KLI

Dual Camera-Based Supervised Foreground Detection for Low-End Video Surveillance Systems

Metadata Downloads
Abstract
Deep learning-based algorithms showed promising prospects in the computer vision domain. However, their deployment in real-time systems is challenging due to their computational complexity, high-end hardware prerequisites, and the amount of annotated data for training. This paper proposes an efficient foreground detection(EFDNet) algorithm based on deep spatial features extracted from an RGB input image using VGG-16 convolutional neural networks (CNN). The VGG-16 CNN is modified by concatenated residual (CR) blocks to learn better global contextual features and recover lost feature information due to several convolution operations. A new upsampling network is designed using bilinear interpolation sandwiched between 3 × 3 convolutions to upsample and refine feature maps for pixel-wise prediction. This helps to propagate loss errors from the upsampling network during backpropagation. The experiments showed the effectiveness of the EFDNet in outperforming top-ranked foreground detection algorithms. EFDNet trains faster on low-end hardware and demonstrated promising results with a minimum of 50 training frames with binary ground-truth.
Author(s)
샤바즈 아즈말조강현
Issued Date
2021
Type
Article
Keyword
BackpropagationConvolutionconvolutional neural networkdual-camera sensorsFeature extractionInterpolationRadio frequencysecurity systemSensorsTrainingVideo surveillance systems
DOI
10.1109/JSEN.2021.3054940
URI
https://oak.ulsan.ac.kr/handle/2021.oak/9129
https://ulsan-primo.hosted.exlibrisgroup.com/primo-explore/fulldisplay?docid=TN_cdi_crossref_primary_10_1109_JSEN_2021_3054940&context=PC&vid=ULSAN&lang=ko_KR&search_scope=default_scope&adaptor=primo_central_multiple_fe&tab=default_tab&query=any,contains,Dual%20Camera-Based%20Supervised%20Foreground%20Detection%20for%20Low-End%20Video%20Surveillance%20Systems&offset=0&pcAvailability=true
Publisher
IEEE SENSORS JOURNAL
Location
미국
Language
영어
ISSN
1530-437X
Citation Volume
21
Citation Number
7
Citation Start Page
9359
Citation End Page
9366
Appears in Collections:
Engineering > IT Convergence
Authorize & License
  • Authorize공개
Files in This Item:
  • There are no files associated with this item.

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.