Development of a combined motion detection method for an intelligent video surveillance system

E.E. Istratova, E.A. Bukhamer, I.N. Tomilov

Abstract


The article presents the results of the development of a motion detection method taking into account the filtering of noise in the frame. Based on the analysis of literature sources, a combined approach to motion detection based on classical and heuristic algorithms was proposed. In the course of the work, both classical approaches to motion detection in video sequences and existing ready-to-use solutions in the field of intelligent video surveillance systems were considered. As a result, a motion detection algorithm was developed that solves the problem of a large number of false positives. Distinctive features of the developed algorithm are resistance to noise and minor movements in frames of video sequences, as well as the ability to easily adapt to various changes in the motion detection environment. The main advantage of the proposed modification of the motion detection algorithm is a sufficiently high processing speed of each frame for a video analytics system in real time.

Full Text:

PDF (Russian)

References


Obukhova, N. A. 2008. Metody` videonablyudeniya, segmentaczii i soprovozhdeniya dvizhushhikhsya ob`ektov [Methods of video surveillance, segmentation and tracking of moving objects]. D.Sc. Diss. Spb. 32 p.

Lokteev, A. S. 2017. Algoritm vy`deleniya ob`ektov na osnove vy`chitaniya fona [Algorithm for object selection based on background subtraction]. Materialy` XKhII Vserossijskoj nauchno-tekhnicheskoj konferenczii studentov, molody`kh ucheny`kh i speczialistov “Novy`e informaczionny`e tekhnologii v nauchny`kh issledovaniyakh” [Materials of the XXII All-Russian scientific and technical conference of students, young scientists and specialists “New information technologies in scientific research”]. Ryazan. 219-220.

Snegireva, M. A., Aliferova, A. I., Aksenov, S. V. 2019. Czifrovaya obrabotka videoizobrazhenij. Metody` vy`chitaniya fona [Digital processing of video images. Background Subtraction Methods]. Sbornik trudov XI Mezhdunarodnoj nauchno-prakticheskoj konferenczii studentov, aspirantov i molody`kh ucheny`kh “Molodezh` i sovremenny`e informaczionny`e tekhnologii” [Proceedings of the XI International Scientific and Practical Conference of Students, Postgraduates and Young Scientists “Youth and Modern Information Technologies”]. Tomsk. 461-463.

Meng, F., Yuan, G., Lv, S. An overview on trajectory outlier detection // Artif Intell Rev 52, 2437–2456 (2019). Available at: https://doi.org/10.1007/s10462-018-9619-1 (accessed August 08, 2021).

Verdant, A., Villard, P., Dupret, A. Three novell analog-domain algorithms for motion detection in video surveillance // Image Video Proc. 2011, 698914 (2011). Available at: https://doi.org/10.1155/2011/698914 (accessed August 08, 2021).

Grigoriev, A. I., Kovalenko, V. V., Pankratov, L. V. 2020. Problemy` vy`chitaniya fona pri individual`nom dozimetricheskom kontrole i radiaczionnom kontrole na otkry`toj mestnosti [Background subtraction problems in individual dosimetric control and radiation control in open areas]. Sbornik tezisov konferenczii “Radiokhimicheskie metody` issledovaniya” [Collection of conference abstracts “Radiochemical research methods”]. St. Petersburg. 37-38.

Viola, P., Jones, M. J. 2014. Robust real-time face detection. International Journal of Computer Vision. Vol. 57. No. 2: 137-154.

Spitsyn, V. G., Bolotova, Y. A. 2016. Raspoznavanie licz na osnove metoda glavny`kh komponent s primeneniem vejvlet-deskriptorov Khaara i Dobeshi [Face recognition based on the method of principal components using Haar and Daubechies wavelet descriptors]. Nauchnaya vizualizacziya [Scientific visualization]. 5:103-112.

Varkonyi-Kóczy, A. R. New advances in digital image processing // Memetic Comp. 2, 283-304 (2020). Available at: https://doi.org/10.1007/s12293-010-0046-3 (accessed August 08, 2021).

Belykh, E.A. 2017. Obuchenie kaskadov Khaara [Training of Haar cascades]. Vestnik Sy`kty`vkarskogo universiteta. Seriya: Matematika. Mekhanika. Informatika [Bulletin of the Syktyvkar University. Series: Mathematics. Mechanics. Computer science]. 1(22): 42-54.

Abbas, Q., Ibrahim, M. E., Jaffar, M. A. A comprehensive review of recent advances on deep vision systems // Artif Intell Rev 52, 39–76 (2019). Available at: https://doi.org/10.107/s10462-018-9633-3 (accessed August 08, 2021).

Molina-Cabello, M. A., García-González, J., Luque-Baena, R. M. The effect of downsampling – upsampling strategy on foreground detection algorithms // Artif Intell Rev 53, 4935–4965 (2020). Available at: https://doi.org/10.1007/s10462-020-09811-y (accessed August 08, 2021).

Kolesnikov, R. S., Belov, Y. S. 2018. Tekhnologiya gistogramm napravlenny`kh gradientov (HOG) v zadache detektirovaniya ob`ektov [The technology of histograms of directional gradients (HOG) in the problem of detecting objects]. Sbornik statej Mezhdunarodnoj nauchno-prakticheskoj konferenczii “Nauchny`e issledovaniya v oblasti tekhnicheskikh i tekhnologicheskikh sistem” [Collection of articles of the International Scientific and Practical Conference “Research in the field of technical and technological systems”]. Kazan. 127-131.

Klyuev, V. V. 2019. Obnaruzhenie ob`ektov na izobrazheniyakh s pomoshh`yu gistogrammy` napravlenny`kh gradientov [Detection of objects in images using a histogram of directional gradients]. Alleya nauki [Alley of Science]. Vol. 2. No. 2 (29):913-917.

Bukhamer, E. A., Tomilov, I. N., Istratova, E. E. 2021. Programma dlya raspoznavaniya licz na vstraivaemy`kh platformakh s ogranichennoj vy`chislitel`noj moshhnost`yu [Face recognition software for embedded platforms with limited computing power]. Certificate of registration of the computer program RF No. 2021615215


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162