• SentiVeillance Server


SentiVeillance Server is a ready-to-use software for easy integration of biometric face identificationvehicle and pedestrian classification and tracking, as well as automatic license plate recognition into operating video management systems (VMS). The software analyzes live video streams, which are served by a VMS from surveillance cameras.
The list of possible uses includes law enforcement, traffic monitoring, security, attendance control, visitor counting and other applications.

SentiVeillance Server是一个现成的软件,可以方便地集成各种识别技术如人脸识别、 车辆和行人分类和跟踪,以及自动车牌识别等,构建智能化视频管理系统(VMS)。该软件分析由VMS系统中的监控摄像机提供的实时视频流。



  • Ready-to-use facial identification software for surveillance systems.
  • Compatible with major video management systems.
  • Biometric persons identification and tracking.
  • Pedestrians and vehicles tracking and classification.
  • Automated license plate recognition (ALPR) for moving vehicles.
  • Real-time watchlist check with automatic event triggering, logging and reporting.
  • Search for events in a timeframe based on person ID, gender or age.
  • Up to 10 video streams from multiple VMS are analyzed in parallel by each SentiVeillance Server.


  • 适用于监视系统的现成面部识别软件。
  • 与主流视频管理系统(VMS)全兼容。
  • 生物识别人员识别和跟踪。
  • 行人和车辆的跟踪和分类。
  • 对移动中车辆的自动车牌识别(ALPR)。
  • 实时监视特殊名单检查,自动事件触发,记录和报告.
  • 搜索时间范围内的事件,个人身份、性别或年龄。
  • 每个SentiVeillance Server可并行分析来自多个VMS的多达10个视频流。

A video management system (VMS) usually provides only motion detection functionality and can help to filter out parts of video from surveillance cameras when there is no movement. SentiVeillance Server software enhances existing VMS with these features and functions:

  • The ready-to-use SentiVeillance Server software needs only configuration via browser-based interface for connecting an operating VMS.
  • SentiVeillance Server is compatible with Milestone XProtect VMS and Luxriot Evo S and Evo Global video management systems. Each running SentiVeillance Server can connect to multiple VMS and receive more than one video stream from each of them.
  • Biometric persons identification and tracking is based on proprietary facial detection and recognition algorithm, which is based on deep neural networks. The face identification technology is also used in other Neurotechnology products, which have millions of end-user deploymentsworldwide. The algorithm accuracy and performance has been tested in the NIST Face Recognition Vendor Test (FRVT).
  • Vehicle or pedestrian detection and classification is performed for moving and static objects in the scene. The algorithm can separate these traffic subjects: pedestrianscarsbussestrucks and bikes. Also, it is possible to estimate color and movement direction for the detected objects.
  • Automated license plate recognition (ALPR) allows to read vehicle's registration numbers after detecting them. The algorithm can process videos from traffic cameras and read license plates from multiple moving vehicles at the same time.
  • SentiVeillance Server analyzes all video streams received from connected VMS in parallel and performs detection and recognition in real-time. All watch list match events trigger alerts, which are sent back to corresponding VMS and reported to an operator, as well as stored in the event log for further reference.
  • Surveillance system operators can perform search in the events log. Search requests are made via VMS user interface and sent to the connected SentiVeillance Server, which returns the search results back. The operator can play back surveillance footage at the timestamps, which are specified by the search results, and perform further actions. The search can be performed within certain timeframe. The search criteria can be one or more person IDs from the watch list, or persons, who belong to specified age or gender group. Finally, operators can review all events with unknown persons.
  • Each SentiVeillance Server can analyze up to 10 video streams in parallel. Several SentiVeillance Servers can connect to the same VMS, as well as several VMS can be connected to the same SentVeillance Server, meaning that SentiVeillance Server software can be integrated into a system with any number of surveillance cameras.

视频管理系统(VMS)通常只提供动态检测功能,在没有移动目标的情况下,可以帮助过滤掉监控摄像机中的部分视频。SentiVeillance Sever软件增强现有的VMS系统,具有以下特点和功能:

  • 现成的SentiVeillance Server软件只需要通过基于浏览器的接口即可用于连接操作VMS。
  • SentiVeillance Server 兼容Milestone XProtect VMSLuxriot Evo S and Evo Global视频管理系统。每个正在运行的SentiVeillance Server都可以连接到多个VMS并接收来自每个VMS的多个视频流。
  • 基于专有的人脸检测和识别算法的人员识别和跟踪,我们基于深度神经网络的人脸识别技术也在其他产品得到应用。我们在全世界有数以百万计的最终用户部署。算法准确度性能已经多种权威测试所证明,比如NIST人脸识别供应商测试(FRVT).
  • 对场景中的运动和静态物体进行车辆或行人的检测和分类。该算法可以将这些交通主体分开:行人汽车客车卡车自行车。而且,可以对检测到的对象估计其颜色运动方向
  • 自动车牌识别(ALPR)允许在检测到车辆登记号码后读取它们。该算法可以处理来自交通摄像头的多辆移动车辆图像,并同时读取它们的车牌。
  • SentiVeillance Server从连接的VMS接收和并行分析所有视频流,进行实时检测和识别。全特殊人群表及匹配事件触发警报,这些警报被发送回相应的VMS并报告给操作员,并存储在事件日志中以供进一步参考。
  • 监视系统操作员可以在事件日志中执行搜索。搜索请求通过VMS用户界面发出,并发送到连接的SentiVeillance Server,该服务器返回搜索结果。操作员可以在搜索结果指定的时间戳上播放监视录像,并执行进一步的操作。搜索可以在特定的时间范围内执行。搜索标准可以是监视列表中的一个或多个人ID,或者属于指定年龄或性别组的人。最后,操作员可以检查所有事件与未知的人。
  • 每个SentiVeillance Server可以并行分析到多达10个视频流。多个SentiVeillance  Server可以连接到同一个VMS,多个VMS也可以连接到同一个SentVeillance Server,这意味着SentiVeillance Server软件可以集成到一个摄像头数量不受限制的VMS系统中。