Accurate Background Modeling for Moving Object Detection in a Dynamic Scene (original) (raw)
Related papers
Accurate Background Modeling for Moving Object Detection in a Dynamic Scene (PDF)
2010
Fast and accurate foreground detection in video sequences is the first step in many computer vision applications. In this paper, we propose a new method for background modeling that operates in color and gray spaces and that manages the entropy information to obtain the pixel state card. Our method is recursive and does not require a training period to handle various problems when classify pixels into either foreground or background. First, it starts by analyzing the pixel state card to build a dynamic matrix. This latter is used to selectively update background model. Secondly, our method eliminates noise and holes from the moving areas, removes uninteresting moving regions and refines the shape of foregrounds. A comparative study through quantitative and qualitative evaluations shows that our method can detect foreground efficiently and accurately in videos even in the presence of various problems including sudden and gradual illumination changes, shaking camera, background component changes, ghost, and foreground speed.
Special Issue on “Background Modeling for Foreground Detection in Real-World Dynamic Scenes”
Special Issue on “Background Modeling for Foreground Detection in Real-World Dynamic Scenes”, 2014
Although background modeling and foreground detection are not mandatory steps for computer vision applications, they may prove useful as they separate the primal objects usually called ”foreground” from the remaining part of the scene called ”background”, and permits different algorithmic treatment in the video processing field such as video-surveillance, optical motion capture, multimedia applications, teleconferencing and human-computer interfaces. Conventional background modeling methods exploit the temporal variation of each pixel to model the background and the foreground detection is made by using change detection. The last decade witnessed very significant publications on background modeling but recently new applications in which background is not static, such as recordings taken from mobile devices or Internet videos, need new developments to detect robustly moving objects in challenging environments. Thus, effective methods for robustness to deal both with dynamic backgrounds, illumination changes in real scenes with fixed cameras or mobile devices are needed and so different strategies may be used such as automatic feature selection, model selection or hierarchical models. Another feature of background modeling methods is that the use of advanced models has to be computed in real-time and with low memory requirements. Algorithms may need to be redesigned to meet these requirements. Thus, the readers can find 1) new methods to model the background, 2) recent strategies to improve foreground detection to tackle challenges such as dynamic backgrounds and illumination changes, and 3) adaptive and incremental algorithms to achieve real-time applications.
Video background modeling: recent approaches, issues and our proposed techniques
Journal of Machine Vision and Applications, 2013
Effective and efficient background subtraction is important to a number of computer vision tasks. We introduce several new techniques to address key challenges for background modeling using a Gaussian mixture model (GMM) for moving objects detection in a video acquired by a static camera. The novel features of our proposed model are that it automatically learns dynamics of a scene and adapts its parameters accordingly, suppresses ghosts in the foreground mask using a SURF features matching algorithm, and introduces a new spatio-temporal filter to further refine the foreground detection results. Detection of abrupt illumination changes in the scene is dealt with by a model shifting-based scheme to reuse already learned models and spatio-temporal history of foreground blobs is used to detect and handle paused objects. The proposed model is rigorously tested and compared with several previous models and has shown significant performance improvements. Keywords Background subtraction • Online learning • Feature matching • Gaussian mixture model 1 Introduction Precise localization of foreground objects is one of the most important building blocks of computer vision applications
Moving Object Detection Using an Adaptive Background Modeling in Dynamic Scene
Determination of moving foreground objects in dynamic scenes for video surveillance systems is still a problem can not be resolved exactly. In the literature; pixel-based, block-based and texture-based methods have been proposed to solve this problem. The method we propose will be block-based method which can be applied to real time in dynamic scenes. We have created non-overlapped blocks with the averages the pixels in the gray level. We used this average value to generate the background model based on a modified original KDE (Kernel Density Estimation) method. To determine the moving foreground objects and to update background model, we use an adaptive parameter which is determined according to the number of changes in the state of this pixel during the last N frames. Performance evaluation of the proposed method is tested by background methods in literature without applying post-processing techniques. Experimental results demonstrate the effectiveness and robustness of our method.
Dual Information-Based Background Model For Moving Object Detection
IEEE International Conference on Image Processing, ICIP 2020, 2020
In this article, a novel pixel based object detection framework is proposed that leverages dual type pixel-level information to construct the backgroundmodel. The first type of information is initially used intensity histograms over a training set of a few initial video frames. Finally, it is formed by gathering all theminimumandmaximumvalues of contiguous non-zero frequencies of the temporal intensity histogram. The second type of information constitutes a set having only the discrete pixel values. Subsequently, a pixel-level periodic updating scheme is used to make the model robust and flexible enough to recognize and detect foregrounds in various critical background environments. This dual format model produces effective results over many state-of-the-art methods in a large variety of challenging real-life video sequences.
Foreground Detection Based on Real-time Background Modeling and Robust Subtraction
This paper presents a robust approach for detecting moving objects from a static background scene that contains slow illumination changes, physical changes and micromovements. First, we propose a new algorithm for background modeling that adapts to slow illumination and physical changes. This algorithm which is based on pixel state computation and background pixel state decision does not need such training sequences excluding moving objects. Second, we develop an efficient background subtraction algorithm that is able to cope with micro-movement of the background scene. This is done by calculating the similarity between the incoming pixel and its neighborhood pixels in the background model. Finally, we applied this robust approach to some video surveillance sequences of both indoor and outdoor scenes. The results demonstrate the effectiveness of our approach.
An efficient background updating model for motion detection
2013 International Conference on Informatics, Electronics and Vision (ICIEV), 2013
In transit system, military, residential area and restricted area video surveillance system is getting more popular for motion detection and object extraction. Background updating process is the most important feature for motion detection in video surveillance system. In this paper, we proposed a novel algorithm for updating the background and therefore detection the motion of an object for a fixed video surveillance system. In our proposed method video frames are taken from a surveillance camera and then for updating background previous 40 frames from the video frames are used. Here pixel wise comparison is done for the previous frames so that maximum common pixel values are stored to get a temporary background. When the temporary background is obtained then it is compared to the last frame's pixel values and the common pixel values are stored as the permanent background. The pixel values which are not common to the both frame then these values are taken from the previous permanent frames which are common with the last frame. Now again if there is any mismatched pixel value remains then the temporary background's pixel value is stored as permanent background for this position. Finally we get the permanent background as an updated background. And now for motion detection, the next frame's pixel values are subtracted with the permanent background, if the value goes beyond a threshold value then there the object motion is detected. We have applied this method for different video datasets and obtained interesting and promising results.
A background subtraction algorithm based on pixel state
Proceedings of the 13th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry - VRCAI '14, 2014
Most of current background subtraction algorithms have issues of ghost and foreground aperture when they process the crowded video sequences in the outdoor scenes. In this paper we present a novel method based on the pixel state to solve the issues. Every pixel in a video steam is assumed to own two different states-active or inactive. Via the pixel state, we divide the whole observing time into many short units. Meanwhile, a new concept, confidence, is proposed to measure the significance of each cluster. By observing small units of time, our method automatically selects the clusters with the highest confidence as the background model. The experimental results show our method not only provides the accurate motion detection of crowded video sequences, but also handles the light change and performs in real time.
International Journal of Spatio-Temporal Data Science
This work proposes a novel method for detection of motion based object having dynamic scenario in the background. The suggested scheme has a strong potential for real-time applications especially for rafting, river, sea-beach, swimming pools, ponds, etc. Apart from these, this work is very beneficial for surveillance of border, tunnel, traffic in the sea, forest, restricted zones, deep zones, etc. This work develops a statistical p based background subtraction method and implemented in three stages. In the first stage, a background model is developed using few initial frames. In the second stage, this work classifies the foreground using the difference frame and the appropriate threshold value. An automatic threshold value is generated at run-time and updated iteratively. It also reduces the problem of using a constant threshold. In the third stage, morphological filters and connected component based region filtering technique is applied to enhance the detection quality. The extensive experimental result shows more accurate results of proposed method. It also demonstrates better performance against considered state-of-the-art methods.
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 ...