An exploration of the performances achievable by combining unsupervised background subtraction algorithms

TL;DR

This paper investigates how combining multiple unsupervised background subtraction algorithms can significantly improve motion detection performance in video, revealing a large potential for enhancement over individual methods.

Contribution

It systematically explores performance bounds of six combination strategies for 26 algorithms, demonstrating substantial gains over single algorithms and comparing with state-of-the-art methods.

Findings

Combination strategies outperform individual algorithms.

Significant performance gap exists between single algorithms and their combinations.

Comparison with state-of-the-art methods shows promising improvements.

Abstract

Background subtraction (BGS) is a common choice for performing motion detection in video. Hundreds of BGS algorithms are released every year, but combining them to detect motion remains largely unexplored. We found that combination strategies allow to capitalize on this massive amount of available BGS algorithms, and offer significant space for performance improvement. In this paper, we explore sets of performances achievable by 6 strategies combining, pixelwise, the outputs of 26 unsupervised BGS algorithms, on the CDnet 2014 dataset, both in the ROC space and in terms of the F1 score. The chosen strategies are representative for a large panel of strategies, including both deterministic and non-deterministic ones, voting and learning. In our experiments, we compare our results with the state-of-the-art combinations IUTIS-5 and CNN-SFC, and report six conclusions, among which the existence of an important gap between the performances of the individual algorithms and the best performances achievable by combining them.