Background subtraction: non-parametric methods

Performance map

BenchmarkNonParametric

Pixel-Based Adaptive Segmenter (PBAS) of Hofmann et al (2012) paper link

{youtube}DjCLUQg4dow{/youtube} 

In this paper we present a novel method for foreground segmentation. Our proposed approach follows a non-parametric background modeling paradigm, thus the background is modeled by a history of recently observed pixel values. The foreground decision depends on a decision threshold. The background update is based on a learning parameter. We extend both of these parameters to dynamic per-pixel state variables and introduce dynamic controllers for each of them. Furthermore, both controllers are steered by an estimate of the background dynamics. In our experiments, the proposed Pixel-Based Adaptive Segmenter (PBAS) outperforms most state-of-the-art methods

{gallery}PBAS{/gallery}

 

GMG of Godbehere et al (2012) paper link

{youtube}Kz4AnNH3aAE{/youtube} 

For a responsive audio art installation in a skylit atrium, we introduce a single-camera statistical segmentation and tracking algorithm. The algorithm combines statistical background image estimation, per-pixel Bayesian segmentation, and an approximate solution to the multi-target tracking problem using a bank of Kalman filters and Gale-Shapley matching. A heuristic confidence model enables selective filtering of tracks based on dynamic data. We demonstrate that our algorithm has improved recall and F2-score over existing methods in OpenCV 2.1 in a variety of situations. We further demonstrate that feedback between the tracking and the segmentation systems improves recall and F2-score. The system described operated effectively for 5-8 hours per day for 4 months; algorithms are evaluated on video from the camera installed in the atrium. Source code and sample data is open source and available in OpenCV.

{gallery}GMG{/gallery}

 

VuMeter of Goyat et al (2006) paper link

{youtube}APy0gyS-Sk8{/youtube} 

Metrology of vehicle trajectories has several applications in the field of road safety, particularly in dangerous curves. Actually, it is of great interest to observe trajectories of vehicles with the aim of designing a real time driver warning device in dangerous areas. This paper addresses the first step of a work with a video system placed along the road with the objective of vehicle’s position and speed estimation. This system has been totally developed for this project and can record simultaneously three cameras with 640 times 480 pixels up to 30 frames per second (fps) and rangefinder informations. The best contribution of this paper is an original probabilistic background subtraction algorithm, first step of a global method (calibration, tracking, …) implemented to be able to measure vehicle trajectories. Kinematic GPS (in post-processing) has been extensively used to get ground truth

{gallery}VuMeter{/gallery}

 

KDE of Elgammal et al (2000) paper link

{youtube}Kakpjp3ML9o{/youtube}

{gallery}KDE{/gallery}

These algorithms are contained in the bgslibrary by Andrews Sobral, that includes over 30 background subtraction algorithms, a common C++ framework for comparing them, and an handy C++/MFC or Java app to see them running on video files or live feed from a webcam.

Return to the list of background subtraction algorithms

Leave a Reply

Your email address will not be published.