Welcome To
XCORE AI Smart Box
Accuracy, Reliability, Versatilit
XCORE AI Smatr box Artificial Intelligence Workstation is an intelligent video analysis processing terminal device from HFSECURITY that supports running deep learning neural network algorithms.The internal integrated high computing power AI processing module, up to 28.8Tops of super computing power. High-performance configuration of the main control platform, with 16 1080P HD video decoding capabilities, integrated with a variety of video signal processing units, with lightweight, high performance, low power consumption, easy access, etc., widely used in various fields such as face recognition, intelligent security, behavior analysis
Artificial Intelligence Workstation
XCore Intelligent edge computing server Supports simultaneous processing of 16 1080P@30fps H.264/H.265 live streams or stored streams
Rich Interface
XCORE Intelligent Analysis AI BOX Support 28.8Tops deep learning operation, using a combination of front-end image preprocessing + back-end algorithm operation, supporting low-bit quantization of CNN, RCNN
and other neural network structure of deep learning dedicated gas pedal, support lowbit quantization of AlexNet, VGG, ResNet and other classification neural network,
support low-bit quantization of Faster R-CNN, SSD, FPN and other target detection
neural network.
Artificial Intelligence Workstation
Support dual Gigabit network ports, expandable 4G/WIFI wireless network mode
XCORE Series
Private Lessons
HFSECURITY fingerprint scanner offers an unparalleled level of security and convenience for a wide range of applications. With its advanced features and compatibility with multiple operating systems, it is a versatile and essential tool for any organization or individual who values security and privacy.
Ease of Use
Certified Image Quality
High Speed
Multifunctional
XCORE Product Features
- Supports simultaneous processing of 16 1080P@30fps H.264/H.265 live streams or stored streams.
- Support 28.8Tops deep learning operation, using a combination of front-end image preprocessing + back-end algorithm operation, supporting low-bit quantization of CNN, RCNN and other neural network structure of deep learning dedicated gas pedal, support lowbit quantization of AlexNet, VGG, ResNet and other classification neural network, support low-bit quantization of Faster R-CNN, SSD, FPN and other target detection neural network.
- Support face detection, tracking, recognition, etc.
- Support dual Gigabit network ports, expandable 4G/WIFI wireless network mode.
- Low power consumption design, combined with shell cooling, can increase the cooling fan active
cooling, product stability and reliability. - Fully embedded structure, highly integrated, can support desktop placement or wall mounting,
very easy to install and maintain.
Device access
- Xcore AI Video analysis box High-definition network cameras that comply with O NVIF , RTSP , and GB/T28181 standards
- Xcore Edge Computing Server the face capture machine that conforms to the GA / T 1400 protocol
- Support H.265 (does not support web preview) / H.2 64 video standard, up to 8 million pixel IPC access
Smart application
- The total library supports up to 300,000 face pictures, and supports 64 libraries
- Multi-class algorithm mixing: face mode, mixed mode (face-human binding + video structured)
- Face recognition: support full load maximum 4/8/1 6 video streams
- Video structure: support full load maximum 4/8/1 6 video streams
- Perimeter alert: support full load maximum 4/8/1 6 video streams
- Behavioral alert: support a maximum of 4/8/10 video streams with full load
- Item alert: support full load maximum 4/8/16 video streams
- People counting: support full load maximum 4/8 video streams
- Fire alert (industry extended algorithm package): supports a maximum of 4/8/16 video streams at full load
- Production safety supervision (industry extended algorithm package): supports a maximum of 4/8/16 video streams at full load
- Bright Kitchen Bright Stove (Industry Extended Algorithm Package): Supports a maximum of 4/8 video streams at full load
- Support face capture, face recognition comparison alarm, stranger recognition alarm, etc.
- Supports recognition of face attributes: gender, age, hat, glasses, mask, etc.
- Supports face, human body, motor vehicle, non-motor vehicle, license plate capture and face-human binding, human-non-motor vehicle binding
- Support the analysis of human body attributes such as the color of the upper and lower clothing, the style of the upper and lower clothing, the status of the backpack, whether to wear a helmet, etc.
- Support motor vehicle classification, vehicle attribute analysis such as color, brand, driving direction and non-motor vehicle classification
- Support license plate recognition and license plate-motor vehicle binding relationship
- Support perimeter alert: no parking of vehicles , departure of vehicles, loitering of personnel, over-the-wall detection, intrusion, border crossing
- Supportive behavior alert: running, falling, smoking , making phone calls, looking at mobile phones, sleeping on duty, leaving duty, overcrowded on duty , less on duty , gathering of people, scuffling
- Support item alert: Debris piled up
- Support people statistics: regional people statistics , entrance and exit people statistics
- Support industry algorithm expansion: open kitchen and bright stove , fire warning , production safety supervision
- Support bright kitchen and bright stove: mouse detection , garbage bin uncovered detection
- Support fire alert: detection of smoke , flame , and fire facilities
- Support production safety supervision: safety helmets , overalls , safety belts, reflective clothing , flames, smoke, fire protection facilities detection
System characteristics
- Support MegConnect protocol to access Hongtu, Pangu and other software platforms
- Cloud map or third-party view library platform through GA / T 1400 standard protocol
- Provide rich RESTful API protocol interface, which is convenient for third-party platforms to do docking development
Application Scenario
- Provides the capabilities of face recognition, all-target structured analysis, intelligent warning , and people counting , and cooperates with the upper platform software to realize the closed loop of face capture recognition, video structuring, intelligent warning , and passenger flow counting
scenarios. - Applied to places that require face recognition, such as entrances and exits of smart communities, entrances and exits of office buildings, key personnel list control and identification alarm, stranger identification, etc.
- Applied to structured places that require face-human-machine non-plate capture and license plate recognition, such as the control of people and vehicles in smart parks, and license plate recognition in smart communities.
- It provides industry algorithm expansion capabilities such as production safety supervision, bright kitchen, fire protection, etc., and cooperates with the industry platform to realize closed-loop scenarios such as safe production, hygienic kitchen, and fire protection
| System Parameters | |
|---|---|
| Main Processor | High performance embedded microprocessor |
| Operating System | Embedded Linux |
| Device Access |
|
| Video Stream Input | Video resolution:1920 x 1080 (2 million ), 2560 x 1440 ( 4 million), 3840 x 2160 (8 million ) |
| Video Decoding Type | H .264 / H .2 65 |
| Face Capture Machine | Maximum support for 8 /16/ 32-channel capture machine access (the capture machine must support the GA / T 1400 protocol) |
| Smart Prameters | |
| Human Face Recognition | Capture rate 99% |
| Capture false capture rate< 1% | |
| Whitelist identification pass rate> 99.5 % _ | |
| Recognition false recognition rate: < 0.5% | |
| The largest base library: 300,000 people portrait library | |
| Human Face Recognition | Capture rate 9 5 % |
| Capture false capture rate＜ 1% | |
| Motor Vehicle | Capture rate 90 % |
| Capture false capture rate＜ 1% | |
| Non-motor Vehicle | Capture rate 9 5 % |
| Capture false capture rate＜ 1% | |
| License Plate | Capture rate 9 5 % |
| Capture false capture rate＜ 1% | |
| Recognition rate 9 5 % | |
| Interface parameters | |
| Network Interface | 2, 10 0M/1000 M adaptive Ethernet , RJ 45 interface |
| Alarm Input/Output Interface | 4 switches |
| Audio Input/Output | 1 way |
| Front/ RearUSB Interface | Front 1 USB2.0 , 1 USB 3.0; Rear 2 USB 2.0 |
| R S485 | 2 way |
| Reset Button/Power LED ( PWR) | 1 |
| Running Indicator Light (RUN) | 1 pc, two-color (red+green) |
| System functions | |
| Running Indicator Light (RUN) | Passage of employees at entrances and exits; key personnel list control and identification alarm, stranger identification, etc. |
| Video Structured | Capture, attribute analysis, license plate recognition of faces, human bodies, motor vehicles, non-motor vehicles, license plates, etc. |
| Algorithm Warehouse Management | algorithm package upload via web, API , Meg Connect protocol, support algorithm package installation , uninstallation, deletion |
| Network Protocol | TCP/UDP/HTTP/MULTICAST/DHCP/FTP/NTP/HTTPS/RTSP /GAT1400 etc |
| Dual Network Port | Are supported : 1.multiple addresssettings 2.load balancing 3.Active/standby mode |
| Log Query | Inquiry, search and display of face-human-machine non-card capture information |
| Environmental equirements | |
| Operating Temperature | -30 ～+ 70 |
| Storage Temperature | -30 ～+ 70 |
| Relative Humidity | 1 0% ~ 90%RH, non-condensing |
| Other | |
| Power Supply | DC12V±10%, 2A |
| Structure | metal case |
| Dimensions (L, D, H) | 229 × 193 × 49 (mm) |
| Weight | <2kg |
company Introduction
Chongqing Huifan Technology Co., Ltd. is a Chinese company that provides biometric solutions and related technologies. As a biometric solution provider, they offer a range of products and services related to identity verification and access control.
We products, services, and technologies. , it is common for companies in the biometric solutions industry to offer a variety of biometric technologies, such as fingerprint recognition, iris recognition, facial recognition, voice recognition, and more.
HFSECURITY offer solutions for specific industries or applications, such as time and attendance tracking, payment authentication, personal identification, and others.
If you have any specific questions about Chongqing Huifan Technology Co., Ltd.,you can visiting our official website or contacting us directly for more information.
CEO
Mike
CSO
Sienna
CMO
Vicky
CTO
Adam
XCORE AI Algorithm
XCore Magic Cube Smart Analysis Box Ecological algorithms
| Face and Keypoint Detection | Face Recognition | Face attribute analysis |
| Quickly detects faces and marks face coordinates, extracts key points for face alignment including cheeks, eyebrows, eyes, mouth, nose and other five facial features, accurately identifies multiple attribute information, and provides reliable support for face recognition. It can run on multiple platforms at the end and side to achieve efficient, accurate and stable face detection function. | Based on the ai algorithm framework, it supports extraction and analysis of face features in various complex scenes (indoor, outdoor, strong light, low light) to accurately complete face recognition, and reduce the extraction difficulty and release greater computational performance through multiple video stream inference; application scenarios cover retail payment, intelligent security, access control, time and attendance, identity verification, etc. | According to the AI algorithm to calculate the face features and face-related attribute analysis, including gender, age, emotion, etc. |
 |
 |
 |
| Pedestrian attribute analysis | License plate/model detection and recognition | Helmet and other object detection |
| AI algorithm pedestrian detection to obtain high precision recognition of pedestrian attribute information and action, including gender and age, clothing category, clothing color, wearing object, behavior and action, etc., providing rich structured information, which can be used for efficient video material management and accurate marketing. | Through AI algorithm, detect the location of the subject vehicle, license plate (license plate frame 4 vertices) / vehicle brand model recognition, while supporting multiple video stream inference, suitable for park, traffic, parking lot and other scenarios. | Detection of helmets and faces according to pedestrian attribute analysis algorithm, through video structuring to determine whether to wear helmets, support including red, white, yellow, blue, orange helmet recognition training; at the same time the algorithm can be used for the detection and recognition of a variety of objects, the accuracy rate is higher than 95%, effectively improve the safety supervision and management work. |
 |
 |
 |
| Pet identification | Elevator electric car recognition warning | Work uniform recognition |
| AI algorithm can recognize a variety of pet species and support multi-species recognition of a single species; application scenarios are applicable to pet machines, photo-recognition, early childhood science, image content analysis and other scenarios. | Detection and identification of all types of electric vehicles, when the detection of electric vehicles into the elevator, the camera can be directly alarm (sound / flash), and automatically upload the alarm information, live images, video and other data to the cloud platform, the management personnel can receive timely information, view the scene, for timely processing. | Detection and identification of various types of uniforms, in the office or construction site, the camera can directly monitor whether the personnel in it wears the specified clothing, and detects the personnel who are not wearing the specified uniforms and automatically uploads the alarm information, site images and to the cloud platform, the management personnel can receive information, view the site situation and carry out timely processing. |
 |
 |
 |
| Throwing objects from height | Mask / hood recognition | Non-motorized vehicle capture |
| AI algorithm can monitor the aerial throwing event 24 hours a day, can effectively filter trees / flying birds / clouds / wind / rain and snow weather / vibration and other sources of interference, the algorithm accuracy is greater than 90%. | Enter and exit the area according to the provisions of hoods, masks, work shoes, such as non-compliance, the system automatically take pictures and form evidence files, algorithm accuracy greater than 90%. | By identifying the non-motorized vehicles entering the area, it can display the capture picture and capture time when a non-motorized vehicle is detected. |
 |
 |
 |
| Chef’s hat/chef’s uniform recognition | Road damage recognition | Vehicle No Parking |
| By identifying the chefs entering the back kitchen space, when a chef’s hat/chef’s uniform is not detected, it can immediately alert and generate corresponding pictures and video clips. | Real-time recognition of road surface damage, when detecting deep potholes, collapses, cracks or road depressions in the road, immediately alert and generate corresponding pictures and video clips. | Real-time recognition of road no-parking sections and generation of corresponding pictures when illegal parking is detected |
 |
 |
 |
| Warning Line | Person intrusion | Person wandering |
| Real-time identification of prohibited road sections, when the detection of people crossing the border, alarm capture pictures | Real-time identification of each security rights, when found someone illegal entry, alarm capture pictures | Real-time identification of people walking status, when found in the lingering wandering, this person key mark, generate pictures |
 |
 |
 |
| Over the wall | ||
| Real-time recognition of wall status, when found someone illegally over the wall, alarm generation picture | ||
 |
| Pedestrian detection | Pedestrian re-identification |
| Efficient detection and tracking based on pedestrian coordinates, supporting multiple video streams with simultaneous inference, realizing target tracking for high frame rate, low frame rate and ultra-low frame rate, adaptive adjustment of tracking parameters, balancing processing speed and algorithm accuracy, providing support for pedestrian attribute analysis and pedestrian re-identification. | Based on AI algorithm pedestrian detection to obtain its features, structured storage; when need to find, the system will extract the features of the target person, match with the image features already stored in the database and identify the identity of the target task. |
 |
 |
| Crowd density analysis | Passenger flow statistics |
| Using AI algorithm of face recognition and pedestrian re-identification technology to turn "people" into "data", support real-time display of crowd trends in different time periods and crowd gathering area portrait video stream inference; can be applied to scenarios: railway stations, office halls, pedestrian streets etc. | Passenger flow statistics is combined with face/head detection AI algorithm to help stores establish a portrait of customers visiting the store from dimensions such as gender, age, expression, new and old customers, and length of stay; deeply digging into user needs to serve as a basis for adjusting store layout. |
 |
 |
| Fall recognition | Perimeter detection | Employee departure detection |
| Based on the behavior posture recognition technology, it automatically identifies the fall behavior of people in public places, and supports fall recognition in multiple scenes and different backgrounds, which is applicable to the fall warning of the elderly and children in public places. | Based on AI algorithm human body recognition technology, accurate human body detection analysis identification for personnel, to achieve early warning of dangerous areas / protection areas of personnel intrusion detection; can customize the perimeter drawing, support multi-person scenario early warning. | According to the AI algorithm to calculate the face features and face-related attribute analysis, including gender, age, emotion, etc. |
 |
 |
 |
| Playing with cell phones | Smoking | Sleeping-post-detection |
| Based on behavioral posture recognition technology, it automatically identifies cell phone playing behavior and supports multiple scenes and different backgrounds of cell phone playing, which is suitable for early warning of office areas and meetings. | Based on behavior posture recognition technology and smoke alarm behavior, automatic recognition of smoking recognition, and support for multiple scenes, smoking in different contexts, suitable for smoke-free, non-smoking environment alarm and early warning | Based on behavioral posture recognition technology, it automatically identifies sleeping posture and supports sleeping in multiple scenes and different contexts, which is suitable for alarm as well as early warning during work |
 |
 |
 |
| Answer the phone | Fighting | Running |
| Based on behavioral posture recognition technology, automatic identification is during work, and support multiple scenes, sleeping in different contexts, suitable for alarm during work as well as early warning | Human body recognition technology based on AI algorithms for accurate action analysis of people and early warning detection of brawls in dangerous areas/protected areas; | Human body recognition technology based on AI algorithms for accurate action analysis of people for capture; |
 |
 |
 |
Download Fingerprint Scanner Brochure
Customized
If you want to know more about the algorithm, or if you have your own demand scenario, fill out the form below to get a customized solution!
Application Scenarios XCORE
 |
 |
|
Smart Analysis Box Smart Site Application |
||
| HFSECURITY technology smart site solutions, around the construction site most common worker uniform recognition, helmet wear recognition, face recognition, safety perimeter detection, phone / smoking, fall detection, open fire detection, dumper truck, soil pile exposed recognition and a series of sub-scenes specifically launched a general solution, focusing on site safety construction, regulate personnel access, protection equipment safety and other rigid needs. | ||
Solution topology diagram |
||
 |
||
| Real name management for entry and exit | Safety helmet identification | Reflective clothing detection |
 |
 |
 |
| Perimeter intrusion detection | Smoke/smoke detection | Smoking detection |
 |
 |
 |
| Exposed mound identification | Dump truck identification | More Customization |
 |
 |
|
 |  | |
Smart AI oil Application | ||
Due to the special nature of the gas station industry, oil depots and stations often store large amounts of finished fuels to meet sales demand, so how to ensure the safety of personnel and property is of paramount importance. The HFSECURITY smart gas station solution takes gas station safety as the core and digital gas stations as the root to create a one-stop solution for smart and safe gas stations; the solution covers the safety management of service areas and unloading operation areas. The solution, through AI edge computing box + camera and other intelligent identification and analysis technologies, can analyze real-time video content to achieve detection of abnormal information and risk prediction, and enhance the safety coefficient of petrol stations in the most efficient and direct way, targeting the detection of smoke and fire in the operation area, phone call identification, personnel intrusion, staff behavior norms, on and off duty, smoking identification, license plate identification, etc., and carry out the corresponding situation processing, prevention before it happens, and the lightweight deployment also facilitates the implementation of the project. | ||
Solution topology diagram | ||
| Personnel retention | License plate recognition | Static removal |
 |  |  |
| Placement of fire extinguishers | Oil loading and unloading | Vehicle inspection |
 |  |  |
| Call detection | Flame detection | Smoking detection |
 |  |  |
| Passenger flow statistics | Crowd density detection | More customization requirements |
| | |
 |
|
|
Smart Analysis Box Smart Factory Application |
||
Due to the special nature of the gas station industry, oil depots and stations often store large amounts of finished fuels to meet sales demand, so how to ensure the safety of personnel and property is of paramount importance. The HFSECURITY smart gas station solution takes gas station safety as the core and digital gas stations as the root to create a one-stop solution for smart and safe gas stations; the solution covers the safety management of service areas and unloading operation areas. The solution, through AI edge computing box + camera and other intelligent identification and analysis technologies, can analyze real-time video content to achieve detection of abnormal information and risk prediction, and enhance the safety coefficient of petrol stations in the most efficient and direct way, targeting the detection of smoke and fire in the operation area, phone call identification, personnel intrusion, staff behavior norms, on and off duty, smoking identification, license plate identification, etc., and carry out the corresponding situation processing, prevention before it happens, and the lightweight deployment also facilitates the implementation of the project. |
||
Solution topology diagram |
||
 |
||
| Dress Code Testing | Product defect detection | Face Recognition Attendance Management |
 |
 |
 |
| On-duty and off-duty recognition | Production operation specification | Equipment predictive maintenance |
 |
 |
|
