Background Subtraction for Effective Object Detection and its Parametric Evaluation (original) (raw)
Related papers
Foreground-adaptive background subtraction
2009
Abstract Background subtraction is a powerful mechanism for detecting change in a sequence of images that finds many applications. The most successful background subtraction methods apply probabilistic models to background intensities evolving in time; nonparametric and mixture-of-Gaussians models are but two examples. The main difficulty in designing a robust background subtraction algorithm is the selection of a detection threshold.
Comparative Study of Statistical background Modeling and Subtraction
Indonesian Journal of Electrical Engineering and Computer Science, 2017
Background subtraction methods are widely exploited for moving object detection in videos in many computer vision applications, such as traffic monitoring, human motion capture and video surveillance. The two most distinguishing and challenging aspects of such approaches in this application field are how to build correctly and efficiently the background model and how to prevent the false detection between; (1) moving background pixels and moving objects, (2) shadows pixel and moving objects. In this paper we present a new method for image segmentation using background subtraction. We propose an effective scheme for modelling and updating a background adaptively in dynamic scenes focus on statistical learning. We also introduce a method to detect sudden illumination changes and segment moving objects during these changes. Unlike the traditional color levels provided by RGB sensor aren’t the best choice, for this reason we propose a recursive algorithm that contributes to select very ...
A spatial sampling mechanism for effective background subtraction
2007
In the video surveillance literature, background (BG) subtraction is an important and fundamental issue. In this context, a consistent group of methods operates at region level, evaluating in fixed zones of interest pixel values' statistics, so that a per-pixel foreground (FG) labeling can be performed. In this paper, we propose a novel hybrid, pixel/region, approach for background subtraction. The method, named Spatial-Time Adaptive Per Pixel Mixture Of Gaussian (S-TAPPMOG), evaluates pixel statistics considering zones of interest that change continuously over time, adopting a sampling mechanism. In this way, numerous classical BG issues can be efficiently faced: actually, it is possible to model the background information more accurately in the chromatic uniform regions exhibiting stable behavior, thus minimizing foreground camouflages. At the same time, it is possible to model successfully regions of similar color but corrupted by heavy noise, in order to minimize false FG detections. Such approach, outperforming state of the art methods, is able to run in quasi-real time and it can be used at a basis for more structured background subtraction algorithms.
Comparative study of background subtraction algorithms
In this paper, we present a comparative study of several state of the art background subtraction methods. Approaches ranging from simple background subtraction with global thresholding to more sophisticated statistical methods have been implemented and tested on different videos with ground truth. The goal of this study is to provide a solid analytic ground to underscore the strengths and weaknesses of the most widely implemented motion detection methods. The methods are compared based on their robustness to different types of video, their memory requirement, and the computational effort they require. The impact of a Markovian prior as well as some post-processing operators are also evaluated. Most of the videos used in this study
Background subtraction: separating the modeling and the inference
Machine Vision and Applications, 2013
In its early implementations, background modeling was a process of building a model for the background of a video with a stationary camera, and identifying pixels that did not conform well to this model. The pixels that were not well-described by the background model were assumed to be moving objects. Many systems today maintain models for the foreground as well as the background, and these models compete to explain the pixels in a video. If the foreground model explains the pixels better, they are considered foreground. Otherwise they are considered background. In this paper, we argue that the logical endpoint of this evolution is to simply use Bayes' rule to classify pixels. In particular, it is essential to have a background likelihood, a foreground likelihood, and a prior at each pixel. A simple application of Bayes' rule then gives a posterior probability over the label. The only remaining question is the quality of the component models: the background likelihood, the foreground likelihood, and the prior. We describe a model for the likelihoods that is built by using not only the past observations at a given pixel location, but by also including observations in a spatial neighborhood around the location. This enables us to model the influence between neighboring pixels and is an improvement over earlier pixelwise models that do not allow for such influence. Although similar in spirit to the joint domain-range model, we show that our model overcomes certain deficiencies in that model. We use a spatially dependent prior for the background and foreground. The background and foreground labels from the
Background Subtraction in Real Applications: Challenges, Current Models and Future Directions
Computer Science Review, 2020
Computer vision applications based on videos often require the detection of moving objects in their first step. Background subtraction is then applied in order to separate the background and the foreground. In literature, background subtraction is surely among themost investigated field in computer vision providing a big amount of publications. Most of them concern the application of mathematical and machine learning models to be more robust to the challenges met in videos. However, the ultimate goal is that the background subtraction methods developed in research could be employed in real applications like traffic surveillance. But looking at the literature, we can remark that there is often a gap between the current methods used in real applications and the current methods in fundamental research. In addition, the videos evaluated in large-scale datasets are not exhaustive in the way that they only covered a part of the complete spectrum of the challenges met in real applications. In this context, we attempt to provide the most exhaustive survey as possible on real applications that used background subtraction in order to identify the real challenges met in practice, the current used background models and to provide future directions. Thus, challenges are investigated in terms of camera, foreground objects and environments. In addition, we identify the background models that are effectively used in these applications in order to find potential usable recent background models in terms of robustness, time and memory requirements.
IEEE Access
Background subtraction is a popular technique for detecting objects moving across a fixed camera view. The performance of this paradigm is influenced by various challenges, such as object relocation, illumination change, cast shadows, waving background, camera shake, bootstrapping, camouflage, and so on. In this paper, we present a synopsis on the evolution of the background subtraction techniques over the last two decades. The different ways of mathematical modeling are taken into consideration to categorize the methods. We also evaluate the performance of some of the state-of-the-art techniques visa -vis the challenges associated. Eleven different algorithms of background subtraction have been simulated on thirty-four image sequences collected from five benchmark datasets. For each image sequence, seven performance metrics are evaluated and an exhaustive comparative analysis has been made to derive inferences. The potential findings in the result analysis are presented for future exploration. The obtained image and video results are uploaded at https://sites.google.com/site/soaBSevaluation. INDEX TERMS Video surveillance, object detection, background subtraction, background modeling, foreground extraction, background maintenance, shadow removal.
PROBABILISTIC METHODS FOR ADAPTIVE BACKGROUND SUBTRACTION
First and foremost, I would like thank my advisor, Professor Janusz Konrad, for all of his support and guidance on this research and throughout my graduate studies. He has done an outstanding job of teaching me, and moreover, leading me in the right directions so that I may learn to better teach myself. I am also grateful for all of the times that, when I've over analyzed and overburdened myself, he has kept me honest and realistic.
2012
Abstract Background subtraction is a widely used technique for segmenting a foreground object from its background. The aim of this paper is to review and compare the performance of the most common statistical background subtraction methods, including median-based, Gaussian-based and Kernel density-based approaches. To obtain a fair evaluation, four challenging scenarios were selected based on Wallflower datasets. All review methods are based on processing speed, memory usage and segmentation accuracy.
Evaluating the Performance of Common Background Subtraction Techniques
recognizing moving objects from a video stream considered to be a fundamental and critical task in many computer-vision applications. A common approach is to perform background subtraction, which identifies moving objects from the portion of a video frame that differs significantly from a background model. This paper compares various background subtraction algorithms for detecting a single object. The work considers approaches varying from simple techniques such as static method and frame differencing to more sophisticated probabilistic modeling techniques such as adaptive median filtering and GMM. The evaluating process is based on visual observation of the output of the background subtraction techniques under assessments.