Development of a Mathematical Model for Detecting Moving Objects in Video Streams in Real-Time

The development of mathematical models for detecting moving objects in real-time video streams is a significant task, especially in light of the growing demands for security and process automation. This paper proposes a detection system based on the Faster Region-Based Convolutional Neural Network (...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhazira Mutalova, Anargul Shaushenova, Ardak Nurpeisova, Maral Ongarbayeva, Aidar Ispussinov, Sandugash Bekenova, Zhanar Altynbekova
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10737329/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846162922085023744
author Zhazira Mutalova
Anargul Shaushenova
Ardak Nurpeisova
Maral Ongarbayeva
Aidar Ispussinov
Sandugash Bekenova
Zhanar Altynbekova
author_facet Zhazira Mutalova
Anargul Shaushenova
Ardak Nurpeisova
Maral Ongarbayeva
Aidar Ispussinov
Sandugash Bekenova
Zhanar Altynbekova
author_sort Zhazira Mutalova
collection DOAJ
description The development of mathematical models for detecting moving objects in real-time video streams is a significant task, especially in light of the growing demands for security and process automation. This paper proposes a detection system based on the Faster Region-Based Convolutional Neural Network (Faster R-CNN) model, utilizing various backbone architectures, including Residual Network-50 (ResNet-50), Feature Pyramid Network (FPN), MobileNet Version 3 Large, and Efficient Network-B0 (EfficientNetB0) with a Self-Attention mechanism. The model extracts object features by combining deep neural networks and scaling mechanisms, enabling adaptation to various operating conditions. Experimental results demonstrate that the proposed approach achieves high accuracy, with the MobileNet Version 3 Large model achieving 95.70% accuracy and the Residual Network-50 model reaching 100% accuracy within the first three training cycles (epochs). The Faster Region-Based Convolutional Neural Network model using Efficient Network-B0 with the Self-Attention mechanism reaches 100% accuracy by the third training cycle, maintaining consistent performance throughout the remaining training cycles. The model with the Residual Network-50 and Feature Pyramid Network backbone architecture shows an average loss reduction from 0.0922 in the first training cycle to 0.0102 by the 15th training cycle, confirming its high stability and performance. Future research could focus on optimizing the proposed approach to handle even more complex and dynamic video sequences and improving data processing to reduce computational costs and increase processing speed.
format Article
id doaj-art-a456f819ee964a7bb3fa37ab14c9df5c
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a456f819ee964a7bb3fa37ab14c9df5c2024-11-20T00:01:00ZengIEEEIEEE Access2169-35362024-01-011216923516924610.1109/ACCESS.2024.348778310737329Development of a Mathematical Model for Detecting Moving Objects in Video Streams in Real-TimeZhazira Mutalova0https://orcid.org/0000-0001-9912-5978Anargul Shaushenova1https://orcid.org/0000-0002-3164-3688Ardak Nurpeisova2https://orcid.org/0000-0002-1245-8313Maral Ongarbayeva3Aidar Ispussinov4https://orcid.org/0009-0001-4134-776XSandugash Bekenova5https://orcid.org/0000-0001-7707-5623Zhanar Altynbekova6S. Seifullin Kazakh Agrotechnical Research University, Astana, KazakhstanS. Seifullin Kazakh Agrotechnical Research University, Astana, KazakhstanS. Seifullin Kazakh Agrotechnical Research University, Astana, KazakhstanSherkhan Murtaza International Taraz Institute, Taraz, KazakhstanS. Seifullin Kazakh Agrotechnical Research University, Astana, KazakhstanWest Kazakhstan Agricultural and Technical University named after Zhangir Khan, Uralsk, KazakhstanSherkhan Murtaza International Taraz Institute, Taraz, KazakhstanThe development of mathematical models for detecting moving objects in real-time video streams is a significant task, especially in light of the growing demands for security and process automation. This paper proposes a detection system based on the Faster Region-Based Convolutional Neural Network (Faster R-CNN) model, utilizing various backbone architectures, including Residual Network-50 (ResNet-50), Feature Pyramid Network (FPN), MobileNet Version 3 Large, and Efficient Network-B0 (EfficientNetB0) with a Self-Attention mechanism. The model extracts object features by combining deep neural networks and scaling mechanisms, enabling adaptation to various operating conditions. Experimental results demonstrate that the proposed approach achieves high accuracy, with the MobileNet Version 3 Large model achieving 95.70% accuracy and the Residual Network-50 model reaching 100% accuracy within the first three training cycles (epochs). The Faster Region-Based Convolutional Neural Network model using Efficient Network-B0 with the Self-Attention mechanism reaches 100% accuracy by the third training cycle, maintaining consistent performance throughout the remaining training cycles. The model with the Residual Network-50 and Feature Pyramid Network backbone architecture shows an average loss reduction from 0.0922 in the first training cycle to 0.0102 by the 15th training cycle, confirming its high stability and performance. Future research could focus on optimizing the proposed approach to handle even more complex and dynamic video sequences and improving data processing to reduce computational costs and increase processing speed.https://ieeexplore.ieee.org/document/10737329/Real-time object detectionvideo stream processingface embeddingsmulti-threaded recognitionmachine learningobject classification
spellingShingle Zhazira Mutalova
Anargul Shaushenova
Ardak Nurpeisova
Maral Ongarbayeva
Aidar Ispussinov
Sandugash Bekenova
Zhanar Altynbekova
Development of a Mathematical Model for Detecting Moving Objects in Video Streams in Real-Time
IEEE Access
Real-time object detection
video stream processing
face embeddings
multi-threaded recognition
machine learning
object classification
title Development of a Mathematical Model for Detecting Moving Objects in Video Streams in Real-Time
title_full Development of a Mathematical Model for Detecting Moving Objects in Video Streams in Real-Time
title_fullStr Development of a Mathematical Model for Detecting Moving Objects in Video Streams in Real-Time
title_full_unstemmed Development of a Mathematical Model for Detecting Moving Objects in Video Streams in Real-Time
title_short Development of a Mathematical Model for Detecting Moving Objects in Video Streams in Real-Time
title_sort development of a mathematical model for detecting moving objects in video streams in real time
topic Real-time object detection
video stream processing
face embeddings
multi-threaded recognition
machine learning
object classification
url https://ieeexplore.ieee.org/document/10737329/
work_keys_str_mv AT zhaziramutalova developmentofamathematicalmodelfordetectingmovingobjectsinvideostreamsinrealtime
AT anargulshaushenova developmentofamathematicalmodelfordetectingmovingobjectsinvideostreamsinrealtime
AT ardaknurpeisova developmentofamathematicalmodelfordetectingmovingobjectsinvideostreamsinrealtime
AT maralongarbayeva developmentofamathematicalmodelfordetectingmovingobjectsinvideostreamsinrealtime
AT aidarispussinov developmentofamathematicalmodelfordetectingmovingobjectsinvideostreamsinrealtime
AT sandugashbekenova developmentofamathematicalmodelfordetectingmovingobjectsinvideostreamsinrealtime
AT zhanaraltynbekova developmentofamathematicalmodelfordetectingmovingobjectsinvideostreamsinrealtime