The document describes an intelligent fusion server that integrates deep learning algorithms for analyzing pictures and videos. It can concurrently analyze up to 30 channels of video for functions like face recognition, vehicle license plate identification, and generating watch lists. The server provides powerful GPU acceleration and storage for up to 30 million pieces of image and video data. It has a web interface and supports cluster deployment for load balancing.
The document describes an intelligent fusion server that integrates deep learning algorithms for analyzing pictures and videos. It can concurrently analyze up to 30 channels of video for functions like face recognition, vehicle license plate identification, and generating watch lists. The server provides powerful GPU acceleration and storage for up to 30 million pieces of image and video data. It has a web interface and supports cluster deployment for load balancing.
The document describes an intelligent fusion server that integrates deep learning algorithms for analyzing pictures and videos. It can concurrently analyze up to 30 channels of video for functions like face recognition, vehicle license plate identification, and generating watch lists. The server provides powerful GPU acceleration and storage for up to 30 million pieces of image and video data. It has a web interface and supports cluster deployment for load balancing.
The document describes an intelligent fusion server that integrates deep learning algorithms for analyzing pictures and videos. It can concurrently analyze up to 30 channels of video for functions like face recognition, vehicle license plate identification, and generating watch lists. The server provides powerful GPU acceleration and storage for up to 30 million pieces of image and video data. It has a web interface and supports cluster deployment for load balancing.
Intelligent fusion server, equipped with professional GPU card, integrates deep learning-based algorithms of picture and video structuralization. It is a colllection of analysis, storage and application. By recognizing, analyzing, modelling and comparing pictures of vehicles, the intelligent fusion server can perform functions as list alarm, creating personnel archives, vehicle arming, and so forth. Integrates analysis, storage and application as one, and applicable to various scenarios.
Concurrent analysis of Max. 30 channels of 1080P network cameras for a single device. Provide Max. 30 million pieces of pictures and data storage for a single device. Performs various functions, including list alarm, personnel archive and vehicle arming, etc. via web application interface. Equipped with professional GPU accelerator and integrates deep learning-based intelligent algorithms. Support cluster deployment to deal with balanced load, dynamic adding and failover. Support adding Max. 5 devices under cluster mode. Specification Model DS-IX2001-A3U/X System CentOS 7.8 Version Device V1.2.0 Version HCP 2.0 Platform HCE 1.1.1 Version HCM Lite 1.1.1 Device Type All-in-one Supports analysis, comparison and classification of faces in pictures, real-time videos or Analysis Type recordings. Recognition 99% Accuracy Face Picture 170 pieces/second Analysis and Format: JPEG, BMP, TIF, PNG Comparison Face Video 30 channels (2 MP) Analysis and 12 channels (2 MP to 5 MP) Comparison 6 channels (5 MP to 8 MP) Concurrent Performance- 30 pairs per second 1V1 Product Comparison Description Blocklist Alarm-Respon 1s se Time Max. Number of List 128 Libraries Max. Number of Arming 3 million Lists Max. Number 10 million of Static Lists Data Type Picture, video Single video size ≤ 10 GB, and total video size ≤ 100 GB Imported Max. 40 times accelerated analysis speed Video Analysis Format: MP4, AVI, TS, PS, MBF, ASF, SVAC Resolution: 720 P to 8 MP Facial Video Real-time video stream: H.264, Hikvision H.265 Format Local recording: H.264, Hikvision H.265 Video Frame Rate 12 to 30 frames per second (25 frames per second recommended) Requirement Face Picture JPEG, BMP, TIF, PNG Format Face analysis target: Resolution: 48 × 48 to 4096 × 4096 (16 MP) Size: ≤ 8 MB Face Picture Pupil distance: 20 to 300 pixels recommended Requirement Face angle deviation: Face analysis: ≤ 35° (vertical); ≤55° (horizontal) Face picture of list library: ≤ 25° (vertical); ≤30° (horizontal) Supports analysis and modelling for human bodies or vehicles in pictures, real-time videos or Analysis Type recordings. Vehicle Vehicle color, vehicle type, vehicle main brand, license plate number Attribute Analysis of 25 channels (2 MP) Vehicle 16 channels (2 MP to 5 MP) Videos 8 channels (5 MP to 8 MP) Analysis of Vehicle 60 pieces per second Pictures Recognition 99% Accuracy Data Type Picture, video Single video size ≤ 10 GB, and total video size ≤ 100 GB Imported Max. 40 times accelerated analysis speed Video Video Analysis Format: MP4, AVI, TS, PS, MBF, ASF, SVAC Structuralizat Resolution: 720 P to 8 MP ion Video Format Real-time video stream: H.264, Hikvision H.265 Video Frame Rate 12 to 30 frames per second (25 frames per second recommended) Requirement Picture JPEG, BMP, TIF, PNG Format Resolution: 256 × 256 to 4096 × 2160 (8 MP) Human Body Human body width: 70 to 300 pixels recommended Picture Completeness: the blocking area should be less than 30 percent of the target Requirement Angle deviation: the depression angle should be no greater than 45° Resolution: 256 × 256 to 4096 × 2160 (8 MP) Vehicle Vehicle width: 100 to 300 pixels recommended Picture License plate width: 80 to 120 pixels recommended Requirement Angle deviation: less than 30°(horizontal) and 25°(vertical), modelling for both the front and rear Picture and Structured 30 million Data Storage Data Search by 2s Vehicle Picture-Respo nse Time Alarm Blocklist, allowlist, and license plate 1V1 Supports rapid and accurate comparison of 2 face pictures Comparison Personnel Support Archive Web Smart Search List library search, capture library search, alarming search Application Number of License Plate ≤ 1000 Arming Lists Device Operation and Support Maintenance Algorithm Vehicles Type DFR V5.0.310; Algorithm FD V5.0.310; Version HMS V4.4.0 Authorization Product Soft Encryption Type Performance Protocol Type ISAPI Cluster ≤5 Capacity Video Accelerating 40 Capacity CPU Intel Xeon Gold 6230 × 1 Memory 128 GB Network Gigabit Ethernet self-adaptive interface × 4 Interface Max. Power 445 W Consumption Rated Power 750 W Consumption Hardware Chassis Height 87 mm (3.4 inch) Specifications HDD 240 GB M.2 × 1 + 480 GB SSD × 2 + 8 TB SATA × 3 Specification GPU Card Tesla T4 ×1 PSU Hot-plugged efficient 1+1 redundant power module External USB 2.0 × 2 + USB 3.0 × 2 + VGA × 2 Interfaces Device 715.5 mm × 482 mm × 86.8 mm (28.2 inch × 19.0 inch × 3.4 inch) Dimensions Package 965 mm × 670 mm × 320 mm (38.0 inch × 29.4 inch × 12.6 inch) Dimensions Storage and Transportatio -40 °C to 70 °C (-40 °F to 158 °F) n Temperature Working 5 °C to 35 °C (41 °F to 95 °F) Temperature Physical and Working Environment 8% to 90% (without condensation) Humidity al Parameters Net Weight (without 18.25 kg (40.23 lb.) package) Gross Weight (with 35.13 kg (77.44 lb.) package)
