Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Article . 2022
License: CC BY
Data sources: Datacite
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Article . 2022
License: CC BY
Data sources: ZENODO
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Article . 2022
License: CC BY
Data sources: Datacite
versions View all 2 versions
addClaim

DEVELOPMENT AND SOFTWARE IMPLEMENTATION OF ALGORITHMS FOR DETECTING ABNORMAL HUMAN BEHAVIOR FOR VIDEO SURVEILLANCE SYSTEMS

Authors: Amangeldiev, A.A.;

DEVELOPMENT AND SOFTWARE IMPLEMENTATION OF ALGORITHMS FOR DETECTING ABNORMAL HUMAN BEHAVIOR FOR VIDEO SURVEILLANCE SYSTEMS

Abstract

Abstract With the rapid growth in the volume of video data, there is an increasing need not only to recognize objects and their behavior, but, in particular, to detect rare, interesting cases of unusual objects or suspicious behavior in a large volume of ordinary data. The detection of such deviations in video recordings is crucial for various applications, ranging from automatic quality control to visual observation. Significant events of interest in long video sequences, such as surveillance footage, often have an extremely low probability of occurrence. Thus, manual detection of such events or anomalies is a very painstaking job that often requires more manpower. This caused the need for automatic detection and segmentation of sequences of interest. However, modern technology requires huge efforts to configure each video stream before deploying the video analysis process, even though these events are based on some predefined heuristics, which makes it difficult to generalize the detection model for various surveillance scenes. How to introduce a new structure for the presentation of video data using a set of common functions that are automatically derived from a long video material using a deep learning approach? Аннотация С быстрым ростом объема видеоданных возрастает потребность не только в распознавании объектов и их поведения, но, в частности, в обнаружении редких, интересных случаев необычных объектов или подозрительного поведения в большом объеме обычных данных. Обнаружение таких отклонений в видеозаписях имеет решающее значение для различных приложений, начиная от автоматического контроля качества и заканчивая визуальным наблюдением. Значимые события, представляющие интерес в длинных видеопоследовательностях, таких как кадры наблюдения, часто имеют крайне низкую вероятность наступления. Таким образом, ручное обнаружение таких событий или аномалий - это очень кропотливая работа, которая часто требует больше рабочей силы. Это вызвало необходимость в автоматическом обнаружении и сегментации интересующих последовательностей. Однако современная технология требует огромных усилий по настройке каждого видеопотока до развертывания процесса анализа видео, даже при этом эти события основаны на некоторых предопределенных эвристиках, что затрудняет обобщение модели обнаружения для различных сцен наблюдения. Как представить новую структуру для представления видеоданных с помощью набора общих функций, которые автоматически выводятся из длинного видеоматериала с помощью подхода глубокого обучения?

Список литературы: 1. Адам А., Ривлин Э., Шимшони И., Рейниц Д. Надежное обнаружение необычных событий в реальном времени с использованием нескольких мониторов с фиксированным местоположением. IEEE Transactions по анализу шаблонов и машинному интеллекту. — 2008. С, 505-515. 2. Хасан М., Чой Дж., Нейман Дж., Рой-Чоудхури А.К., Дэвис Л.С. Изучение временной регулярности в видеопоследовательностях. 2016. С. 733-742. 3. Карпати А., Тодеричи Г., Шетти С., Леунг Т., Суктханкар Р., Фей-Фей Л. Крупномасштабная классификация видео с помощью сверточных нейронных сетей. 2014. С. 1725-1732. 4. КРедди В., Сандерсон К., Ловелл Б.К. Обнаружение аномалий в многолюдных сценах. 2011. С. 55-61.

Related Organizations
Keywords

абнормальной, детект, анализ видео, сегментация, автокодировщик, abnormal, detection, video analysis, segmentation, auto encoder

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    download downloads 4
  • 4
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
4
Green