Retrieval in long surveillance videos using user-described motion & object attributes

Gregory Castañón, Mohamed Elgharib, Venkatesh Saligrama, Pierre Marc Jodoin

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We present a content-based retrieval method for long surveillance videos in wide-area (Airborne) and near-field (CCTV) imagery. Our goal is to retrieve video segments, with a focus on detecting objects moving on routes, that match user-defined events of interest. The sheer size and remote locations where surveillance videos are acquired necessitates highly compressed representations that are also meaningful for supporting user-defined queries. To address these challenges we archive long-surveillance video through lightweight processing based on low-level local spatio-temporal extraction of motion and object 2. These are then hashed into an inverted index using locality-sensitive hashing (LSH This local approach allows for query flexibility and leads to significant gains in compression. Our second task is to extract partial matches to user-created queries and assemble them into full matches using Dynamic Programming (DP DP assembles the indexed low level features into a video segment that matches the query route by exploiting causality. We examine CCTV and Airborne footage, whose low contrast makes motion extraction more difficult. We generate robust motion estimates for Airborne data using a tracklets generation algorithm while we use Horn and Schunck approach to generate motion estimates for CCTV. Our approach handles long routes, low contrasts and occlusion. We derive bounds on the rate of false positives and demonstrate the effectiveness of the approach for counting, motion pattern recognition and abandoned object applications.

Original languageEnglish
Article number7225141
JournalIEEE Transactions on Circuits and Systems for Video Technology
VolumePP
Issue number99
DOIs
Publication statusPublished - 2015
Externally publishedYes

Fingerprint

Closed circuit television systems
Content based retrieval
Dynamic programming
Pattern recognition
Processing

Keywords

  • Airborne
  • CCTV
  • Dynamic programming
  • Surveillance
  • Tracklets
  • Video retrieval

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

Retrieval in long surveillance videos using user-described motion & object attributes. / Castañón, Gregory; Elgharib, Mohamed; Saligrama, Venkatesh; Jodoin, Pierre Marc.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. PP, No. 99, 7225141, 2015.

Research output: Contribution to journalArticle

@article{c957f6871fc34de292b8fd47ea06d573,
title = "Retrieval in long surveillance videos using user-described motion & object attributes",
abstract = "We present a content-based retrieval method for long surveillance videos in wide-area (Airborne) and near-field (CCTV) imagery. Our goal is to retrieve video segments, with a focus on detecting objects moving on routes, that match user-defined events of interest. The sheer size and remote locations where surveillance videos are acquired necessitates highly compressed representations that are also meaningful for supporting user-defined queries. To address these challenges we archive long-surveillance video through lightweight processing based on low-level local spatio-temporal extraction of motion and object 2. These are then hashed into an inverted index using locality-sensitive hashing (LSH This local approach allows for query flexibility and leads to significant gains in compression. Our second task is to extract partial matches to user-created queries and assemble them into full matches using Dynamic Programming (DP DP assembles the indexed low level features into a video segment that matches the query route by exploiting causality. We examine CCTV and Airborne footage, whose low contrast makes motion extraction more difficult. We generate robust motion estimates for Airborne data using a tracklets generation algorithm while we use Horn and Schunck approach to generate motion estimates for CCTV. Our approach handles long routes, low contrasts and occlusion. We derive bounds on the rate of false positives and demonstrate the effectiveness of the approach for counting, motion pattern recognition and abandoned object applications.",
keywords = "Airborne, CCTV, Dynamic programming, Surveillance, Tracklets, Video retrieval",
author = "Gregory Casta{\~n}{\'o}n and Mohamed Elgharib and Venkatesh Saligrama and Jodoin, {Pierre Marc}",
year = "2015",
doi = "10.1109/TCSVT.2015.2473295",
language = "English",
volume = "PP",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "99",

}

TY - JOUR

T1 - Retrieval in long surveillance videos using user-described motion & object attributes

AU - Castañón, Gregory

AU - Elgharib, Mohamed

AU - Saligrama, Venkatesh

AU - Jodoin, Pierre Marc

PY - 2015

Y1 - 2015

N2 - We present a content-based retrieval method for long surveillance videos in wide-area (Airborne) and near-field (CCTV) imagery. Our goal is to retrieve video segments, with a focus on detecting objects moving on routes, that match user-defined events of interest. The sheer size and remote locations where surveillance videos are acquired necessitates highly compressed representations that are also meaningful for supporting user-defined queries. To address these challenges we archive long-surveillance video through lightweight processing based on low-level local spatio-temporal extraction of motion and object 2. These are then hashed into an inverted index using locality-sensitive hashing (LSH This local approach allows for query flexibility and leads to significant gains in compression. Our second task is to extract partial matches to user-created queries and assemble them into full matches using Dynamic Programming (DP DP assembles the indexed low level features into a video segment that matches the query route by exploiting causality. We examine CCTV and Airborne footage, whose low contrast makes motion extraction more difficult. We generate robust motion estimates for Airborne data using a tracklets generation algorithm while we use Horn and Schunck approach to generate motion estimates for CCTV. Our approach handles long routes, low contrasts and occlusion. We derive bounds on the rate of false positives and demonstrate the effectiveness of the approach for counting, motion pattern recognition and abandoned object applications.

AB - We present a content-based retrieval method for long surveillance videos in wide-area (Airborne) and near-field (CCTV) imagery. Our goal is to retrieve video segments, with a focus on detecting objects moving on routes, that match user-defined events of interest. The sheer size and remote locations where surveillance videos are acquired necessitates highly compressed representations that are also meaningful for supporting user-defined queries. To address these challenges we archive long-surveillance video through lightweight processing based on low-level local spatio-temporal extraction of motion and object 2. These are then hashed into an inverted index using locality-sensitive hashing (LSH This local approach allows for query flexibility and leads to significant gains in compression. Our second task is to extract partial matches to user-created queries and assemble them into full matches using Dynamic Programming (DP DP assembles the indexed low level features into a video segment that matches the query route by exploiting causality. We examine CCTV and Airborne footage, whose low contrast makes motion extraction more difficult. We generate robust motion estimates for Airborne data using a tracklets generation algorithm while we use Horn and Schunck approach to generate motion estimates for CCTV. Our approach handles long routes, low contrasts and occlusion. We derive bounds on the rate of false positives and demonstrate the effectiveness of the approach for counting, motion pattern recognition and abandoned object applications.

KW - Airborne

KW - CCTV

KW - Dynamic programming

KW - Surveillance

KW - Tracklets

KW - Video retrieval

UR - http://www.scopus.com/inward/record.url?scp=84991451249&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991451249&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2015.2473295

DO - 10.1109/TCSVT.2015.2473295

M3 - Article

VL - PP

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 99

M1 - 7225141

ER -