Motion Vector–Guided Object Detection and Tracking for Smart

Surveillance Systems

V. Vinothini1,* N. Karthika Devi1 R. Nazreen Roja1 G. Mahendran2

1 Assistant Professor, Syed Ammal Engineering College, Tamil Nadu, India

2 Professor, Syed Ammal Engineering College, Tamil Nadu, India

Received: January 03, 2026 R e vis ed: February 03 2026 A c cep ted: March 01, 2026 ⋆ C or responding author

ABSTRACT

Multiple moving object detection and tracking are challenging roles in many computer vision applications such as

object navigation and human identification. Object tracking is one of the key challenges for securing against crime,

supporting public safety, and enabling effective traffic management systems. In video surveillance applications,

detection of multiple moving vehicles from video is the major task for tracking and understanding the behaviour

of the detected objects. Performance of object detection algorithms is degraded by factors such as fog or haze,

occlusion, dynamic background, poor illumination, and low resolution. Fog is one of the major bottlenecks of video

surveillance applications. The proposed Dark Channel Prior algorithm using guided filter (GDCP) is adapted for fog

removal. The Gaussian Mixture Model (GMM) is proposed for detecting multiple moving objects, and features are

extracted from the detected objects using Motion Vector Estimation. The K-Nearest Neighbor algorithm is used for

tracking the moving objects (vehicles) using the detected features. Efficiency is improved due to the adoption of the

proposed fog-removal algorithm and feature extraction for effective tracking. There are wide varieties of applications

in moving object detection and tracking.

Keywords: Gaussian Mixture Model (GMM) Motion Vector Estimation K-Nearest Neighbors (KNN)

1. INTRODUCTION

Video surveillance is an emerging topic which detects, tracks,

and identifies multiple moving objects without human intervention.

Applications of video surveillance systems include

security, traffic surveillance, crowd statistics, human

iden-tification, and detection of anomalous behaviour.

Moving object detection is very difficult when videos are

captured in challenging weather conditions such as winter,

snow storms, snow on the ground, fog, and air turbulence

[1].

Object detection and tracking have a wide variety of applications

in computer vision, video surveillance, vision-based

control, video compression, and man-machine interfaces.

A robust, accurate, and high-performance approach is still a

great challenge today. The difficulty level of this problem

de-pends strongly on how the object to be detected and

tracked is defined [2]. In the proposed method, multiple

moving objects are detected effectively by using the Gaussian

Mixture Model method. One of the bottlenecks of video

surveillance systems is weather condition, especially fog.

Fog or haze is the cause of many road accidents. Since fog

affects the visual quality of an image, it leads to

misinterpretation of target objects. To improve the

efficiency of video surveillance systems, fog should be

eradicated using the Guided Dark Channel Prior technique.

Motion Vector Estimation is used for effective tracking of

multiple moving objects.