Mayfly Optimization with Deep Learning-based Robust Object Detection and Classification on Surveillance Videos

Abstract

Surveillance videos are recordings captured by video recording devices for monitoring and securing an area or property. These videos are frequently used in applications, involving law enforcement, security systems, retail analytics, and traffic monitoring. Surveillance videos can provide valuable visual information for analyzing patterns, identifying individuals or objects of interest, and detecting and investigating incidents. Object detection and classification on video surveillance involves the usage of computer vision techniques to identify and categorize objects within the video footage. Object detection algorithms are employed to locate and identify objects within each frame. These algorithms use various techniques, namely bounding box regression, Convolutional Neural Networks (CNNs), and feature extraction to detect objects of interest. This study presents the Mayfly Optimization with Deep Learning-based Robust Object Detection and Classification (MFODL-RODC) method on surveillance videos. The main aim of the MFODL-RODC technique lies in the accurate classification and recognition of objects in surveillance videos. To accomplish this, the MFODL-RODC method follows a two-step process, consisting of object detection and object classification. The MFODL-RODC method uses the EfficientDet object detector for the object detection process. Besides, the classification of detected objects takes place using the Variational Autoencoder (VAE) model. The MFO algorithm is employed to enrich the performance of the VAE model. The simulation examination of the MFODL-RODC technique is performed on benchmark datasets. The extensive results accentuated the improved performance of the MFODL-RODC method over other existing algorithms with an output of 98.89%.