Background Subtraction on Embedded Hardware

2014 International Conference on 3D Imaging (IC3D)

2014

This paper proposes a new pixel-based background subtraction technique, applicable to range images, to detect motion. Our method exploits the physical meaning of depth information, which leads to an improved background/foreground segmentation and the instantaneous suppression of ghosts that would appear on color images.In particular, our technique considers certain characteristics of depth measurements, such as failures for certain pixels or the non-uniformity of the spatial distribution of noise in range images, to build an improved pixel-based background model. Experiments show that incorporating specificities related to depth measurements allows us to propose a method whose performance is increased with respect to other stateof-the-art methods.

Section: Related Workmentioning

confidence: 99%

A physically motivated pixel-based model for background subtraction in 3D images

Braham

Lejeune

2014 International Conference on 3D Imaging (IC3D)

2014

“…2. The evaluation of the segmentation map occurs on a pixel base in most benchmarks such as changedetection.net [2,10], which indicates that the spatial coherence is not the primary concern. In fact, none of the 7 metrics computed on that website depends on the temporal or spatial order of pixels.…”

Section: Methodsmentioning

confidence: 99%

“…The background subtraction (BGS) is a well studied problem [2,10] for which, despite the impressive amount of methods proposed in the literature so far, no satisfactory technique has been found yet (for all cases) [6,7]. This paper discusses the limits of pixel-based BGS methods.…”

Section: Introductionmentioning

confidence: 99%

A Perfect Estimation of a Background Image Does Not Lead to a Perfect Background Subtraction: Analysis of the Upper Bound on the Performance

Pierard

New Trends in Image Analysis and Processing -- ICIAP 2015 Workshops

2015

Abstract. The quest for the best background subtraction technique is ongoing. Despite that a considerable e ort has been undertaken to develop exible and e cient methods, some elementary questions are still unanswered. One of them is the existence of an intrinsic upper bound to the performance. In fact, data are a ected by noise, and therefore it is illusory to believe that it is possible to achieve a perfect segmentation.This paper aims at exploring some intrinsic limitations of the principle of background subtraction. The purpose consists in studying the impact of several limiting factors separately. One of our conclusions is that even if an algorithm would be able to calculate a perfect background image, it is not su cient to achieve a perfect segmentation with background subtraction, due to other intrinsic limitations.

“…While this operation seems obvious, it is very difficult to accommodate to the large variety of scenes and to deal with dynamical effects such as sudden lighting changes, dynamic backgrounds, shadows, etc. Therefore, many techniques have been proposed and reviewed for background subtraction (see for example Brutzer et al [1], Bouwmans [2,3], or Jodoin et al [4]). …”

Section: Introductionmentioning

confidence: 99%

Time Ordering Shuffling for Improving Background Subtraction

Laugraud

Latour

Advanced Concepts for Intelligent Vision Systems

2015

Abstract. By construction, a video is a series of ordered frames, whose order is dened at the time of the acquisition process. Background subtraction methods then take this input video and produce a series of segmentation maps expressed in terms of foreground objects and scene background. To our knowledge, this natural ordering of frames has never been questioned or challenged. In this paper, we propose to challenge, in a prospective view, the natural ordering of video frames in the context of background subtraction, and examine alternative time orderings. The idea consists in changing the order before background subtraction is applied, by means of shuing strategies, and re-ordering the segmentation maps afterwards. For this purpose, we propose several shuing strategies and show that, for some background subtraction methods, results are preserved or even improved. The practical advantage of time shuing is that it can been applied to any existing background subtraction seamlessly.