Video Analysis

The ‘visual channel’ within a video signal contains a wealth of information that can be extracted to help form an index of the video. Examples of visual analysis include keyframing, face detection and recognition, on-screen text recognition, and more. Typically, a visual analysis is restricted to a narrow problem domain because image understanding is a very difficult problem to solve in the generic sense. As a result, Autonomy Virage employs a Media Analysis framework for incorporating modular algorithms for visual analysis, while still maintaining real-time performance criteria.

Scene Analysis

Autonomy Virage is able to extract content by "watching" video and identifying key objects within the image. This technology also recognizes changes in the scene, enabling it to extract more information from the video file than can be indexed manually. This includes recognizing key objects such as a house, a person, or a sequence of rapidly changing events. Combined with Intelligent Keyframing, Scene Analysis can create storyboards automatically, giving users an unprecedented level of control over their video assets.

Video Motion Detect

VMD is the most basic form of recognition which identifies movement of objects within a specified field of view, for example, a person entering a restricted area. Non Motion Detect (NMD) has the ability to recognize static objects within a scene such as unattended baggage in an airport. Users may set parameters to define the types of object which should be detected and also define the length of time an object should be static in order to be classed as a stationary object.

Object Sizing

Detecting the size of an object or a group of objects in a field of view alerts surveillance staff to situations which may require a response. For example, where iSAS is used for monitoring traffic flow, if a traffic jam is detected, surveillance staff can be alerted immediately and if necessary, an additional lane could be opened to ease congestion.

Object Tracking

In addition to identifying objects, Autonomy Virage can track objects entirely automatically between multiple cameras. While an object remains in a field of view, it is tracked automatically using the coordinate information to control a Pan Tilt Zoom (PTZ) camera.

Object Counting

By automatically categorizing identified objects into known types, Autonomy Virage can generate counts for different categories. Multiple counts can also be configured such as the number of cars entering a car park and the number of cars leaving simultaneously.

Facial Identification

Autonomy Virage’s Facial Identification plug-in provides automatic real-time detection and identification of faces that appear within the video and can compare these to a database of known individuals. Facial recognition techniques are often used for example where suspects need to be identified at a distance and/or non-cooperatively. However, 2D face recognition has always had fundamental limitations with regard to posture, expression and lighting. Autonomy Virage employ superior three-dimensional recognition techniques rather than the traditional 2D facial matching process for optimum performance.

Optical Character Recognition

Autonomy Virage’s Optical Character Recognition (OCR) plug-in provides automatic real-time detection and identification of characters and numbers that appear in the video. The plug-in configuration settings allow you to optimize its operation in a variety of ways, including definition of regions of interest, contrast settings (light-on-dark, dark-on-light), and lexicon options. For example, license and number plates can be recognized in conjunction with ANPR applications. Full integration with multiple databases and the ability to correlate recorded number plates with other data, such as stolen vehicle registers, traffic and law enforcement records, credit card transaction reports and customer records place Autonomy Virage's OCR capabilities way beyond traditional recognition systems.