Diamond sentry: Integrating sensors and cameras for real-time monitoring of indoor spaces

Pavan Turaga, Yuri A. Ivanov

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Video-based surveillance and monitoring of indoor spaces such as offices, airports and convenience stores has attracted increasing interest in recent years. While video proves useful for inferring information pertaining to identities and activities, it results in large data overheads. On the other hand, motion sensors are much more data-efficient and far less expensive, but possess limited recognition capabilities. In this paper, we describe a system that integrates a large number of wireless motion sensors and a few strategically placed cameras and its application to real-time monitoring of indoor spaces. The system described here responds to an event immediately as it happens and provides visual evidence of the location of the event, thereby establishing an awareness of the events in the entire location being monitored, supplying the user with the information about "when", "where", and "what" happens in the space as the events unfold. We introduce a system that is designed for maximizing the utility of the video data recorded from a location. It achieves this goal by following the minimal commitment strategy, where no data is discarded and no particular hypothesis is pursued until the time when the interpretation is necessary. Additionally, we employ an alternative modality to help in indexing video data for real time, as well as for possible future use in forensic mode. We use the motion sensor data to specify policies of camera control. Utilizing these policies makes the application of machine learning and computer vision techniques simple to use to perform on-line surveillance tasks in a fast, accurate, and scalable way.

Original languageEnglish (US)
Article number5483195
Pages (from-to)593-602
Number of pages10
JournalIEEE Sensors Journal
Volume11
Issue number3
DOIs
StatePublished - 2011
Externally publishedYes

Fingerprint

Diamonds
Cameras
diamonds
cameras
video data
Monitoring
sensors
Sensors
surveillance
Airports
Computer vision
machine learning
Learning systems
airports
supplying
computer vision

Keywords

  • Activity recognition
  • camera network
  • fusion
  • human detection
  • motion sensors
  • surveillance

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Instrumentation

Cite this

Diamond sentry : Integrating sensors and cameras for real-time monitoring of indoor spaces. / Turaga, Pavan; Ivanov, Yuri A.

In: IEEE Sensors Journal, Vol. 11, No. 3, 5483195, 2011, p. 593-602.

Research output: Contribution to journalArticle

@article{047a1726c9cc4bc8a51398b8c2698d37,
title = "Diamond sentry: Integrating sensors and cameras for real-time monitoring of indoor spaces",
abstract = "Video-based surveillance and monitoring of indoor spaces such as offices, airports and convenience stores has attracted increasing interest in recent years. While video proves useful for inferring information pertaining to identities and activities, it results in large data overheads. On the other hand, motion sensors are much more data-efficient and far less expensive, but possess limited recognition capabilities. In this paper, we describe a system that integrates a large number of wireless motion sensors and a few strategically placed cameras and its application to real-time monitoring of indoor spaces. The system described here responds to an event immediately as it happens and provides visual evidence of the location of the event, thereby establishing an awareness of the events in the entire location being monitored, supplying the user with the information about {"}when{"}, {"}where{"}, and {"}what{"} happens in the space as the events unfold. We introduce a system that is designed for maximizing the utility of the video data recorded from a location. It achieves this goal by following the minimal commitment strategy, where no data is discarded and no particular hypothesis is pursued until the time when the interpretation is necessary. Additionally, we employ an alternative modality to help in indexing video data for real time, as well as for possible future use in forensic mode. We use the motion sensor data to specify policies of camera control. Utilizing these policies makes the application of machine learning and computer vision techniques simple to use to perform on-line surveillance tasks in a fast, accurate, and scalable way.",
keywords = "Activity recognition, camera network, fusion, human detection, motion sensors, surveillance",
author = "Pavan Turaga and Ivanov, {Yuri A.}",
year = "2011",
doi = "10.1109/JSEN.2010.2050309",
language = "English (US)",
volume = "11",
pages = "593--602",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Diamond sentry

T2 - Integrating sensors and cameras for real-time monitoring of indoor spaces

AU - Turaga, Pavan

AU - Ivanov, Yuri A.

PY - 2011

Y1 - 2011

N2 - Video-based surveillance and monitoring of indoor spaces such as offices, airports and convenience stores has attracted increasing interest in recent years. While video proves useful for inferring information pertaining to identities and activities, it results in large data overheads. On the other hand, motion sensors are much more data-efficient and far less expensive, but possess limited recognition capabilities. In this paper, we describe a system that integrates a large number of wireless motion sensors and a few strategically placed cameras and its application to real-time monitoring of indoor spaces. The system described here responds to an event immediately as it happens and provides visual evidence of the location of the event, thereby establishing an awareness of the events in the entire location being monitored, supplying the user with the information about "when", "where", and "what" happens in the space as the events unfold. We introduce a system that is designed for maximizing the utility of the video data recorded from a location. It achieves this goal by following the minimal commitment strategy, where no data is discarded and no particular hypothesis is pursued until the time when the interpretation is necessary. Additionally, we employ an alternative modality to help in indexing video data for real time, as well as for possible future use in forensic mode. We use the motion sensor data to specify policies of camera control. Utilizing these policies makes the application of machine learning and computer vision techniques simple to use to perform on-line surveillance tasks in a fast, accurate, and scalable way.

AB - Video-based surveillance and monitoring of indoor spaces such as offices, airports and convenience stores has attracted increasing interest in recent years. While video proves useful for inferring information pertaining to identities and activities, it results in large data overheads. On the other hand, motion sensors are much more data-efficient and far less expensive, but possess limited recognition capabilities. In this paper, we describe a system that integrates a large number of wireless motion sensors and a few strategically placed cameras and its application to real-time monitoring of indoor spaces. The system described here responds to an event immediately as it happens and provides visual evidence of the location of the event, thereby establishing an awareness of the events in the entire location being monitored, supplying the user with the information about "when", "where", and "what" happens in the space as the events unfold. We introduce a system that is designed for maximizing the utility of the video data recorded from a location. It achieves this goal by following the minimal commitment strategy, where no data is discarded and no particular hypothesis is pursued until the time when the interpretation is necessary. Additionally, we employ an alternative modality to help in indexing video data for real time, as well as for possible future use in forensic mode. We use the motion sensor data to specify policies of camera control. Utilizing these policies makes the application of machine learning and computer vision techniques simple to use to perform on-line surveillance tasks in a fast, accurate, and scalable way.

KW - Activity recognition

KW - camera network

KW - fusion

KW - human detection

KW - motion sensors

KW - surveillance

UR - http://www.scopus.com/inward/record.url?scp=79251648091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79251648091&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2010.2050309

DO - 10.1109/JSEN.2010.2050309

M3 - Article

AN - SCOPUS:79251648091

VL - 11

SP - 593

EP - 602

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 3

M1 - 5483195

ER -