Computer Vision to Improve Security Surveillance through the Identification of Digital Patterns

Abdulhussein, Ansam A.; Kuba, Hasanien Kariem; Alanssari, A.N.

doi:10.1109/icieam48468.2020.9112022

Cited by 7 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Computer vision is a transformative branch of artificial intelligence that reshapes the way machines interpret visual information [1][2][3][4][5][6][7][8]. It has broad applications across various sectors such as healthcare imaging [9], autonomous vehicle technology [10], advanced robotics [11], security [12], and the construction industry [13]. A key process in computer vision is image segmentation [14], which simplifies the analysis and interpretation of images by dividing them into distinct sections.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Semantic Scene Segmentation for Indoor Autonomous Systems Using Advanced Attention-Supported Improved UNet

Ngoc,

Vinh,

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper introduces EFFB7-UNet, an advanced semantic segmentation framework tailored for Indoor Autonomous Vision Systems (IAVSs) utilizing the U-Net architecture. The framework employs EfficientNetB4 as its encoder, significantly enhancing feature extraction. It integrates a spatial and channel Squeeze-and-Excitation (scSE) attention block, emphasizing critical areas and features to refine segmentation outcomes. Comprehensive evaluations using the NYUv2 Dataset and various augmented datasets were conducted. This study systematically compares EFFB7-UNet's performance with multiple U-Net encoders, including ResNet50, ResNet101, MobileNet V2, VGG16, VGG19, and EfficientNets B0-B6. The findings reveal that EFFB7-UNet not only surpasses these configurations in terms of accuracy but also highlights the effectiveness of the scSE attention block in achieving superior segmentation results. Without utilizing depth information, EFFB7-UNet achieves a 12\% improvement in mean Intersection over Union (mIOU). This notable enhancement highlights EFFB7-UNet's adaptability across different domains, implying substantial progress in enhancing the effectiveness and reliability of Intelligent Autonomous Vision Systems (IAVS) technologies.

show abstract