A hybrid heuristic model for video surveillance-based on object detection and video anomaly classification using optimized Bi-LSTM-RBF

Nowadays, video monitoring applications have become significant for observing human activity with the help of computer vision-based approaches for investigating numerous video sequences. The major goal of anomaly identification is to discover the abnormalities automatically in a short interval of time. Performing efficient anomaly detection in a video monitoring system is considered as a complex task due to video noise, spilling, and anomalies. Various anomaly detection models based on Artificial Intelligence (AI) have been developed for video surveillance; however, these models often address only specific issues and do not consider the evaluation concerns over time. Hence, this paper aims to implement a video anomaly detection model through surveillance cameras for reducing abnormal activities that enhance the security of the environment. At first, the input videos are collected from the standard benchmark datasets. These collected videos are given in the frame extraction phase. Further, the extracted frames are fed to the object detection phase, where the YOLO-V3 technique is used. Parameter optimization of YOLO-V3 is achieved using the Modified Cat and Mouse Optimization (MCMO) algorithm to improve detection performance. The object-detected frames are fed as input to the ResNet for extracting the deep features. The extracted deep features are utilized for the classification phase, where the Optimized Bi-directional Long Short Term Memory (Bi-LSTM)-Radial Basis Function (RBF) (OBi-LSTM-RBF) provides the classified anomaly outcome. The variables are optimized using the enhanced CMO algorithm for enhancing the efficacy of the anomaly classification. Simulation evaluations are carried out to reveal the effectiveness of the offered approach with diverse baseline algorithms using diverse performance measures. The offered approach shows significant enhancement in accuracy over baseline approaches. Specifically, it outperforms conventional CNNs by 45.47%, DNNs by 90.03%, Bi-LSTMs by 34.6%, RBF by 90%, and Bi-LSTM -RBF by 89.7% at a learning percentage of 75. This enhancement in performance ensures the effectiveness of the recommended model in handling complex video data and detecting anomalies more precisely.