Reconstruction-Free Compressive Vision for Surveillance Applications

Research output: Contribution to journalArticle

Abstract

Compressed sensing (CS) allows signals and images to be reliably inferred from undersampled measurements. Exploiting CS allows the creation of new types of high-performance sensors including infrared cameras and magnetic resonance imaging systems. Advances in computer vision and deep learning have enabled new applications of automated systems. In this book, we introduce reconstruction-free compressive vision, where image processing and computer vision algorithms are embedded directly in the compressive domain, without the need for first reconstructing the measurements into images or video. Reconstruction of CS images is computationally expensive and adds to system complexity. Therefore, reconstruction-free compressive vision is an appealing alternative particularly for power-aware systems and bandwidth-limited applications that do not have on-board post-processing computational capabilities. Engineers must balance maintaining algorithm performance while minimizing both the number of measurements needed and the computational requirements of the algorithms. Our study explores the intersection of compressed sensing and computer vision, with the focus on applications in surveillance and autonomous navigation. Other applications are also discussed at the end and a comprehensive list of references including survey papers are given for further reading.

Original languageEnglish (US)
Pages (from-to)1-100
Number of pages100
JournalSynthesis Lectures on Signal Processing
Volume14
Issue number1
DOIs
StatePublished - Jan 1 2019

Fingerprint

Compressed sensing
Computer vision
Magnetic resonance
Imaging systems
Navigation
Image processing
Cameras
Infrared radiation
Bandwidth
Engineers
Sensors
Processing

Keywords

  • compressed sensing
  • deep learning
  • sparse representations
  • surveillance
  • track-before-detect

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Reconstruction-Free Compressive Vision for Surveillance Applications. / Braun, Henry; Turaga, Pavan; Spanias, Andreas; Katoch, Sameeksha; Jayasuriya, Suren; Tepedelenlioglu, Cihan.

In: Synthesis Lectures on Signal Processing, Vol. 14, No. 1, 01.01.2019, p. 1-100.

Research output: Contribution to journalArticle

@article{798a8617fb4747b88f6f65182c436e72,
title = "Reconstruction-Free Compressive Vision for Surveillance Applications",
abstract = "Compressed sensing (CS) allows signals and images to be reliably inferred from undersampled measurements. Exploiting CS allows the creation of new types of high-performance sensors including infrared cameras and magnetic resonance imaging systems. Advances in computer vision and deep learning have enabled new applications of automated systems. In this book, we introduce reconstruction-free compressive vision, where image processing and computer vision algorithms are embedded directly in the compressive domain, without the need for first reconstructing the measurements into images or video. Reconstruction of CS images is computationally expensive and adds to system complexity. Therefore, reconstruction-free compressive vision is an appealing alternative particularly for power-aware systems and bandwidth-limited applications that do not have on-board post-processing computational capabilities. Engineers must balance maintaining algorithm performance while minimizing both the number of measurements needed and the computational requirements of the algorithms. Our study explores the intersection of compressed sensing and computer vision, with the focus on applications in surveillance and autonomous navigation. Other applications are also discussed at the end and a comprehensive list of references including survey papers are given for further reading.",
keywords = "compressed sensing, deep learning, sparse representations, surveillance, track-before-detect",
author = "Henry Braun and Pavan Turaga and Andreas Spanias and Sameeksha Katoch and Suren Jayasuriya and Cihan Tepedelenlioglu",
year = "2019",
month = "1",
day = "1",
doi = "10.2200/S00914ED2V01Y201904SPR017",
language = "English (US)",
volume = "14",
pages = "1--100",
journal = "Synthesis Lectures on Signal Processing",
issn = "1932-1236",
publisher = "Morgan and Claypool Publishers",
number = "1",

}

TY - JOUR

T1 - Reconstruction-Free Compressive Vision for Surveillance Applications

AU - Braun, Henry

AU - Turaga, Pavan

AU - Spanias, Andreas

AU - Katoch, Sameeksha

AU - Jayasuriya, Suren

AU - Tepedelenlioglu, Cihan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Compressed sensing (CS) allows signals and images to be reliably inferred from undersampled measurements. Exploiting CS allows the creation of new types of high-performance sensors including infrared cameras and magnetic resonance imaging systems. Advances in computer vision and deep learning have enabled new applications of automated systems. In this book, we introduce reconstruction-free compressive vision, where image processing and computer vision algorithms are embedded directly in the compressive domain, without the need for first reconstructing the measurements into images or video. Reconstruction of CS images is computationally expensive and adds to system complexity. Therefore, reconstruction-free compressive vision is an appealing alternative particularly for power-aware systems and bandwidth-limited applications that do not have on-board post-processing computational capabilities. Engineers must balance maintaining algorithm performance while minimizing both the number of measurements needed and the computational requirements of the algorithms. Our study explores the intersection of compressed sensing and computer vision, with the focus on applications in surveillance and autonomous navigation. Other applications are also discussed at the end and a comprehensive list of references including survey papers are given for further reading.

AB - Compressed sensing (CS) allows signals and images to be reliably inferred from undersampled measurements. Exploiting CS allows the creation of new types of high-performance sensors including infrared cameras and magnetic resonance imaging systems. Advances in computer vision and deep learning have enabled new applications of automated systems. In this book, we introduce reconstruction-free compressive vision, where image processing and computer vision algorithms are embedded directly in the compressive domain, without the need for first reconstructing the measurements into images or video. Reconstruction of CS images is computationally expensive and adds to system complexity. Therefore, reconstruction-free compressive vision is an appealing alternative particularly for power-aware systems and bandwidth-limited applications that do not have on-board post-processing computational capabilities. Engineers must balance maintaining algorithm performance while minimizing both the number of measurements needed and the computational requirements of the algorithms. Our study explores the intersection of compressed sensing and computer vision, with the focus on applications in surveillance and autonomous navigation. Other applications are also discussed at the end and a comprehensive list of references including survey papers are given for further reading.

KW - compressed sensing

KW - deep learning

KW - sparse representations

KW - surveillance

KW - track-before-detect

UR - http://www.scopus.com/inward/record.url?scp=85065248585&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065248585&partnerID=8YFLogxK

U2 - 10.2200/S00914ED2V01Y201904SPR017

DO - 10.2200/S00914ED2V01Y201904SPR017

M3 - Article

AN - SCOPUS:85065248585

VL - 14

SP - 1

EP - 100

JO - Synthesis Lectures on Signal Processing

JF - Synthesis Lectures on Signal Processing

SN - 1932-1236

IS - 1

ER -