Intelligent video analytics of air objects in real time

Abstract

Intelligent video analytics is a technology that combines many accurate analytical and approximate numerical methods of automated analysis of the sequence of images coming from video cameras in real time or from archival recordings. Video analytics is implemented in the form of software (software) for working with video content. The software is based on a wide range of mathematical models and methods that allow video monitoring and data mining without direct human involvement. Currently, in video surveillance systems, there are numerous examples of successfully solved problems using video analytics: - recognition of people and transport in order to count their number; - number recognition (on transport, on banknotes, documents, etc.); - detection of events (movement, movement, intersection of permissible lines and boundaries, stay in areas, throwing objects over the fence, etc.); - detection of dangerous situations (crowds, abandoned objects, fires and smoke, etc.); - recognition of dangerous objects, identification of human faces and their search in databases; - analysis of data without the direct participation of people. Extensive use of IP-cameras allows to adequately reflect the real world in a parallel - digital world, in which strict conditions (laws) of stay and behavior of different subjects of this world can be established. Video analytics, without the intervention of individual entities, allows the most effective monitoring of these conditions by different entities and, in the first stage, to issue emergency messages in case of violation. In the next stages, video analytics provides support for decision-making on measures and tools that should be applied to entities that have violated the conditions of stay and behavior, up to their implementation. Airspace monitoring systems use video cameras with rotation, tilt and zoom functions - PTZ cameras, named for their ability to rotate left and right, tilt up and down, zoom and convert images. Rotary cameras perform these actions thanks to a unique combination of pan, tilt and zoom control functions. The overall ability of the PTZ camera to approximate the image consists of the value of digital and optical zooms. Digital zoom uses electronics to enlarge and reduce the image, while optical zoom uses lens movement. The total value of the camera's zoom capability can be calculated by multiplying the digital and optical zoom values. Video analytics of air objects (SO) automates many functions of airspace monitoring, the main of which are: - detection (detection) of all software located in the controlled area of ​​air space; - tracking of selected software; - software type recognition; - forecasting software trajectories; - detection of events related to the behavior (trajectory) of the software. All functions are performed repeatedly, providing continuous refinement of hypotheses about the number, location, type of software and its intentions in the controlled area of ​​air space. Software recognition means a wide range of tasks - from binary classification of software type target / noise to the identification or verification of software on the basis of characteristics. The use of video analytics software in airspace monitoring systems makes it possible to automatically, without human intervention, in the process of video surveillance to solve problems that are usually only possible for humans. This technology is used both to ensure the safety of protected objects and to prevent software from being in a controlled area of ​​airspace. Video analytics software is used to obtain an objective assessment of the effectiveness of airspace monitoring, as it is able to produce continuous and automated collection and analysis of video data, independent of the human factor, and generate reports at the request of the user at any time .