2019
DOI: 10.11591/ijeecs.v15.i1.pp517-526
|View full text |Cite
|
Sign up to set email alerts
|

Automatic foreground detection based on KDE and binary classification

Abstract: In the recent decades, several methods have been developed to extract moving objects in the presence of dynamic background. However, most of them use a global threshold, and ignore the correlation between neighboring pixels. To address these issues, this paper presents a new approach to generate a probability image based on Kernel Density Estimation (KDE) method, and then apply the Maximum A Posteriori in the Markov Random Field (MAP-MRF) based on probability image, so as to generate an energy function, this f… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 23 publications
0
2
0
Order By: Relevance
“…are having several issues in the detection of edges for underwater image [23]. We can utilize the edge detection results in several automatic foreground extraction applications [24,25], but still, it is a challenging issue to detect the efficient edges for applications such as ocean and oceanography. Low Error Rate, Good Localization, minimal response are the three important criteria of the optimal canny edge detection algorithm.…”
Section: Edge Detectionmentioning
confidence: 99%
“…are having several issues in the detection of edges for underwater image [23]. We can utilize the edge detection results in several automatic foreground extraction applications [24,25], but still, it is a challenging issue to detect the efficient edges for applications such as ocean and oceanography. Low Error Rate, Good Localization, minimal response are the three important criteria of the optimal canny edge detection algorithm.…”
Section: Edge Detectionmentioning
confidence: 99%
“…In order to teste the ability and efficiency of the methods in extracting the moving objects under dynamic background, the aforementioned methods are analyzed and compared using the K-way ANONVA. Lahraichi et al [14] presented a new approach through two criteria : the first is based on creating a probabilistic image based on Kernel density estimation method and the second is the extraction of the moving pixels using graph cutting algorithm. Zaharin et al [15] studied different methods of the background subtraction and the frame difference.…”
Section: Introductionmentioning
confidence: 99%