Open AccessOpen Access


Anomalous Situations Recognition in Surveillance Images Using Deep Learning

Qurat-ul-Ain Arshad1, Mudassar Raza1, Wazir Zada Khan2, Ayesha Siddiqa2, Abdul Muiz2, Muhammad Attique Khan3,*, Usman Tariq4, Taerang Kim5, Jae-Hyuk Cha5,*

1 Department of Computer Science, COMSATS University Islamabad, Wah Campus, 47040, Pakistan
2 Deptartment of Computer Science, University of Wah, Wah Cantt, 47040, Pakistan
3 Deptartment of Computer Science, HITEC University, Taxila, 47080, Pakistan
4 Management Information System Department, College of Business Administration, Prince Sattam Bin Abdulaziz University, Al-Kharj 16278, Saudi Arabia
5 Department of Computer Science, Hanyang University, Seoul, 04763, Korea

* Corresponding Authors: Muhammad Attique Khan. Email: ; Jae-Hyuk Cha. Email:

(This article belongs to this Special Issue: Multimedia Encryption and Information Security)

Computers, Materials & Continua 2023, 76(1), 1103-1125.


Anomalous situations in surveillance videos or images that may result in security issues, such as disasters, accidents, crime, violence, or terrorism, can be identified through video anomaly detection. However, differentiating anomalous situations from normal can be challenging due to variations in human activity in complex environments such as train stations, busy sporting fields, airports, shopping areas, military bases, care centers, etc. Deep learning models’ learning capability is leveraged to identify abnormal situations with improved accuracy. This work proposes a deep learning architecture called Anomalous Situation Recognition Network (ASRNet) for deep feature extraction to improve the detection accuracy of various anomalous image situations. The proposed framework has five steps. In the first step, pretraining of the proposed architecture is performed on the CIFAR-100 dataset. In the second step, the proposed pre-trained model and Inception V3 architecture are used for feature extraction by utilizing the suspicious activity recognition dataset. In the third step, serial feature fusion is performed, and then the Dragonfly algorithm is utilized for feature optimization in the fourth step. Finally, using optimized features, various Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) based classification models are utilized to detect anomalous situations. The proposed framework is validated on the suspicious activity dataset by varying the number of optimized features from 100 to 1000. The results show that the proposed method is effective in detecting anomalous situations and achieves the highest accuracy of 99.24% using cubic SVM.


Cite This Article

Q. Arshad, M. Raza, W. Z. Khan, A. Siddiqa, A. Muiz et al., "Anomalous situations recognition in surveillance images using deep learning," Computers, Materials & Continua, vol. 76, no.1, pp. 1103–1125, 2023.

This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 425


  • 248


  • 0


Share Link