Face detector

Viinex offers face detection feature. Face detector provides technical capability of “filtering” video data on the edge. It allows to provide already processed data for face detection algorithms in cloud service from various vendors or in your data center, optimize interaction with these remote systems using thin communication channels and minimize traffic (transferring from the edge frames measured in kilobytes, instead of video streams of megabits per second which also has to be decompressed on the data center side).

The implementation is divided into two modules in Viinex: there is an “engine” which processes the still images, and a “video analytics module”, which presents the sequence of frames to the engine until a result is produced. Both components are available from the HTTP API.

Face detection performed on still images

One can try the engine on an arbitrary image using the CURL utility to issue the HTTP POST requests to Viinex (an image goes in the HTTP request body).

POST http://servername:port/v1/svc/facedetN

Detection result is returned as a JSON structure in the HTTP response body.

Face detection performed on video

Managed mode face detection (HTTP request)

Alternatively, one can associate the face detection video analytics module with a camera, in order to detect the faces on video upon request, — in this case Viinex takes care about the media data, while the client software just gets the face detection results — the geometry of faces and the timestamp of a frame where the faces were found.

GET http://servername:port/v1/svc/faceDetCamN

When the faces are detected on video, the analytics module stores corresponding frames in a buffer in memory, so that the client software can get them later, as snapshots. As always, the whole frame is available as a snapshot as well as the region(s) of interest containing the face(s) just detected.

The video source attached to the face detection video analytics module could be an IP camera or an RTSP video source, as well as USB camera that produces uncompressed video.

One video analytics module can be linked with multiple cameras (of various types) to perform the facial detection on the same scene viewing it from different angles. With Viinex a client software can do it in a single HTTP API request

Automated mode face detection (WebSocket)

Along with face detector management via HTTP request a freeflow mode can be used, i.e. integrating application can subscribe to WebSocket to receive detection updates in real time. The video source linked to the face detection video analytics module could be an IP camera or an RTSP video source, as well as a USB camera that produces uncompressed video stream.