Journal influence
Higher Attestation Commission (VAK) - К1 quartile
Russian Science Citation Index (RSCI)
Bookmark
Next issue
№3
Publication date:
16 September 2025
The algorithm for recognizing situations in a distributed video surveillance system
Date of submission article: 07.09.2017
UDC: 004.93`1
The article was published in issue no. № 2, 2018 [ pp. 368-373 ]Abstract:CCTV systems are the most important means for preventing and timely handling of contingencies, such as crimes, emergency situations. A big number of cameras and a large control area makes it necessary to introduce video analytics to recognize dangerous situations. In this case it is necessary to take into account the data from a number of video cameras both for detecting a motion path of a recognized object and for increasing recognition reliability. The article proposes an algorithm for recognizing emergencies for a distributed video surveillance system based on stochastic grammars. Recognition of a situation occurs at 3 levels: images are recognized at the lower level, events are recognized at the average level, and situations are recognized at the top. To reduce the system response time, it is proposed to use a multi-agent architecture that allows distributing the load between intelligent cameras. Data exchange occurs only between nearby nodes, so network traffic reduces. The use of a large number of cameras involves zones controlled by several nodes. Combination of detection results from several cameras makes it possible to increase the estimate reliability. However, it is required to know the mutual arrangement of chambers and the angles of their turns. The article suggests some methods for automatic calibration of cameras in a distributed video surveillance system, ways of combining images from different cameras, in particular, based on speed rate vectors of objects. Taking into account certain features of a distributed video surveillance system, there is a developed algorithm for recognizing emergencies for an intelligent surveillance camera. Each camera generates probable situations based on previously recognized events. When a threshold value of probabilistic evaluation of the detection result is exceeded, its refinement is carried out in the process of interaction with neighboring nodes.
Аннотация:Системы видеонаблюдения являются важнейшим средством для предотвращения нештатных ситуаций, таких как преступления, аварийные ситуации. Большое количество камер и значительная площадь зоны контроля обусловливают необходимость внедрения видеоаналитики для распознавания опасных ситуаций. При этом нужно учитывать данные с множества видеокамер как для детектирования траектории движения распознаваемого объекта, так и для повышения достоверности распознавания. В статье предлагается алгоритм распознавания нештатных ситуаций для распределенной системы видеонаблюдения, основанной на стохастических грамматиках. Распознавание ситуации происходит на трех уровнях: нижнем – распознаются образы, среднем – события и верхнем – ситуации. Для снижения времени отклика системы предлагается использовать многоагентную архитектуру, позволяющую распределять нагрузку между интеллектуальными камерами. Уменьшение сетевого трафика достигается тем, что обмен данными происходит только между близлежащими узлами. Использование большого количества видеокамер предполагает наличие зон, контролируемых несколькими узлами. Совмещение результатов детектирования нескольких камер позволяет повысить оценку достоверности, но для этого требуется знать взаимное расположение камер и углов их поворотов. В статье предложены методы для автоматической калибровки камер распределенной системы видеонаблюдения, способы совмещения образов на разных камерах, в частности, на основе векторов скорости движения объектов. С учетом определенных особенностей распределенной системы видеонаблюдения разработан алгоритм распознавания нештатных ситуаций для интеллектуальной камеры видеонаблюдения. Каждая камера генерирует вероятные ситуации на основе ранее распознанных событий. При превышении порогового значения вероятностной оценки результата детектирования осуществляется его уточнение в процессе взаимодействия с соседними узлами.
Authors: A.Yu. Kruchinin (kruchinin-al@mail.ru) - Orenburg State University (Associate Professor), Orenburg, Russia, Ph.D, D.V. Kolmykov (malin.chyn@gmail.com) - Orenburg State University, Orenburg, Russia, R.R. Galimov (rin-galimov@yandex.ru) - Orenburg State University (Associate Professor), Orenburg, Russia, Ph.D | |
Keywords: distributed video surveillance system, contingency detection, multiagents systems |
|
Page views: 10541 |
PDF version article Full issue in PDF (19.46Mb) |
Алгоритм распознавания ситуаций в распределенной системе видеонаблюдения
DOI: 10.15827/0236-235X.122.368-373
Date of submission article: 07.09.2017
UDC: 004.93`1
The article was published in issue no. № 2, 2018. [ pp. 368-373 ]
CCTV systems are the most important means for preventing and timely handling of contingencies, such as crimes, emergency situations. A big number of cameras and a large control area makes it necessary to introduce video analytics to recognize dangerous situations. In this case it is necessary to take into account the data from a number of video cameras both for detecting a motion path of a recognized object and for increasing recognition reliability.
The article proposes an algorithm for recognizing emergencies for a distributed video surveillance system based on stochastic grammars. Recognition of a situation occurs at 3 levels: images are recognized at the lower level, events are recognized at the average level, and situations are recognized at the top. To reduce the system response time, it is proposed to use a multi-agent architecture that allows distributing the load between intelligent cameras. Data exchange occurs only between nearby nodes, so network traffic reduces.
The use of a large number of cameras involves zones controlled by several nodes. Combination of detection results from several cameras makes it possible to increase the estimate reliability. However, it is required to know the mutual arrangement of chambers and the angles of their turns. The article suggests some methods for automatic calibration of cameras in a distributed video surveillance system, ways of combining images from different cameras, in particular, based on speed rate vectors of objects.
Taking into account certain features of a distributed video surveillance system, there is a developed algorithm for recognizing emergencies for an intelligent surveillance camera. Each camera generates probable situations based on previously recognized events. When a threshold value of probabilistic evaluation of the detection result is exceeded, its refinement is carried out in the process of interaction with neighboring nodes.
A.Yu. Kruchinin (kruchinin-al@mail.ru) - Orenburg State University (Associate Professor), Orenburg, Russia, Ph.D, D.V. Kolmykov (malin.chyn@gmail.com) - Orenburg State University, Orenburg, Russia, R.R. Galimov (rin-galimov@yandex.ru) - Orenburg State University (Associate Professor), Orenburg, Russia, Ph.D
Ссылка скопирована!
Permanent link: http://swsys.ru/index.php?page=article&id=4469&lang=&lang=en&like=1 |
Print version Full issue in PDF (19.46Mb) |
The article was published in issue no. № 2, 2018 [ pp. 368-373 ] |
The article was published in issue no. № 2, 2018. [ pp. 368-373 ]
Perhaps, you might be interested in the following articles of similar topics:Perhaps, you might be interested in the following articles of similar topics:
- Синергетика информационно-когнитивного взаимодействия в интеллектуальных робототехнических системах с дистанционным обменом знаниями
- Агентно-ориентированные модели, методика и средства разработки совместимых решателей задач интеллектуальных систем
- Кроссплатформенная поисковая мультиагентная система
- Ресурсно-целевые сети
- Проблема специализации в иерархических обучающихся системах управления на примере задачи фуражировки
Back to the list of articles