CoChat

Smart Video Surveillance System Based on Edge Computing

Open access
Cob-Parro, Antonio Carlos, Losada-Gutiérrez, Cristina, Marrón-Romera, Marta, Gardel-Vicente, Alfredo, Bravo-Muñoz, Ignacio · 2021 · Sensors

The DOI matches its Crossref record; 54 of the 55 references it cites were found in a registry or an index, and 1 are not checked yet.

Abstract

New processing methods based on artificial intelligence (AI) and deep learning are replacing traditional computer vision algorithms. The more advanced systems can process huge amounts of data in large computing facilities. In contrast, this paper presents a smart video surveillance system executing AI algorithms in low power consumption embedded devices. The computer vision algorithm, typical for surveillance applications, aims to detect, count and track people’s movements in the area. This application requires a distributed smart camera system. The proposed AI application allows detecting people in the surveillance area using a MobileNet-SSD architecture. In addition, using a robust Kalman filter bank, the algorithm can keep track of people in the video also providing people counting information. The detection results are excellent considering the constraints imposed on the process. The selected architecture for the edge node is based on a UpSquared2 device that includes a vision processor unit (VPU) capable of accelerating the AI CNN inference. The results section provides information about the image processing time when multiple video cameras are connected to the same edge node, people detection precision and recall curves, and the energy consumption of the system. The discussion of results shows the usefulness of deploying this smart camera node throughout a distributed surveillance system.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s21092958

Cites

54 of 55 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 OpenVino structure.
Figure 1 OpenVino structure.CC BY · PubMed Central
Figure 2 Data flow and multiple thread processing.
Figure 2 Data flow and multiple thread processing.CC BY · PubMed Central
Figure 3 Data flow and multiple thread processing.
Figure 3 Data flow and multiple thread processing.CC BY · PubMed Central
Figure 4 Standard convolution kernels [14].
Figure 4 Standard convolution kernels [14].CC BY · PubMed Central
Figure 5 Depthwise convolution kernels [14].
Figure 5 Depthwise convolution kernels [14].CC BY · PubMed Central
Figure 6 Pointwise convolution kernels [14].
Figure 6 Pointwise convolution kernels [14].CC BY · PubMed Central
Figure 7 Kalman structure.
Figure 7 Kalman structure.CC BY · PubMed Central
Figure 8 Pipelined stages.
Figure 8 Pipelined stages.CC BY · PubMed Central
Figure 9 Mounted test system.
Figure 9 Mounted test system.CC BY · PubMed Central
Figure 10 Different scenarios of the EPFL dataset.
Figure 10 Different scenarios of the EPFL dataset.CC BY · PubMed Central
Figure 11 Recall-precision curves for different environments in EPFL dataset.
Figure 11 Recall-precision curves for different environments in EPFL dataset.CC BY · PubMed Central
Figure 12 Stream processing schedule using CPU cores.
Figure 12 Stream processing schedule using CPU cores.CC BY · PubMed Central
Figure 13 Stream processing schedule using CPU and VPU cores.
Figure 13 Stream processing schedule using CPU and VPU cores.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

1 retracted

Research works printed but not linked: 5

  1. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.
  2. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., and Zisserman, A. (2012, May 08). The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. Available online: http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html.
  3. Veringham, M., Van Gool, L., Williams, C.K.I., Winn, J., and Zisserman, A. (2012, May 08). The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. Available online: http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html.
  4. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
  5. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.

Cited by

See all 97

Metadata

Authors
Cob-Parro, A. C., Losada-Gutiérrez, C., Marrón-Romera, M., Gardel-Vicente, A., & Bravo-Muñoz, I.
Affiliations
  • Universidad de Alcalá (ES)
  • Department of Electronics, University of Alcalá, Alcalá de Henares, 28801 Madrid, Spain
Venue
Sensors
Publisher
MDPI AG
Published
2021-04-23
Volume
21
Issue
9
Pages
2958
ISSN
1424-8220 (ISSN-L)
OpenAlex
W3157789903
Cited by
84
References
54
Citations by year
2026: 20 · 2025: 19 · 2024: 19 · 2023: 14 · 2022: 10 · 2021: 2
FWCI
4.05
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • e_Buah (submittedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
European Union’s Horizon 2020 Research and Innovation Programme (PALAEMON project (Grant Agreement nº 814962))
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
video surveillance, edge computing, smart cameras, human detection, people counting, human tracking, MobileNet-SSD, Kalman filter, embedded devices, low power consumption, energy consumption

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.