Mobile-Le Harmonic Fusion Network for Object Recognition and SiamMoT Based Multi-Object Tracking Using Video Surveillance

Video surveillance plays a vital role in applications like crowd control, traffic monitoring, and security, but accurately tracking multiple moving objects remains challenging. Traditional methods often lack reliability in complex scenes. To address this, the Mobile-Le Harmonic Fusion Network (MLeHF-Net) + SiamMoT (MLeHF-Net + SiamMoT) combined with SiamMoT has been introduced, offering improved object detection and tracking performance. The process starts by extracting video from the dataset and breaking it into frames, which are segmented using Entropy Weighting K-Means (EWKM). Objects are then detected via MLeHF-Net a fusion of LeNet, Harmonic analysis, and MobileNet and tracked using the Siamese Multi-Object Tracking network (SiamMoT). This study uses the UCSD Anomaly Detection Dataset to benchmark video surveillance performance. The proposed MLeHF-Net + SiamMOT model is compared with established methods You Only Look Once (YOLOv2) + LuNet, SMSBoxNet, Densely Feature Selection Convolutional Neural Network – Hyper Parameter tuning (DFCN-HP), and Computational Intelligence-based Harmony Search Algorithm for Real-Time Object Detection and Tracking (CIHSA-RTODT). Experimental results show that proposed method achieved high performance with MOTP, TNR, TPR, and overall accuracy of 91.099%, 91.134%, 93.577%, and 92.315%. Compared to existing methods YOLOv2 + LuNet, SMSBoxNet, DFCN-HP, and CIHSA-RTODT it delivered accuracy improvements of up to 13.72%.