Multispectral background subtraction with deep learning

Liu, Rongrong; Ruichek, Yassine; Bagdouri, M. El

doi:10.1016/j.jvcir.2021.103267

Cited by 7 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Background subtraction or removal is closely associated with other data mining processes, such as change detection, foreground detection, and foreground-background segmentation (Liu et al, 2021). Background subtraction also involves its detection, which is usually done using thresholding or clustering (Amigo & Santos, 2019).…”

Section: Background Subtractionmentioning

confidence: 99%

See 1 more Smart Citation

Multispectral data mining: A focus on remote sensing satellite images

Lim,

Sreevalsan‐Nair,

Daya Sagar

2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

This article gives a brief overview of various aspects of data mining of multispectral image data. We focus on specifically the remote sensing satellite images acquired using multispectral imaging (MSI), given the technology used across multiple knowledge domains, such as chemistry, medical imaging, remote sensing, and so on with a sufficient amount of variation. In this article, the different data mining processes are reviewed along with state‐of‐the‐art methods and applications. To study data mining, it is important to know how the data are acquired and preprocessed. Hence, those topics are briefly covered in the article. The article concludes with applications demonstrating the knowledge discovery from data mining, modern challenges, and promising future directions for MSI data mining research.This article is categorized under: Application Areas > Science and Technology Fundamental Concepts of Data and Knowledge > Knowledge Representation Fundamental Concepts of Data and Knowledge > Big Data Mining

show abstract

Section: Background Subtractionmentioning

confidence: 99%

“…The former is done using principal component analysis (pca), and the latter using K-means clustering, both of which are also used for feature extraction (Section 3.3). Deep learning is also used for background subtraction through the use of convolutional neural networks (CNNs) (Liu et al, 2021).…”

Section: Background Subtractionmentioning

confidence: 99%

Multispectral data mining: A focus on remote sensing satellite images

Lim,

Sreevalsan‐Nair,

Daya Sagar

2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…e function of the pooling layer is mainly to reduce the size of the feature map, and it is often used in the middle of two convolutional layers to reduce network parameters and reduce the overfitting of the model. Common types of pooling operations are max pooling and average pooling [18]. e maximum pooling operation is usually used in the middle of the convolutional network to reduce the size of the feature map, and the average pooling operation is generally used at the end of the network to replace the fully connected layer and reduce network parameters.…”

Section: Pooling Layermentioning

confidence: 99%

Research on Modern Book Packaging Design Based on Aesthetic Evaluation Based on a Deep Learning Model

Wen

2022

Scientific Programming

View full text Add to dashboard Cite

Through the analysis of the application and development of deep learning in the field of book design and publishing, the article expounds on the positive impact of deep learning on book design and publishing, discusses the shortcomings of deep learning in creative ability, aesthetic ability, emotion, etc., and then discusses the design and publishing of books. The future development direction of intelligent aided design and intelligent personalized design is proposed to provide a reference for researchers in deep learning and book design and publication.

show abstract

“…To satisfy the need for real-time computing in object surveillance, background difference based methods [ 8 , 9 ] are still the most cost-effective methods in practical application. After background difference, all the areas of objects with shadows are detected.…”

Section: Introductionmentioning

confidence: 99%

A differential correction based shadow removal method for real-time monitoring

Liu

Chen

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Shadow removal is an important issue in the field of motion object surveillance and automatic control. Although many works are concentrated on this issue, the diverse and similar motion patterns between shadows and objects still severely affect the removal performance. Constrained by the computational efficiency in real-time monitoring, the pixel feature based methods are still the main shadow removal methods in practice. Following this idea, this paper proposes a novel and simple shadow removal method based on a differential correction calculation between the pixel values of Red, Green and Blue channels. Specifically, considering the fact that shadows are formed because of the occlusion of light by objects, all the reflected light will be attenuated. Hence there will be a similar weakening trends in all Red, Green and Blue channels of the shadow areas, but not in the object areas. These trends can be caught by differential correction calculation and distinguish the shadow areas from object areas. Based on this feature, our shadow removal method is designed. Experiment results verify that, compared with other state-of-the-art shadow removal methods, our method improves the average of object and shadow detection accuracies by at least 10% in most of the cases.

show abstract

Multispectral background subtraction with deep learning

Cited by 7 publications

References 35 publications

Multispectral data mining: A focus on remote sensing satellite images

Multispectral data mining: A focus on remote sensing satellite images

Research on Modern Book Packaging Design Based on Aesthetic Evaluation Based on a Deep Learning Model

A differential correction based shadow removal method for real-time monitoring

Contact Info

Product

Resources

About