Better Foreground Segmentation Through Graph Cuts

TL;DR

This paper introduces a graph cut-based method for foreground segmentation in background subtraction tasks, improving boundary accuracy and reducing errors compared to traditional morphological techniques.

Contribution

It applies a minimum graph cut algorithm to enhance foreground segmentation quality, demonstrating superior results over conventional methods.

Findings

Reduces boundary errors in foreground segmentation

Produces cleaner, more accurate segmentations

Effective on both artificial and real data

Abstract

For many tracking and surveillance applications, background subtraction provides an effective means of segmenting objects moving in front of a static background. Researchers have traditionally used combinations of morphological operations to remove the noise inherent in the background-subtracted result. Such techniques can effectively isolate foreground objects, but tend to lose fidelity around the borders of the segmentation, especially for noisy input. This paper explores the use of a minimum graph cut algorithm to segment the foreground, resulting in qualitatively and quantitiatively cleaner segmentations. Experiments on both artificial and real data show that the graph-based method reduces the error around segmented foreground objects. A MATLAB code implementation is available at http://www.cs.smith.edu/~nhowe/research/code/#fgseg