Xnap Box
Face / Object Detection Edge Device Make your video surveillance camera smart enough to see human face/body & vehicle Xnap Box processes video from any standard 1080p RTSP H.264 / HTTP MJPEG IP camera / MJPEG AVI File Your surveillance camera is now a smart camera – and more. Without significant wiring changes with your current surveillance camera and NVR system, XnapTM Box reads H. 264/MJPEG video stream or USB file source (FAT32/exFAT) of your IP or USB cameras, decode it and detect and track all faces/object visible in video frames at 20fps (or more), and crop all faces/objects out of background, and send face stream based on quality criteria in HTTP protocol alongside with Tracker ID and other metadata to enable real-time identification or post- event analysis and / or identification. Xnap Box is designed for seamless integration with third-party face recognition system to form large-scale surveillance system with automatic face and/or object recognition. Product comes with well- documented sample codes (on GitHub) and email support service to enable software developer to integrate the output of Xnap Box with their existing surveillance system. Current, Xnap Box data grabber SDK come with 3 different favours: Java, Python, and .NET (c#).
Process RTSP H.264 / MJPEG stream
Each Xnap™ Box processes one RTSP H.264 / MJPEG video stream over IP network (wired Ethernet or Wifi), USB camera, or MJPEG AVI USB File sources on FAT32 thumb drive
Sample Selection
Built-in face tracking and face sample selection: each person appearance will be tracked and assigned with Tracker ID: an unique ID sticky throughout the life cycle of the given face. No. of image images to be exported can be configurable based on sharpness/face size/sample parameters
Built-in ONVIF camera discovery tool
To simplify configuration when connecting ONVIF compliant camera by built-in video source URL discovery tool.
1080p 2MP support
Support up to frame size 1920×1080 pixel with precise resolution auto-detection
LiveView Export
Export of face-annotated “Live View” to assist configuration or for display on application (overlay sharpness & Tracker ID values)
Face Stream Export
Export MJPEG face/object streams, alongside with meta-data, such as timestamp & Tracker ID, through HTTP protocol by default
Fast reliable face finder
Near real-time face detection algorithm using field trained deep learning technology
Built-in object colour detection
Built-in object colour detection to provide dominant colour image of pedestrian/vehicle (meta-data to be sent via HTTP)
NTP time synchronization
NTP support for time synchronization to ensure precise (up to micro-second level) timestamp with all captured images
Detect multiple faces
Detect multiple (up to 12) faces and objects with size range from 72 to 1200 pixels in 1080p (2 mega pixel) frame
Soft AP mode support
802.11n Soft-AP mode support to allow web-based administration from any PC / smartphone / tablet with a standard web browser.
Detailed System Status
provide detailed system operating status of Xnap Box
Included in the Box:
Requires:
Specification
