DEEPER INTELLIGENCE.

DEEPER SURVEILLANCE.
HIKVISION DEEP LEARNING SOLUTION
DEEP LEARNING
TECHNOLOGY
In this ever-expanding era of Surveillance Data Technology (SDT), deep intelligence will become the foundation for the security industry. Technologies that “learn” will become
more common and more powerful. This trend will strengthen critical security efforts in every sphere. Now, Hikvision’s DeepinView Cameras and DeepinMind NVRs will lead the
way in this new world of surveillance technology by making invisible intelligence visible for users, and then putting that intelligence to good use.

Deep
Learning
ADVANTAGES OF
DEEP LEARNING
1. Traditional Intelligent Algorithm 2. From “Shallow” to “Deep”
The number of video surveillance devices and the sheer The algorithmic model for deep learning has a much deeper structure than the two 3-layered structures of
amount of data are both rapidly increasing in their own traditional algorithms. In deep learning, an original signal passes through layers of processing; next, it takes a
rite, while the traditional intelligent algorithm continues partial understanding (shallow) to an overall abstraction (deep) where it can perceive an object.
to operate only on the surface level. Current systems
suffer from：

Low
Accuracy

Poor

3. From “Artificial Features” to “Feature Learning”

Environmental
Suitability

Fewer
Recognition Deep learning does not require manual intervention but relies on a computer to extract features by itself. The more
Types
features there are, the more accurate the recognition and classifications will be.
KEY FACTORS OF
DEEP LEARNING

The rapid development of GPUs, supercomputers, cloud computing,

and other high performance hardware platforms has made deep
learning possible.

Scale Computing Network

of Data Power Architecture

User experience has improved and more users are involved, Through the constant optimization of deep learning
facilitating a larger scale of data. With such a large amount of quality algorithms, better target-object recognition is
training data, object pattern recognition models will become more continually being achieved.
accurate for video surveillance use.
KEY FEATURES OF
DEEP LEARNING
Facial Detection is only the beginning for Deep Learning features.
With analytics that take business solutions into the next century,
and with automatic alarm accuracy above 90%, this technology is
a step above and beyond anything video surveillance as you know
it. Hikvision’s Deep Learning technology filters out insignificant
objects and movements in a scene that would trigger normal alarm
systems.

Vehicle data gets recorded and shapes the database to perform

numerous security functions. People Counting systems give
businesses an advantage in marketing and conversion efforts.
Hikvision’s solutions add value on multiple levels.

95%
Similar
1. Facial Detection 2. False Alarm Filter
Facial Detection software will analyse images and determine the presence of a The False Alarm Filter enables the system to perform secondary recognition for
human face. When a face is detected, the system captures its position, size, and human body targets in behavioral detection events (line crossing detection, intrusion
expression. The video stream will judge whether there is a human face. If so, the detection), effectively reducing the false alarms caused by shaking leaves, shadows,
position, size, and main features will be recorded. Identifying characteristics can light variations, vehicles, small animals, etc.
be obtained from this information. When compared against recorded human faces
in a database, a face can be identified. Facial comparison is the process by which Images and alarm messages from IP Cameras
structured data information operates after data modeling and analysis for the
human face.

Line Crossing Detection Intrusion Detection

DeepinView Primeter detection

Human Detection & Analysis NVR

95% Similar Cats Leaves

After DeepinMind NVR processes images, the false alarms are filtered out!

Light Cats Rain

People

Alarm accuracy at least

Birds Leaves 90%

3. People Counting 4. Vehicle Structured Data
The People Counting function counts people Vehicle Structured Data refers to a bivariate table formed by extracting the vehicle information, like licence plate number,
entering, exiting and passing by a specific vehicle color, model, brand, sub-brand, etc., and is used for vehicle information retrieval.
scene, such as in a supermarket or museum
where large crowds move through on foot.

Good Anti-Interference Ability

5. Human Body Search

The search by human body picture feature enables the system to use a provided human body picture to find matching
images and information in recorded footage.
Height Filtering

Loitering Filtering
APPLICATIONS
SELECTED PRODUCTS Customer Behaviour
• People Counting: Identify peak hours and days and assign staff
accordingly. Use together with POS data to calculate conversion
rates.
• Dual-Lens People Counting Camera iDS-2CD6810F/C

Loss Prevention
• Facial Recognition: Loss prevention managers can be notified when
a suspected “habitual thief” visits. His or her face can be shared
across all chain stores.
• Dual-lens facial recognition iDS-2CD8426G0/F

RETAIL Intrusion Alarms

• Accurate human body detection: Deep Learning technology
Brick-and-mortar retailers need to better understand
dramatically increases the accuracy of intrusion, it eliminates the
their customers’ behaviors to boost competitiveness influences from animal, shaking leaves and etc.
against online competitors. And loss prevention • DeepinView Primeter detection cameras DS-2CD7X26G0
plays an important role in boosting profits. Deep
Learning technology helps users accomplish these
tasks – and much more – providing advanced
analytics and video surveillance.
Residential buildings, industrial plants, stadiums
– there are many types of structures, but security
is the one thing that each one requires. Access Human Body Detection and Analysis
control and perimeter protection are the most • Hikvision’s DeepInmind Series NVRs are the first embedded NVR based
on a deep learning algorithm executed by its GPU, making it faster and
common requirements. Deep Learning technology
more accurate than conventional CPUs. This NVR effectively filters out
establishes more accurate intrusion alarms and alarms triggered by animals and inanimate objects, with greater than
more convenient access control. 90% accuracy.
• Deep learning has come to the security industry in this amazing video

BUILDING
recording unit iDS-9632NXI-I8/8S(/16S), iDS-7716(32)NXI-I4(/16P)/8S

Intrusion Alarms
• Accurate human body detection: the Deep Learning technology
dramatically increases the accuracy of intrusion and eliminates the
influences from animal, shaking leaves and etc.
• DeepinView Primeter detection cameras DS-2CD7X26G0

Facial Recognition
• Control building access using facial recognition cameras and get
alarmed of suspicious visitors.
• Facial recognition technology helps to eliminate buddy clocking and
timesheet abuse.
 Facial Recognition
• Indoor Dual-Lens Facial Recognition Camera iDS-2CD8426G0/F
• Facial Recognition NVR
iDS-9632NXI-I8/4F
• Facial Recognition Server DS-IE6308/16/32/64-E/FA

Intelligent Traffic
• Video Vehicle Detector iDS-TCD200-A
• Traffic Capture Unit iDS-TCV300/700 iDS-TCE300/700
• Traffic Incident Detection Server iDS-TP40-16B

SMART
• ANPR Bullet Camera iDS-2CD8626G0/P
• Parking Violation Detection PTZ Camera iDS-2VS235-F836

CITIES
Effective protection of citizens, their property
and public areas, is a concern for city authorities
around the world. In Safe City Project, Hikvision’s
Deep Learning technology is adopted to identity
specific personnels and analyze human and
vehicle behaviors. This can be used for locating a
fugitive at large, finding lost people, preventing
potential crimes, detecting parking violations, etc.
OTHERS AIRPORTS GOVERNMENT SECTORS

RAILWAY STATIONS PUBLIC SQUARES

CUSTOMS & BORDER CONTROL

PRODUCT SHOWCASE

Model Picture People Facial ANPR Human capture/ Parking violation False alarm filter, line crossing detection, Vehicle brand/color recognition, special vehicle Loitering Queue Crowd density 9 kinds of traffic Vehicle Vehicle feature Behavior violation Vehicle over-speed
counting recognition comparison detection intrusion detection, region entry/exit recognition (police, ambulance, fire truck, etc.) detection detection detection and alarm data collection capture detection detection detection

iDS-2CD6810F/C
•
iDS-2CD6810F-IV/C
•
iDS-2XM6810F-I(M)/C
•
iDS-2CD8426G0/F
•
iDS-2CD8626G0/P
• •
•
iDS-2PT9122BX-DE/S
iDS-2PT9142BX-DE/S

iDS-2VS235-F836
• •
•
DS-2DF8xxxIX
DS-2DF6xxxX

DS-2CD7xxxG0
•
iDS-2CD86XX
•
iDS-2CD8426G0/B
•
DS-2CD7126G0/L
•
iDS-TCD200-A
•
• • • •
iDS-TCV300
iDS-TCV700

• • • •
iDS-TCE300
iDS-TCE700
PRODUCT SHOWCASE

iDS-2CD6810F/C iDS-2CD6810F-IV/C iDS-2XM6810F-I(M)/C

DeepinView Indoor Dual-Lens DeepinView Outdoor Dual-Lens DeepinView Mobile Dual-Lens
People Counting Camera People Counting Camera People Counting Camera

• Indoor dual-lens people counting • Outdoor dual-lens people counting • Mobile dual-lens people counting
• People counting • People counting • People counting
• Stereo vision • Stereo vision • Stereo vision
Scenario Scenario Scenario
Buildings/airports Stadiums/parks Buses/trains

iDS-2CD8426G0/F iDS-2CD8626G0/P iDS-2PT9122BX-DE/S

DeepinView Dual-Lens Facial DeepinView ANPR Bullet Camera iDS-2PT9142BX-DE/S
Recognition Camera DeepinView PanoVu Camera

• Dual-lens face recognition • ANPR bullet • PanoVu

• Onboard face recognition, massive face library with up to • ANPR • Works with DeepinView NVR to create accurate human and face
60,000 faces. • H.265 comparisons.
• H.265 Stereo vision • PanoVu
Scenario
Scenario Streets/checkpoints Scenario
Buildings/airports/stadiums Intersections/airports/public/squares

iDS-2VS235-F836 DS-2DF8xxxIX DS-2CD7xxxG0

DeepinView Parking Violation DS-2DF6xxxX DeepinView Perimeter Detection
Detection Camera DeepinView Perimeter Detection Cameras
Cameras

• Traffic event detection PTZ • Primeter detection • Primeter detection

• Vehicle parking detection • False alarm filter; line crossing detection, intrusion detection, • False alarm filter; line crossing detection, intrusion detection,
• PTZ region entry/exit region entry/exit
• PTZ
Scenario Scenario
Streets Scenario Public/squares/streets
Public/squares/streets
 DS-2CD7126G0/L-I iDS-86XX iDS-2CD8426G0/B
DeepinView Dual-Lens Queue DeepinView Crowd Density DeepinView Dual-Lens
Detection Camera Detection Bullet Camera Behavior Analysis Camera

• Dual-lens queue detection • Crowd density bullet • Dual-lens behavior analysis

• Line-up queue detection • Crowd density detection and alarm • Loitering, fall down, etc.
• Stereo vision • Stereo vision
Scenario
Scenario Public squares Scenario
Stores Banks, hospitals, schools

iDS-TCD200-A iDS-TCV300/700 iDS-TCE300/700

DeepinView Video Vehicle DeepinView Traffic Capture DeepinView Traffic
Detector Unit Capture Unit

• Video Vehicle Detector • Traffic Capture Unit • Traffic Capture Unit

• 9 kinds of traffic data collection • ANPR • ANPR
lane flow/average vehicle speed/time headway/space • H.265 • H.265
headway/time occupancy/space occupancy/lane queue • Support radar speed measurement • Five kinds of traffic violation detection: red light violation/
length/vehicle type (large, small, motorcycle)/lane traffic • Wrong-way detection wrong-way driving/illegal lane change detection/driving
status • Vehicle type detection against guidance detection
• Three congestion levels: smooth/slow/in queue • Vehicle color detection
Scenario
Scenario Scenario Crossings/t-junctions
Expressways/elevated roads/urban roads/tunnels/bridges Expressways/elevated roads/urban roads/tunnels/downhill
slopes/bridges
PRODUCT SHOWCASE

Human body detection analysis (line Secondary analysis of Face detection and facial recognition, Event detection and capture. Detection types: traffic Traffic data collection, including types: traffic flow, speed, space Search by facial image and
Model Picture crossing detection, intrusion detection, human bodies to improve Human Analysis facial image modeling and comparison, jam, parking, over lane line, U-turn, reverse driving, headway, time headway, lane-time occupation rate, lane-space comparison, Blacklist alarm
etc.) to improve alarm accuracy alarm accuracy alarm linkage, search by facial image pedestrian, throwing object, illegal line change. occupation rate, queue length, traffic traveling status. identity confirmation

iDS-96064NXI-I16
• • • • •
iDS-96128NXI-I16
• • • • •
iDS-9632NXI-I8/16S
• • •
iDS-9632NXI-I8/8S
• • •
iDS-9632NXI-I8/4F
• •
iDS-7716NXI-I4/8S
• • •
iDS-7716NXI-I4/16P/8S
• • •
iDS-7732NXI-I4/8S
• • •
iDS-7732NXI-I4/16P/8S
• • •
iDS-TP40-16B
• •
DS-IE6308/16/32/64-E/FA
• •
DS-IC0116-F
• •
 iDS-96064NXI-I16 iDS-96128NXI-I16
DeepinMind 16-ch Facial Recognition & DeepinMind 32-ch Facial Recognition
Analysis Embedded NVR Embedded NVR

• Up to 16-ch IP cameras analysis, face detection and face recognition.Face pictures modeling and • Up to 32-ch IP cameras analysis, face Detection and face Recognition.Face pictures modeling and
comparison, alarm linkage actions.Search People by face pictures comparison, alarm linkage actions.Search People by face pictures
• Powerful face pictures library management, up to 100,000 Face list • Powerful face pictures library management, up to 100,000 Face list
• Coopration with iVMS-4200 • Coopration with iVMS-4200
• Human Body Detection analytics (line crossing detection, intrusion detection, etc.) to improve the • Human Body Detection analytics (line crossing detection, intrusion detection, etc.) to improve the
alarm accuracy rate effectively alarm accuracy rate effectively
• Like the Rain/Leaf/Cat/Bird/Light/Human Body, All of these things may trigger line crossing or • Like the Rain/Leaf/Cat/Bird/Light/Human Body, All of these things may trigger line crossing or
instruction alarm,DeepinMind NVR(16S) can realize the secondary analysis of human body, improving instruction alarm,DeepinMind NVR(16S) can realize the secondary analysis of human body, improving
the alarm accuracy the alarm accuracy
• Search by human features and similarity • Search by human features and similarity
• More precise facial recognition and analytics based on Deep Learning algorithm • More precise facial recognition and analytics based on Deep Learning algorithm
• More precise Human body detection. Analytics based on Deep Learning algorithm • More precise Human body detection. Analytics based on Deep Learning algorithm
• Alarm accuracy at least 90%.(After processing by DeepinMind NVR(/S), the false alarms would be • Alarm accuracy at least 90%.(After processing by DeepinMind NVR(/S), the false alarms would be
Filtered) Filtered)

Scenario Scenario
• Applied to all kinds of smalls and medium-sized faces project, can meet the demand of various • Applied to all kinds of smalls and medium-sized faces project, can meet the demand of various
industries face application industries face application.
• Such as casino/residential buildings/schoolyard/mall • Such as casino/residential buildings/schoolyard/mall

DS-9632NXI-I8/8S(16S) iDS-9632NXI-I8/4F
DeepinMind 8/16-ch Human Detection DeepinMind 4-ch Facial Recognition
& Analysis Embedded NVR Embedded NVR

• High accuracy human body detection analysis (line crossing detection, intrusion detection); up to • Up to 4 channels of IP cameras analysis, face detection and facial recognition. Facial image
8/16 channels of IP camera analysis available modeling and comparison, alarm linkage actions. Search for persons by facial images
• DeepinMind NVRs (16S) runs a secondary analysis and filters out objects that may trigger false • Powerful facial image library management; stores up to 50,000 faces
alarms such as rains, leaves, cats, birds, and light variations • Integrates with iVMS-4200
• More precise human body detection based on Deep Learning algorithm • More precise facial recognition and analysis based on Deep Learning algorithm
• Alarm accuracy at 90%+
Scenario
Scenario • Applies to all-size facial recognition projects and all industries, such as casinos, residence,
• Applies to any scenario that requires high alarm accuracy for perimeter precaution, such as schools, and shopping malls
casinos, office buildings, industry parks, hotels, and banks
 iDS-7716/32NXI-I4/(16P)8S iDS-TP40-16B
DeepinMind 8-ch Human Detection & DeepinMind Server
Analysis Embedded NVR Traffic Incident Detection Server

• Human Body Detection analytics (line crossing detection, intrusion detection, etc.) to improve the • Up to 16 channels of 3 MP IP cameras for traffic incident detection and traffic data collection.
alarm accuracy rate effectively.Up to 8-ch IP cameras analysis • Traffic incident detection type: congestion, parking violation, driving on a lane line, wrong-way
• Like the Rain/Leaf/Cat/Bird/Light/Human Body, All of these things may trigger line crossing or driving, pedestrians, falling objects, illegal lane change, roadblocks, construction, occupying the
instruction alarm,DeepinMind NVR(8S) can realize the secondary analysis of human body, improving emergency lane.
the alarm accuracy • Traffic data collection: vehicle type, lane flow, average speed, space headway, time headway, time
• Search by human features and similarity occupancy, space occupancy, lane queue length, lane traffic status
• More precise Human body detection. Analytics based on Deep Learning algorithm
Scenario
• Alarm accuracy at least 90%.(After processing by DeepinMind NVR(/S), the false alarms would be
• Expressways/tunnels/elevated roads/bridges
Filtered)

Scenario
• All kinds of scenarios(for example:perimeter precaution)that require high alarm accuracy, such as
casino/building/industry park/hotel/bank

Coming Soon
DS-IE6308/16/32/64-E/FA DS-IC0116-F
DeepinMind Facial Recognition Server DeepinMind Facial Recognition
Server

• Supports for up to 16 MP uploaded images for comparison • Supports for up to 16 MP uploaded images for comparison
• Supports for up to 8 MP camera for real-time computing and comparison • Supports for up to 8 MP camera for real-time computing and comparison
• 1-to-1 facial comparison for identity confirmation • Blacklist alarm supports 300K blacklist targets
• Blacklist alarm supports 300K blacklist targets • Supports server clustering for large-scale projects; provides more facial recognition applications
• Stores 1 million captured images via integration with Hikvision VMS platform
• Facial recognition and blacklist comparison, identity confirmation, blacklist alarm, independent • Facial recognition and comparison blacklist, identity confirmation, blacklist alarm
working mode support
Scenario
Scenario • Airport/customs/public squares/government offices
• Airport/customs/public squares/government offices
DEEPER INTELLIGENCE.
DEEPER SURVEILLANCE.
HIKVISION DEEP LEARNING SOLUTION

Distributed by

Headquarters
No.555 Qianmo Road, Binjiang District,
Hangzhou 310051, China
T +86-571-8807-5998
overseasbusiness@hikvision.com

Hikvision USA Hikvision Europe Hikvision Middle East Hikvision Russia Hikvision India Hikvision Italy Hikvision France

2017-H2
T +1-909-895-0400 T +31-23-55-42-770 T +971-4-8816086 T +7-495-669-67-99 T +91-22-28469900 T +39-0438-6902 T +33(0)1-85-330-450
sales.usa@hikvision.com info.eu@hikvision.com salesme@hikvision.com saleru@hikvision.com sales@pramahikvision.com info.it@hikvision.com info.fr@hikvision.com

Hikvision Spain Hikvision Poland Hikvision UK Hikvision Singapore Hikvision Oceania Hikvision Canada Hikvision Korea
T +34-91-737-16-55 T +48-22-460-01-50 T +01628-902140 T +65-6684-4718 T +61-2-8599-4233 T +1-909-895-0400 T +82-31-731-8841
info.es@hikvision.com poland@hikvision.com sales.uk@hikvision.com sg@hikvision.com salesau@hikvision.com sales.usa@hikvision.com sales.korea@hikvision.com

Hikvision Brazil Hikvision Africa Hikvision Turkey Hikvision Kazakhstan Hikvision Hong Kong
T +55 11 3318-0050 T +27 (10) 0351172 T +90-216-521-70-70 T +7-727-9730667 T +852-2151-1761
Latam.support@hikvision.com sale.africa@hikvision.com sales.tr@hikvision.com nikia.panfilov@hikvision.ru info.hk@hikvision.com

Follow us on social media to get the latest product and solution information

Hikvision
Hikvision HikvisionHQ HikvisionHQ Hikvision_Global Corporate Channel
www.hikvision.com