EGMM video surveillance for monitoring urban traffic scenario

Abstract

Purpose

In the traffic monitoring system, the detection of stirring vehicles is monitored by fitting static cameras in the traffic scenarios. Background subtraction a commonly used method detaches poignant objects in the foreground from the background. The method applies a Gaussian Mixture Model, which can effortlessly be contaminated through slow-moving or momentarily stopped vehicles.

Design/methodology/approach

This paper proposes the Enhanced Gaussian Mixture Model to overcome the addressed issue, efficiently detecting vehicles in complex traffic scenarios.

Findings

The model was evaluated with experiments conducted using real-world on-road travel videos. The evidence intimates that the proposed model excels with other approaches showing the accuracy of 0.9759 when compared with the existing Gaussian mixture model (GMM) model and avoids contamination of slow-moving or momentarily stopped vehicles.

Originality/value

The proposed method effectively combines, tracks and classifies the traffic vehicles, resolving the contamination problem that occurred by slow-moving or momentarily stopped vehicles.

Citation

Reyana, A., Kautish, S., Vibith, A.S. and Goyal, S.B. (2023), "EGMM video surveillance for monitoring urban traffic scenario", International Journal of Intelligent Unmanned Systems, Vol. 11 No. 1, pp. 35-47. https://doi.org/10.1108/IJIUS-07-2021-0061