Lost world: Looking for anomalous tracks in long-term surveillance videos

John See; Suyin Tan

doi:10.1145/2683405.2683436

Lost world: Looking for anomalous tracks in long-term surveillance videos

John See, Suyin Tan

School of Mathematical & Computer Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

Video surveillance over a long span of time is no longer a luxury in this day and age. The abundance of video data captured over time presents a slew of new problems in computer vision. One potential challenge involves the task of finding anomalous tracks over a long period of time. In this work, we propose a new time-scale framework for mining anomalous track patterns in long-term surveillance videos. Track clustering is performed at two separate temporal levels to better represent the common modes of behaviour. A probabilistic anomaly prediction algorithm is also introduced to evaluate the abnormality of new tracks. In our preliminary work, experiments conducted on the LOST dataset offer insights into how track anomalies can be mined and classified. We hope this work will provide the impetus for further advancements in this direction.

Original language	English
Title of host publication	IVCNZ '14
Subtitle of host publication	Proceedings of the 29th International Conference on Image and Vision Computing New Zealand
Publisher	Association for Computing Machinery
Pages	224-229
Number of pages	6
ISBN (Electronic)	9781450331845
DOIs	https://doi.org/10.1145/2683405.2683436
Publication status	Published - 19 Nov 2014
Event	29th International Conference on Image and Vision Computing New Zealand 2014 - Hamilton, New Zealand Duration: 19 Nov 2014 → 21 Nov 2014

Conference

Conference	29th International Conference on Image and Vision Computing New Zealand 2014
Abbreviated title	IVCNZ 2014
Country/Territory	New Zealand
City	Hamilton
Period	19/11/14 → 21/11/14

Keywords

Anomaly mining
Long-term video surveillance
Track clustering
Video data mining

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/2683405.2683436

Cite this

@inproceedings{768acbd5e88f437c96310de1209a20d0,

title = "Lost world: Looking for anomalous tracks in long-term surveillance videos",

abstract = "Video surveillance over a long span of time is no longer a luxury in this day and age. The abundance of video data captured over time presents a slew of new problems in computer vision. One potential challenge involves the task of finding anomalous tracks over a long period of time. In this work, we propose a new time-scale framework for mining anomalous track patterns in long-term surveillance videos. Track clustering is performed at two separate temporal levels to better represent the common modes of behaviour. A probabilistic anomaly prediction algorithm is also introduced to evaluate the abnormality of new tracks. In our preliminary work, experiments conducted on the LOST dataset offer insights into how track anomalies can be mined and classified. We hope this work will provide the impetus for further advancements in this direction.",

keywords = "Anomaly mining, Long-term video surveillance, Track clustering, Video data mining",

author = "John See and Suyin Tan",

note = "Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 29th International Conference on Image and Vision Computing New Zealand 2014, IVCNZ 2014 ; Conference date: 19-11-2014 Through 21-11-2014",

year = "2014",

month = nov,

day = "19",

doi = "10.1145/2683405.2683436",

language = "English",

pages = "224--229",

booktitle = "IVCNZ '14",

publisher = "Association for Computing Machinery",

address = "United States",

}

See, J & Tan, S 2014, Lost world: Looking for anomalous tracks in long-term surveillance videos. in IVCNZ '14: Proceedings of the 29th International Conference on Image and Vision Computing New Zealand. Association for Computing Machinery, pp. 224-229, 29th International Conference on Image and Vision Computing New Zealand 2014, Hamilton, New Zealand, 19/11/14. https://doi.org/10.1145/2683405.2683436

TY - GEN

T1 - Lost world

T2 - 29th International Conference on Image and Vision Computing New Zealand 2014

AU - See, John

AU - Tan, Suyin

PY - 2014/11/19

Y1 - 2014/11/19

N2 - Video surveillance over a long span of time is no longer a luxury in this day and age. The abundance of video data captured over time presents a slew of new problems in computer vision. One potential challenge involves the task of finding anomalous tracks over a long period of time. In this work, we propose a new time-scale framework for mining anomalous track patterns in long-term surveillance videos. Track clustering is performed at two separate temporal levels to better represent the common modes of behaviour. A probabilistic anomaly prediction algorithm is also introduced to evaluate the abnormality of new tracks. In our preliminary work, experiments conducted on the LOST dataset offer insights into how track anomalies can be mined and classified. We hope this work will provide the impetus for further advancements in this direction.

AB - Video surveillance over a long span of time is no longer a luxury in this day and age. The abundance of video data captured over time presents a slew of new problems in computer vision. One potential challenge involves the task of finding anomalous tracks over a long period of time. In this work, we propose a new time-scale framework for mining anomalous track patterns in long-term surveillance videos. Track clustering is performed at two separate temporal levels to better represent the common modes of behaviour. A probabilistic anomaly prediction algorithm is also introduced to evaluate the abnormality of new tracks. In our preliminary work, experiments conducted on the LOST dataset offer insights into how track anomalies can be mined and classified. We hope this work will provide the impetus for further advancements in this direction.

KW - Anomaly mining

KW - Long-term video surveillance

KW - Track clustering

KW - Video data mining

UR - http://www.scopus.com/inward/record.url?scp=84985914883&partnerID=8YFLogxK

U2 - 10.1145/2683405.2683436

DO - 10.1145/2683405.2683436

M3 - Conference contribution

AN - SCOPUS:84985914883

SP - 224

EP - 229

BT - IVCNZ '14

PB - Association for Computing Machinery

Y2 - 19 November 2014 through 21 November 2014

ER -

Lost world: Looking for anomalous tracks in long-term surveillance videos

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this