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

arXiv: https://arxiv.org/abs/2202.12563 · HTML: https://mlsanity.com/paper/2202.12563/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 38 references that are in the map.
- First posted on arXiv 25 Feb 2022.

## Builds on (most cited first, 6 of 6)

- [Background Subtraction in Real Applications: Challenges, Current Models and Future Directions](https://mlsanity.com/paper/1901.03577/) (2019)
- [Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation](https://mlsanity.com/paper/1811.05255/) (2018)
- [An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs](https://mlsanity.com/paper/2105.01342/) (2021)
- [Combining Background Subtraction Algorithms with Convolutional Neural Network](https://mlsanity.com/paper/1807.02080/) (2018)
- [Summarizing the performances of a background subtraction algorithm measured on several videos](https://mlsanity.com/paper/2002.05654/) (2020)
- [Comparative study of motion detection methods for video surveillance systems](https://mlsanity.com/paper/1804.05459/) (2018)

## Built on by (most cited first, 1 of 1)

- [A Methodology to Evaluate Strategies Predicting Rankings on Unseen Domains](https://mlsanity.com/paper/2505.15595/) (2025)

## Abstract (arXiv)

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.