VicarVision develops state of the art solutions and products for computer vision. Plugging a camera into a computer is an easy first step, but how can you make a machine see things? How can algorithms extract meaningful interpretations from a stream of pixels? The technologies we develop aim for vicarious perception. We want our machines to perceive and name the objects and events presented to them through cameras, in the same way that we would; so they can keep an eye on things for us.

VicarVision has a special interest in perceiving people. FaceReader™ is the premier product for online evaluation of the emotional expressions of the human face. It is used in behaviorial research institutes all over the world for studies in e.g. usability and user experience of software systems, food preferences and video conferencing interactions. Back in 1996 our PIRES™ system was the first ‘mugshot’, or forensic portrait analysis system, able to fill in a full police suspect description form; and better than most cops did, actually. BodyReader™ estimates the poses of a human, the articulations of the human body, in real time. GazeTracker™ follows the direction of attention of a person watching a screen, from the images of a standard webcam. AIVOS™ is a generic platform for intelligent video surveillance systems, in which actions and interactions of multiple persons can be analysed.

Over the years, we have also developed vision solutions for other objects than people, such as cars, horses, shoe traces for forensic analysis, and setting classification for evaluating the context of images. SewerViewer™ is a visual analysis system for a sewer crawling robot, able to detect, classify and interpret various abnormalities, cracks and obstructions in a sewer system. We have a foot sole analysis system under development, able to perform a screening on footsole images, for early detection of ulceration.