Copyright © 2024 The Authors. Published by Tech Science Press. 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. ech T Press Science DOI: 10.32604/cmc.2024.057684 ARTICLE A Scalable and Generalized Deep Ensemble Model for Road Anomaly Detection in Surveillance Videos Sarfaraz Natha 1 , 2 , * , Fareed A. Jokhio 1 , Mehwish Laghari 1 , Mohammad Siraj 3 , * , Saif A. Alsaif 3 , Usman Ashraf 4 and Asghar Ali 5 1 Department of Information Technology, Quaid-e-Awam University of Engineering, Science & Technology, Nawabshah, 67480, Pakistan 2 Department of Soſtware Engineering, Sir Syed University of Engineering and Technology, Karachi, 75000, Pakistan 3 Electrical Engineering Department, College of Engineering, King Saud University, Riyadh, 11421, Saudi Arabia 4 School of Business, Torrens University, Sydney, NSW 2007, Australia 5 School of Engineering and Information Technology, e University of New South Wales (UNSD), Canberra, ACT 2604, Australia *Corresponding Authors: Sarfaraz Natha. Email: sasattar@ssuet.edu.pk; Mohammad Siraj. Email: siraj@ksu.edu.sa Received: 25 August 2024 Accepted: 29 November 2024 Published: 19 December 2024 ABSTRACT Surveillance cameras have been widely used for monitoring in both private and public sectors as a security measure. Close Circuits Television (CCTV) Cameras are used to surveillance and monitor the normal and anomalous incidents. Real-world anomaly detection is a significant challenge due to its complex and diverse nature. It is difficult to manually analyze because vast amounts of video data have been generated through surveillance systems, and the need for automated techniques has been raised to enhance detection accuracy. is paper proposes a novel deep-stacked ensemble model integrated with a data augmentation approach called Stack Ensemble Road Anomaly Detection (SERAD). SERAD is used to detect and classify the four most happening road anomalies, such as accidents, car fires, fighting, and snatching, through road surveillance videos with high accuracy. e SERAD adapted three pre-trained Convolutional Neural Networks (CNNs) models, namely VGG19, ResNet50 and InceptionV3. e stacking technique is employed to incorporate these three models, resulting in much-improved accuracy for classifying road abnormalities compared to individual models. Additionally, it presented a custom real-world Road Anomaly Dataset (RAD) comprising a comprehensive collection of road images and videos. e experimental results demonstrate the strength and reliability of the proposed SERAD model, achieving an impressive classification accuracy of 98.7%. e results indicate that the proposed SERAD model outperforms than the individual CNN base models. KEYWORDS Convolutional neural network; transfer learning; stack ensemble learning; road anomaly detection; data augmentation