Improved Gaussian Mixture Model for Moving Object Detection

Chen, Gang; Yu, Zhezhou; Wen, Quan; Yu, Yangquan

doi:10.1007/978-3-642-23881-9_23

Cited by 6 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [15] presented an improvement in GMM through a background updating period using different learning rates for the estimated background and foreground pixels. The result shows the method works better than the typical gaussian mixture model.…”

Section: ░ 2 Review Of Literaturementioning

confidence: 99%

A Novel User-Friendly Application for Foreground Detection with Post-Processing in Surveillance Video Analytics

Joy

Vijayakumar

2022

IJEER

View full text Add to dashboard Cite

Detection of the object in the video is a primary task of all video-processing-based applications. It is one of the challenging areas in computer vision. The paper presents a novel MATLAB-based object detection application based on an improved Gaussian Mixture Model. Gaussian Mixture Model with post-processing applied here for segmentation of foreground from background. The application is divided into three modules pre-processing, detection and post-processing. The morphological gradient filter uses here for segmenting the foreground objects from the background. The proposed method was tested for various video sequences with challenges and proved that the approach performs well for the majority video sequences.

show abstract

Section: ░ 2 Review Of Literaturementioning

confidence: 99%

A Novel User-Friendly Application for Foreground Detection with Post-Processing in Surveillance Video Analytics

Joy

Vijayakumar

2022

IJEER

View full text Add to dashboard Cite

show abstract

“…Hence, in case of long-term lighting variations, the leading Gaussian can be discarded from its position (considering the x/r factor) due to the increasing deviation. This problem can be partially solved by utilizing independent adaptation factors for Gaussian mean and deviation [4]. Another modification of the GMM introduces spatial dependencies for the pixel assignment process, making it more robust [32].…”

Section: Gaussian Mixture Modelmentioning

confidence: 99%

Parallel implementation of background subtraction algorithms for real-time video processing on a supercomputer platform

Szwoch

Ellwart

Czyżewski

2012

J Real-Time Image Proc

View full text Add to dashboard Cite

Results of evaluation of the background subtraction algorithms implemented on a supercomputer platform in a parallel manner are presented in the article. The aim of the work is to chose an algorithm, a number of threads and a task scheduling method, that together provide satisfactory accuracy and efficiency of a real-time processing of high-resolution camera images, maintaining the cost of resources usage at a reasonable level. Two selected algorithms: the Gaussian mixture models and the Codebook, are presented and their computational complexity is discussed. Various approaches to the parallel implementation, including assigning the image pixels to threads, the task scheduling methods and the thread management systems, are presented. The experiments were performed on a supercomputer cluster, using a single machine with 12 physical cores. The accuracy and performance of the implemented algorithms were evaluated for varying image resolutions and numbers of concurrent processing threads. On a basis of the evaluation results, an optimal configuration for the parallel implementation of the system for real-time video content analysis on a supercomputer platform was proposed.

show abstract

“…Background subtraction method is an effective method for moving object detection, and is one of the most used methods currently [10][11]. The basic idea of background subtraction method is to establish a background mathematical model to represent background image.…”

Section: Introductionmentioning

confidence: 99%

Moving Object Detection Based on Improved ViBe Algorithm

Gu¹,

Song²,

Dao-yin³

et al. 2015

IJSEIA

View full text Add to dashboard Cite

In this paper, an improved ViBe background subtraction algorithm is proposed for dealing with ghost problem during the process of moving object detection. The ghost areas in image can be detected based on the theory that the histogram distributions of ghost areas have similarity distribution characteristics. However, the histogram distributions of real moving objects change with the real objects moving. The influence of ghost areas on moving object detection is eliminated. The improved ViBe, the original ViBe and the Gauss mixture model are compared and analyzed, The results show that the improved ViBe can effectively eliminate ghost areas, and has high real-time.

show abstract

Improved Gaussian Mixture Model for Moving Object Detection

Cited by 6 publications

References 6 publications

A Novel User-Friendly Application for Foreground Detection with Post-Processing in Surveillance Video Analytics

A Novel User-Friendly Application for Foreground Detection with Post-Processing in Surveillance Video Analytics

Parallel implementation of background subtraction algorithms for real-time video processing on a supercomputer platform

Moving Object Detection Based on Improved ViBe Algorithm

Contact Info

Product

Resources

About