3D-Based Unattended Object Detection Method for Video Surveillance

Chia Hung Yeh; Kahlil Muchtar; Chih Yang Lin

doi:10.1007/978-981-10-6916-1_25

3D-Based Unattended Object Detection Method for Video Surveillance

Chia Hung Yeh, Kahlil Muchtar, Chih Yang Lin^*

^*Corresponding author for this work

Department of Electrical Engineering

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

Abstract

Inspired by 2D GrabCut for still images, this paper proposes automated abandoned object segmentation by introducing 3D GrabCut in surveillance scenario. This allows the method to produce precise object extraction without needing user intervention. Both RGB and depth input are utilized to build abandoned object detector which can resist to shadow and brightness changes. We performed the indoor experiments to show that our system obtains an accurate detection and segmentation. Both quantitative and qualitative measurements are provided to analyze the result.

Original language	English
Title of host publication	Lecture Notes in Networks and Systems
Publisher	Springer
Pages	269-276
Number of pages	8
DOIs	https://doi.org/10.1007/978-981-10-6916-1_25
Publication status	Published - 2018

Publication series

Name	Lecture Notes in Networks and Systems
Volume	18
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Keywords

3D processing
Abandoned object detection
GrabCut

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

Access to Document

10.1007/978-981-10-6916-1_25

Cite this

@inbook{ba9a2b109aae4a79b9c8f3587ebea409,

title = "3D-Based Unattended Object Detection Method for Video Surveillance",

abstract = "Inspired by 2D GrabCut for still images, this paper proposes automated abandoned object segmentation by introducing 3D GrabCut in surveillance scenario. This allows the method to produce precise object extraction without needing user intervention. Both RGB and depth input are utilized to build abandoned object detector which can resist to shadow and brightness changes. We performed the indoor experiments to show that our system obtains an accurate detection and segmentation. Both quantitative and qualitative measurements are provided to analyze the result.",

keywords = "3D processing, Abandoned object detection, GrabCut",

author = "Yeh, {Chia Hung} and Kahlil Muchtar and Lin, {Chih Yang}",

note = "Publisher Copyright: {\textcopyright} 2018, Springer Nature Singapore Pte Ltd.",

year = "2018",

doi = "10.1007/978-981-10-6916-1_25",

language = "English",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "269--276",

booktitle = "Lecture Notes in Networks and Systems",

}

TY - CHAP

T1 - 3D-Based Unattended Object Detection Method for Video Surveillance

AU - Yeh, Chia Hung

AU - Muchtar, Kahlil

AU - Lin, Chih Yang

PY - 2018

Y1 - 2018

N2 - Inspired by 2D GrabCut for still images, this paper proposes automated abandoned object segmentation by introducing 3D GrabCut in surveillance scenario. This allows the method to produce precise object extraction without needing user intervention. Both RGB and depth input are utilized to build abandoned object detector which can resist to shadow and brightness changes. We performed the indoor experiments to show that our system obtains an accurate detection and segmentation. Both quantitative and qualitative measurements are provided to analyze the result.

AB - Inspired by 2D GrabCut for still images, this paper proposes automated abandoned object segmentation by introducing 3D GrabCut in surveillance scenario. This allows the method to produce precise object extraction without needing user intervention. Both RGB and depth input are utilized to build abandoned object detector which can resist to shadow and brightness changes. We performed the indoor experiments to show that our system obtains an accurate detection and segmentation. Both quantitative and qualitative measurements are provided to analyze the result.

KW - 3D processing

KW - Abandoned object detection

KW - GrabCut

UR - http://www.scopus.com/inward/record.url?scp=85063295826&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063295826&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-6916-1_25

DO - 10.1007/978-981-10-6916-1_25

M3 - Chapter

AN - SCOPUS:85063295826

T3 - Lecture Notes in Networks and Systems

SP - 269

EP - 276

BT - Lecture Notes in Networks and Systems

PB - Springer

ER -

3D-Based Unattended Object Detection Method for Video Surveillance

Abstract

Publication series

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this