Research Article

Multi-Object Detection for Real-time Video Surveillance Systems

Authors

  • Fatemeh Rasoulpour * * Department of Computer Engineering and Mathematics, Morvarid Intelligent Industrial Systems Research Group, Tehran, Iran.
  • Milos Milovancevic Department of Mechanical Engineering, University of Nis, Serbia.

https://doi.org/10.48314/ceti.v1i1.21

Abstract

Video surveillance systems play a crucial role in modern security, with real-time applications becoming increasingly important across various sectors. This paper proposes a novel method for detecting moving objects in real time using Convolutional Neural Networks (CNNs) combined with Gaussian Mixture Modeling (GMM) for background subtraction. The system processes video sequences, converting them into frames where moving objects are distinguished from the background. GMM is used to model the background, while CNNs extracts local optimal features to enhance object tracking accuracy. This method is particularly effective for applications such as operational robotics and military surveillance, which require real-time mobile detection systems. The proposed system was tested using custom video sequences, demonstrating significant improvements in object detection accuracy and reliability even in challenging conditions such as low-light environments. The results show improved performance in tracking moving objects, with the system successfully reducing noise and maintaining detection precision.

Keywords

Real-time video surveillance Multi-object detection Convolutional neural networks Gaussian mixture model Background subtraction Mobile surveillance systems Video sequence processing Real-time detection Low-light object detection
References (22)
  1. [1] Thenmozhi, T., & Kalpana, A. M. (2020). Retracted: Adaptive motion estimation and sequential outline separation based moving object detection in video surveillance system, 76. https://doi.org/10.1016/j.micpro.2020.103084

  2. [2] Sengar, S. S., & Mukhopadhyay, S. (2020). Moving object detection using statistical background subtraction in wavelet compressed domain. Multimedia tools and applications, 79(9), 5919–5940. https://doi.org/10.1007/s11042-019-08506-z

  3. [3] Chauhan, A. K., & Krishan, P. (2013). Moving object tracking using gaussian mixture model and optical flow. International journal of advanced research in computer science and software engineering, 3(4), 243–246. https://api.semanticscholar.org/CorpusID:17721082

  4. [4] Mangal, S., & Kumar, A. (2017). Real time moving object detection for video surveillance based on improved GMM. International journal of advanced technology and engineering exploration, 4(26), 17. http://dx.doi.org/10.19101/IJATEE.2017.426004

  5. [5] Elhoseny, M. (2020). Multi-object detection and tracking (MODT) machine learning model for real-time video surveillance systems. Circuits, systems, and signal processing, 39(2), 611–630. https://doi.org/10.1007/s00034-019-01234-7

Article Metrics

How to Cite

Rasoulpour *, F., & Milovancevic, M. (2024). Multi-Object Detection for Real-time Video Surveillance Systems. Computational Engineering and Technology Innovations, 1(1), 11-24. https://doi.org/10.48314/ceti.v1i1.21

Similar Articles

1-10 of 71

You may also start an advanced similarity search for this article.