Analisis Perbandingan Metode Gaussian Mixture Model dan Logika Fuzzy untuk Deteksi dan Penghitungan Objek Bergerak pada Sistem Surveilans Video Malam Hari

Abstract

Object detection and counting in video surveillance is a crucial task with various applications, yet it faces significant challenges due to dynamic environmental conditions such as varying illumination, occlusions, and noise. This research evaluates and compares the performance of two prominent background subtraction techniques: Gaussian Mixture Model (GMM) and Fuzzy Logic, for moving object segmentation and counting. The methodology involves image preprocessing (grayscale conversion, Gaussian blur, normalization), background model generation using the median of initial frames, object segmentation with both GMM and Fuzzy Logic enhanced by Region of Interest (ROI) and morphological operations, and object tracking using a simple Centroid Tracker. Performance was evaluated using segmentation metrics (Precision, Recall, F1-score, Percentage of Wrong Classifications (PWC)) and counting accuracy metrics (Mean Absolute Error (MAE), Accuracy). Results indicate that GMM achieved a slightly better F1-score (0.23 vs 0.18) for segmentation, while Fuzzy Logic demonstrated marginally higher Precision (0.37 vs 0.33). For object counting, both methods yielded an identical average MAE of 0.94, with Fuzzy Logic showing a slightly higher average accuracy (9.88% vs 9.41%). The study highlights that both GMM and Fuzzy Logic are viable for moving object detection and counting, each with distinct strengths and weaknesses, but performance remains sensitive to dynamic scene conditions. The dataset utilized, CDnet's "night videos" category, specifically the "busyBoulvard" sequence, presented unique challenges due to low light and dense traffic, which were central to the evaluation.