, and displays up to 5 items at the same time. Pedestrians (age, gender, top clothes and color, hat, umbrella and bag), vehicle (model, brand, license plate and color)

Metadata Analytics Performance

AIX3300-A card (The following information is for a single card)
• Performs video analysis of moving targets through up to 80 channels in 1080p.
• In performing metadata analysis of targets, it can process up to 100 images/sec or 3 million images/day in 1080p.

Search by Image Performance

When performing search by image in the snapshot database, each AIC5000 card has the ability to process up to 100 million pieces of data in seconds.

Detection Rate of Moving Target

The pedestrians and non-motor vehicles are clear and distinguishable when the resolution is ≥40 × 80 and the environment has normal lighting in the daytime and a fill light at night.
• Detection rate of pedestrians: ≥95%
• Detection rate of non-motor vehicles: ≥95%
The motor vehicles are clear and distinguishable when the resolution is ≥120 × 120 and the environment has normal lighting in the daytime and a fill light at night.
• Detection rate of motor vehicles: ≥95%.
These figures are subject to actual testing.

Pedestrian Recognition Accuracy

The pedestrians are clear and distinguishable when the resolution is ≥80×160 and the environment has normal lighting in the daytime and a fill light at night.
• Gender accuracy: ≥90%
• Hair style accuracy: ≥90%
• Clothes style and color accuracy: ≥90%
• Wearing accuracy: ≥90%
• Belongings accuracy: ≥90%
These figures are subject to actual testing.

Recognition Accuracy of Non-motor Vehicle

The non-motor vehicles are clear and distinguishable when the resolution is ≥80 × 160 and the environment has normal lighting in the daytime and a fill light at night.
• Gender accuracy: ≥90%
• Hair style accuracy: ≥90%
• Clothes style and color accuracy: ≥90%
• Wearing accuracy: ≥90%
• Belongings accuracy: ≥90%
• Non-motor vehicle type accuracy: ≥90%
These figures are subject to actual testing.

Vehicle Recognition Accuracy

The motor vehicles are clear and distinguishable when the resolution is ≥240× 240 and the environment has normal lighting in the daytime and a fill light at night.
• Motor vehicle type accuracy: ≥92%
• Motor vehicle color accuracy: ≥90%
• Driver and passengers' safety belt accuracy: ≥85%
• Driver and passengers' phone call accuracy: ≥80%
The license plate is clear and distinguishable when the resolution width is ≥120 and the environment has normal lighting in the daytime and a fill light at night.
• Plate accuracy: ≥96%;
• Plate color accuracy: ≥90%.
These figures are subject to actual testing.

Port

Network Port

4 × 1000 Mbps self-adaptive network ports

USB

2 × front USB2.0 ports and 2 × rear USB3.0 ports

VGA

1 × VGA port

Others

1 × RJ-45 management network port

General

Power Supply

100–127/200–240 VAC, 60/50 Hz, 12/8 A

Power Redundancy

Dual

Power Consumption

Working (all HDDs connected, with 1 AIX3300-A cards): ≤660 W (2,252 BTU/h)
Working (all HDDs connected, with 6 AIX3300-A cards): ≤1,080 W (3,685 BTU/h)

Operating Temperature

+10 °C to +35 °C (+50 °F to +95 °F)

Operating Humidity

20%–80% (RH), non-condensing

Storage Temperature

–40 °C to +60 °C (–40 °F to +140 °F)

Storage Humidity

5%–95% (RH), non-condensing

Gross Weight

28.62 kg (63.10 lb)

Net Weight

22.56 kg (49.74 lb)

Product Dimensions

794.0 mm × 446.0 mm × 87.8 mm (31.26" × 17.56" × 3.46") (D × W × H)

Packaging Dimensions

1000 mm × 600 mm × 260 mm (39.37" × 23.62" × 10.24") (D × W × H)

Installation

Standard 19" rack installation with guide rail

Certifications

CE-EMC:
• EN 55032:2015
• EN 55032:2015/A11:2020
• EN 55032:2015/A1:2020
• EN 55035:2017
• EN 55035:2017/A11:2020
• EN 61000-3-3:2013/A2:2021
• EN IEC 61000-3-2:2019/A1:2021
• IEC 61000-4-2:2008
• IEC 61000-4-3:2020
• IEC 61000-4-4:2012
• IEC 61000-4-5:2014/AMD1:2017
• IEC 61000-4-6:2023
• IEC 61000-4-8:2009
• IEC 61000-4-11:2020/COR2:2022
CE-LVD:
• EN IEC 62368-1:2020+A11:2020
• BS EN IEC 62368-1:2020+A11:2020

Optional

Product Type

Hardware