Wyszukiwanie zaawansowane ?

Obiekt

AI-based Violent Incident Detection in Surveillance Videos to Enhance Public Safety, Journal of Telecommunications and Information Technology, 2025, nr 4
Pobierz

Tytuł: AI-based Violent Incident Detection in Surveillance Videos to Enhance Public Safety, Journal of Telecommunications and Information Technology, 2025, nr 4

Autor:

Merit, Khaled ; Beladgham, Mohammed

Data wydania:

2025, nr 4

Typ zasobu:

artykuł

Tytuł publikacji grupowej:

2025, nr 4, JTIT-artykuły

Opis:

kwartalnik

Abstrakt:

Acts of violence may occur at any moment, even in densely populated areas, making it important to monitor human activities to ensure public safety. Although surveillance cameras are capable of detecting the activity of people, around-the-clock monitoring still requires human support. As such, an automated framework capable of detecting violence, issuing early alerts, and facilitating quick reactions is required. However, automation of the entire process is challenging due to issues such as low video resolution and blind spots. This study focuses on detecting acts of violence using three video data sets (movies, hockey game and crowd) by applying and comparing advanced ResNet architectures (ResNet50V2, ResNet101V2, ResNet152V2) with the use of the bidirectional gated recurrent unit (BiGRU) algorithm. Spatial features of each video frame sequence are extracted using these pre-trained deep transfer learning models and classified by means of an optimized BiGRU model. The experimental results were then compared with those achieved by wavelet feature extraction approaches and other classification models, including CNN and LSTM. Such an analysis indicates that the combination of ResNet152V2 and BiGRU offers decent performance in terms of higher accuracy, recall, precision, and F1 score across the different datasets. Furthermore, the results indicate that deeper ResNet models significantly improve overall performance of the model in terms of violence detection scores, relative to shallower ResNet models. ResNet152V2 was found to be the ultimate model across the datasets when it comes to a high degree of accuracy in detecting acts of violence.

Numer:

4

Wydawca:

National Institute of Telecommunications

Identyfikator zasobu:

oai:bc.itl.waw.pl:2419

DOI:

10.26636/jtit.2025.4.2328

eISSN:

on-line: ISSN 1899-8852

Źródło:

Journal of Telecommunications and Information Technology

Język:

ang

Prawa:

Biblioteka Naukowa Instytutu Łączności

Licencja:

CC BY 4.0

Temat i słowa kluczowe:

bidirectional gated recurrent unit deep learning deep transfer learning video processing violence detection

Kolekcje, do których przypisany jest obiekt:

Data ostatniej modyfikacji:

1 kwi 2026

Data dodania obiektu:

7 sty 2026

Liczba wyświetleń treści obiektu:

148

Wszystkie dostępne wersje tego obiektu:

https://bc.itl.waw.pl/publication/2738

Wyświetl opis w formacie RDF:

RDF

Wyświetl opis w formacie OAI-PMH:

OAI-PMH

Nazwa wydania Data
Merit, Khaled, AI-based Violent Incident Detection in Surveillance Videos to Enhance Public Safety, Journal of Telecommunications and Information Technology, 2025 1 kwi 2026

Obiekty Podobne

2024, nr 4, JTIT-artykuły
2024, nr 4, JTIT-artykuły
Enhancing Biometric Security with Bimodal Deep Learning and Feature-Level Fusion of Facial and Voice Data, Journal of Telecommunications and Information Technology, 2024, nr 4

Merit, Khaled Beladgham, Mohammed

2024, nr 4
artykuł
2024, nr 3, JTIT-artykuły
2024, nr 3, JTIT-artykuły
A Generalized Learning Approach to Deep Neural Networks, Journal of Telecommunications and Information Technology, 2024, nr 3

Ponti, Francesca Frezza, Fabrizio Simeoni, Patrizio Parisi, Raffaele

2024, nr 3
artykuł
2025, nr 3, JTIT-artykuły
2025, nr 3, JTIT-artykuły
A Comprehensive Study on Path Loss Estimation Using Deep Hybrid Learning in 5G Networks, Journal of Telecommunications and Information Technology, 2025, nr 3

Yeaser, Kazi Md Abrar Hassan, Kazi Md Abir

2025, nr 3
artykuł
2026, nr 3, JTIT-artykuły
2026, nr 3, JTIT-artykuły
Explainable Network Traffic Classification Using XGBoost and SHAP: Interpreting Feature Contributions Across Traffic Classes, Journal of Telecommunications and Information Technology, 2026, nr 3

Deghem, Boubakar Seddik Aid, Lahcene Mostefaoui, Kadda

2026, nr 3
artykuł
2025, nr 1, JTIT-artykuły
2025, nr 1, JTIT-artykuły
Enhancing Cloud-Hosted Phishing Detection Using RNN-LSTM: A Deep Learning Framework, Journal of Telecommunications and Information Technology, 2025

Senouci, Oussama Benaouda, Nadjib

2025, nr 1
artykuł
2025, nr 1, JTIT-artykuły
2025, nr 1, JTIT-artykuły
Semantic Segmentation of Plant Structures with Deep Learning and Channel-wise Attention Mechanism, Journal of Telecommunications and Information Technology, 2025, nr 1

Surehli, Mukund Kumar Aggarwal, Naveen Joshi, Garima Harsh Nayyar, Harsh

2025, nr 1
artykuł
2024, nr 3, JTIT-artykuły
2024, nr 3, JTIT-artykuły
A Collaborative Approach to Detecting DDoS Attacks in SDN Using Entropy and Deep Learning, Journal of Telecommunications and Information Technology, 2024, nr 3

Narayan, D. G. Heena, W Amit, K

2024, nr 3
artykuł
Convolutional Neural Networks for C. Elegans Muscle Age Classification Using Only Self-learned Features, Journal of Telecommunications and Information Technology, 2022, nr 4

Dzwonkowski, Mariusz Czaplewski, Bartosz Panas, Damian

2022, nr 4
artykuł
Więcej
×

Cytowanie

Styl cytowania:

Dane kontaktowe

Adres

Instytut Łączności – Państwowy Instytut Badawczy ul. Szachowa 1 04-894 Warszawa

Telefon

(+48) 5128 696

E-Mail

biblioteka@il-pib.pl

Odwiedź nas!

Ta strona wykorzystuje pliki 'cookies'. Więcej informacji