DEEPER INTELLIGENCE. DEEPER SURVEILLANCE. HIKVISION DEEP . - Viditronic

DEEPER INTELLIGENCE.DEEPER SURVEILLANCE.HIKVISION DEEP LEARNING SOLUTION

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

ADVANTAGES OFDEEP LEARNING1. Traditional Intelligent Algorithm2. From “Shallow” to “Deep”The number of video surveillance devices and the sheeramount of data are both rapidly increasing in their ownrite, while the traditional intelligent algorithm continuesto operate only on the surface level. Current systemssuffer from：The algorithmic model for deep learning has a much deeper structure than the two 3-layered structures oftraditional algorithms. In deep learning, an original signal passes through layers of processing; next, it takes apartial understanding (shallow) to an overall abstraction (deep) where it can perceive an rRecognitionTypes3. From “Artificial Features” to “Feature Learning”Deep learning does not require manual intervention but relies on a computer to extract features by itself. The morefeatures there are, the more accurate the recognition and classifications will be.

KEY FACTORS OFDEEP LEARNINGThe rapid development of GPUs, supercomputers, cloud computing,and other high performance hardware platforms has made deeplearning possible.Scaleof DataComputingPowerUser experience has improved and more users are involved,facilitating a larger scale of data. With such a large amount of qualitytraining data, object pattern recognition models will become moreaccurate for video surveillance use.NetworkArchitectureThrough the constant optimization of deep learningalgorithms, better target-object recognition iscontinually being achieved.

KEY FEATURES OFDEEP LEARNINGFacial 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 isa step above and beyond anything video surveillance as you knowit. Hikvision’s Deep Learning technology filters out insignificantobjects and movements in a scene that would trigger normal alarmsystems.Vehicle data gets recorded and shapes the database to performnumerous security functions. People Counting systems givebusinesses an advantage in marketing and conversion efforts.Hikvision’s solutions add value on multiple levels.95%Similar

1. Facial Detection2. False Alarm FilterFacial Detection software will analyse images and determine the presence of ahuman face. When a face is detected, the system captures its position, size, andexpression. The video stream will judge whether there is a human face. If so, theposition, size, and main features will be recorded. Identifying characteristics canbe obtained from this information. When compared against recorded human facesin a database, a face can be identified. Facial comparison is the process by whichstructured data information operates after data modeling and analysis for thehuman face.The False Alarm Filter enables the system to perform secondary recognition forhuman body targets in behavioral detection events (line crossing detection, intrusiondetection), effectively reducing the false alarms caused by shaking leaves, shadows,light variations, vehicles, small animals, etc.Images and alarm messages from IP CamerasIntrusion DetectionLine Crossing DetectionDeepinView Primeter detectionHuman Detection & Analysis NVR95% SimilarCatsLeavesAfter DeepinMind NVR processes images, the false alarms are filtered out!LightCatsRainPeopleAlarm accuracy at leastBirdsLeaves90%

3. People Counting4. Vehicle Structured DataThe People Counting function counts peopleentering, exiting and passing by a specificscene, such as in a supermarket or museumwhere large crowds move through on foot.Vehicle Structured Data refers to a bivariate table formed by extracting the vehicle information, like licence plate number,vehicle color, model, brand, sub-brand, etc., and is used for vehicle information retrieval.Good Anti-Interference Ability5. Human Body SearchHeight FilteringLoitering FilteringThe search by human body picture feature enables the system to use a provided human body picture to find matchingimages and information in recorded footage.

APPLICATIONSSELECTED PRODUCTSCustomer Behaviour People Counting: Identify peak hours and days and assign staffaccordingly. Use together with POS data to calculate conversionrates. Dual-Lens People Counting Camera iDS-2CD6810F/CLoss Prevention Facial Recognition: Loss prevention managers can be notified whena suspected “habitual thief” visits. His or her face can be sharedacross all chain stores. Dual-lens facial recognition iDS-2CD8426G0/FRETAILBrick-and-mortar retailers need to better understandtheir customers’ behaviors to boost competitivenessagainst online competitors. And loss preventionplays an important role in boosting profits. DeepLearning technology helps users accomplish thesetasks – and much more – providing advancedanalytics and video surveillance.Intrusion Alarms Accurate human body detection: Deep Learning technologydramatically increases the accuracy of intrusion, it eliminates theinfluences from animal, shaking leaves and etc. DeepinView Primeter detection cameras DS-2CD7X26G0

Residential buildings, industrial plants, stadiums– there are many types of structures, but securityis the one thing that each one requires. Accesscontrol and perimeter protection are the mostcommon requirements. Deep Learning technologyestablishes more accurate intrusion alarms andmore convenient access control.BUILDINGHuman Body Detection and Analysis Hikvision’s DeepInmind Series NVRs are the first embedded NVR basedon a deep learning algorithm executed by its GPU, making it faster andmore accurate than conventional CPUs. This NVR effectively filters outalarms triggered by animals and inanimate objects, with greater than90% accuracy. Deep learning has come to the security industry in this amazing videorecording unit iDS-9632NXI-I8/8S(/16S), iDS-7716(32)NXI-I4(/16P)/8SIntrusion Alarms Accurate human body detection: the Deep Learning technologydramatically increases the accuracy of intrusion and eliminates theinfluences from animal, shaking leaves and etc. DeepinView Primeter detection cameras DS-2CD7X26G0Facial Recognition Control building access using facial recognition cameras and getalarmed of suspicious visitors. Facial recognition technology helps to eliminate buddy clocking andtimesheet abuse.

Facial Recognition Indoor Dual-Lens Facial Recognition Camera iDS-2CD8426G0/F Facial Recognition NVRiDS-9632NXI-I8/4F Facial Recognition Server DS-IE6308/16/32/64-E/FAIntelligent TrafficSMARTCITIESEffective protection of citizens, their propertyand public areas, is a concern for city authoritiesaround the world. In Safe City Project, Hikvision’sDeep Learning technology is adopted to identityspecific personnels and analyze human andvehicle behaviors. This can be used for locating afugitive at large, finding lost people, preventingpotential crimes, detecting parking violations, etc. Video Vehicle Detector iDS-TCD200-A Traffic Capture Unit iDS-TCV300/700 iDS-TCE300/700 Traffic Incident Detection Server iDS-TP40-16B ANPR Bullet Camera iDS-2CD8626G0/P Parking Violation Detection PTZ Camera iDS-2VS235-F836

OTHERSAIRPORTSRAILWAY STATIONSCUSTOMS & BORDER CONTROLGOVERNMENT SECTORSPUBLIC SQUARES

PRODUCT PeoplecountingFacialrecognitionANPRParking violationdetectionFalse alarm filter, line crossing detection,intrusion detection, region entry/exitVehicle brand/color recognition, special vehicle LoiteringQueueCrowd density9 kinds of traffic Vehicle Vehicle featurerecognition (police, ambulance, fire truck, etc.) detection detection detection and alarm data collection capturedetection DS-2CD7xxxG0 iDS-2CD86XX iDS-2CD8426G0/B DS-2CD7126G0/L iDS-TCD200-AiDS-TCE300iDS-TCE700Vehicle over-speeddetection r violationdetection 6Human capture/comparison

PRODUCT SHOWCASEiDS-2CD6810F/CDeepinView Indoor Dual-LensPeople Counting CameraiDS-2CD6810F-IV/CDeepinView Outdoor Dual-LensPeople Counting CameraiDS-2XM6810F-I(M)/CDeepinView Mobile Dual-LensPeople Counting Camera Indoor dual-lens people counting People counting Stereo vision Outdoor dual-lens people counting People counting Stereo vision Mobile dual-lens people counting People counting Stereo arksScenarioBuses/trainsiDS-2CD8626G0/PDeepinView ANPR Bullet CameraiDS-2CD8426G0/FDeepinView Dual-Lens FacialRecognition Camera Dual-lens face recognition Onboard face recognition, massive face library with up to60,000 faces. H.265 Stereo visionScenarioBuildings/airports/stadiums ANPR bullet ANPR H.265 Traffic event detection PTZ Vehicle parking detection PTZScenarioStreets PanoVu Works with DeepinView NVR to create accurate human and facecomparisons. epinView Parking ViolationDetection ew PanoVu sDS-2CD7xxxG0DeepinView Perimeter DetectionCamerasDS-2DF8xxxIXDS-2DF6xxxXDeepinView Perimeter DetectionCameras Primeter detection False alarm filter; line crossing detection, intrusion detection,region entry/exit PTZScenarioPublic/squares/streets Primeter detection False alarm filter; line crossing detection, intrusion detection,region entry/exitScenarioPublic/squares/streets

DS-2CD7126G0/L-IDeepinView Dual-Lens QueueDetection CameraiDS-86XXDeepinView Crowd DensityDetection Bullet Camera Crowd density bullet Crowd density detection and alarm Dual-lens queue detection Line-up queue detection Stereo vision Dual-lens behavior analysis Loitering, fall down, etc. Stereo visionScenarioPublic squaresScenarioStoresiDS-TCD200-ADeepinView Video VehicleDetectoriDS-2CD8426G0/BDeepinView Dual-LensBehavior Analysis CameraScenarioBanks, hospitals, schoolsiDS-TCE300/700DeepinView TrafficCapture UnitiDS-TCV300/700DeepinView Traffic CaptureUnit Video Vehicle Detector 9 kinds of traffic data collectionlane flow/average vehicle speed/time headway/spaceheadway/time occupancy/space occupancy/lane queuelength/vehicle type (large, small, motorcycle)/lane trafficstatus Three congestion levels: smooth/slow/in queue Traffic Capture UnitANPRH.265Support radar speed measurementWrong-way detectionVehicle type detectionVehicle color detectionScenarioExpressways/elevated roads/urban roads/tunnels/bridgesScenarioExpressways/elevated roads/urban roads/tunnels/downhillslopes/bridges Traffic Capture UnitANPRH.265Five kinds of traffic violation detection: red light violation/wrong-way driving/illegal lane change detection/drivingagainst guidance detectionScenarioCrossings/t-junctions

PRODUCT SHOWCASEHuman body detection analysis (linecrossing detection, intrusion detection,etc.) to improve alarm accuracySecondary analysis ofhuman bodies to improvealarm accuracyiDS-96064NXI-I16 iDS-96128NXI-I16 iDS-9632NXI-I8/16S iDS-9632NXI-I8/8S ModelPictureFace detection and facial recognition, Event detection and capture. Detection types: traffic Traffic data collection, including types: traffic flow, speed, spaceHuman Analysis facial image modeling and comparison, jam, parking, over lane line, U-turn, reverse driving, headway, time headway, lane-time occupation rate, lane-spacealarm linkage, search by facial imagepedestrian, throwing object, illegal line change.occupation rate, queue length, traffic traveling status.iDS-9632NXI-I8/4FiDS-7716NXI-I4/8S iDS-7716NXI-I4/16P/8S iDS-7732NXI-I4/8S iDS-7732NXI-I4/16P/8S iDS-TP40-16B Search by facial image andcomparison,identity confirmationBlacklist alarm DS-IE6308/16/32/64-E/FA DS-IC0116-F