Abnormal Motion Detection in a Real-Time Smart Camera System

Mona Akbarniai Tehrani; Richard Kleihorst; Peter Meijer; Lambert Spaanenburg

doi:10.1109/ICDSC.2009.5289359

Abnormal Motion Detection in a Real-Time Smart Camera System

Mona Akbarniai Tehrani, Richard Kleihorst, Peter Meijer, Lambert Spaanenburg

Department of Electrical and Information Technology

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

9 Citations (SciVal)

Abstract

This paper discusses a method for abnormal motion detection and its real-time implementation on a smart camera. Abnormal motion detection is a surveillance technique that only allows unfamiliar motion patterns to result in alarms. Our approach has two phases. First, normal motion is detected and the motion paths are trained, building up a model of normal behaviour. Feed-forward neural networks are here used for learning. Second, abnormal motion is detected by comparing the current observed motion to the stored model. A complete demonstration system is implemented to detect abnormal paths of persons moving in an indoor space. As platform we used a wireless smart camera system containing an SIMD (Single. Instruction Multiple-Data) processor for real-time detection of moving persons and an 8051 microcontroller for implementing the neural network. The 8051 also functions as camera host to broadcast abnormal events using Zig Bee to a main network system.

Original language	English
Title of host publication	Third ACM/IEEE International Conference on Distributed Smart Cameras, 2009. ICDSC 2009
Publisher	IEEE - Institute of Electrical and Electronics Engineers Inc.
Pages	410-416
ISBN (Print)	978-1-4244-4620-9
DOIs	https://doi.org/10.1109/ICDSC.2009.5289359
Publication status	Published - 2009
Event	3rd ACM/IEEE International Conference on Distributed Smart Cameras - Como, Italy Duration: 2009 Aug 30 → 2009 Sep 2

Conference

Conference	3rd ACM/IEEE International Conference on Distributed Smart Cameras
Country/Territory	Italy
City	Como
Period	2009/08/30 → 2009/09/02

Subject classification (UKÄ)

Electrical Engineering, Electronic Engineering, Information Engineering

Access to Document

10.1109/ICDSC.2009.5289359

Cite this

@inproceedings{8ac12b3ddf60402f9d8b881d8b96d453,

title = "Abnormal Motion Detection in a Real-Time Smart Camera System",

abstract = "This paper discusses a method for abnormal motion detection and its real-time implementation on a smart camera. Abnormal motion detection is a surveillance technique that only allows unfamiliar motion patterns to result in alarms. Our approach has two phases. First, normal motion is detected and the motion paths are trained, building up a model of normal behaviour. Feed-forward neural networks are here used for learning. Second, abnormal motion is detected by comparing the current observed motion to the stored model. A complete demonstration system is implemented to detect abnormal paths of persons moving in an indoor space. As platform we used a wireless smart camera system containing an SIMD (Single. Instruction Multiple-Data) processor for real-time detection of moving persons and an 8051 microcontroller for implementing the neural network. The 8051 also functions as camera host to broadcast abnormal events using Zig Bee to a main network system.",

author = "Tehrani, {Mona Akbarniai} and Richard Kleihorst and Peter Meijer and Lambert Spaanenburg",

year = "2009",

doi = "10.1109/ICDSC.2009.5289359",

language = "English",

isbn = "978-1-4244-4620-9",

pages = "410--416",

booktitle = "Third ACM/IEEE International Conference on Distributed Smart Cameras, 2009. ICDSC 2009",

publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "3rd ACM/IEEE International Conference on Distributed Smart Cameras ; Conference date: 30-08-2009 Through 02-09-2009",

}

Tehrani, MA, Kleihorst, R, Meijer, P & Spaanenburg, L 2009, Abnormal Motion Detection in a Real-Time Smart Camera System. in Third ACM/IEEE International Conference on Distributed Smart Cameras, 2009. ICDSC 2009. IEEE - Institute of Electrical and Electronics Engineers Inc., pp. 410-416, 3rd ACM/IEEE International Conference on Distributed Smart Cameras, Como, Italy, 2009/08/30. https://doi.org/10.1109/ICDSC.2009.5289359

Abnormal Motion Detection in a Real-Time Smart Camera System. / Tehrani, Mona Akbarniai; Kleihorst, Richard; Meijer, Peter; Spaanenburg, Lambert.

Third ACM/IEEE International Conference on Distributed Smart Cameras, 2009. ICDSC 2009. IEEE - Institute of Electrical and Electronics Engineers Inc., 2009. p. 410-416.

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - Abnormal Motion Detection in a Real-Time Smart Camera System

AU - Tehrani, Mona Akbarniai

AU - Kleihorst, Richard

AU - Meijer, Peter

AU - Spaanenburg, Lambert

PY - 2009

Y1 - 2009

N2 - This paper discusses a method for abnormal motion detection and its real-time implementation on a smart camera. Abnormal motion detection is a surveillance technique that only allows unfamiliar motion patterns to result in alarms. Our approach has two phases. First, normal motion is detected and the motion paths are trained, building up a model of normal behaviour. Feed-forward neural networks are here used for learning. Second, abnormal motion is detected by comparing the current observed motion to the stored model. A complete demonstration system is implemented to detect abnormal paths of persons moving in an indoor space. As platform we used a wireless smart camera system containing an SIMD (Single. Instruction Multiple-Data) processor for real-time detection of moving persons and an 8051 microcontroller for implementing the neural network. The 8051 also functions as camera host to broadcast abnormal events using Zig Bee to a main network system.

AB - This paper discusses a method for abnormal motion detection and its real-time implementation on a smart camera. Abnormal motion detection is a surveillance technique that only allows unfamiliar motion patterns to result in alarms. Our approach has two phases. First, normal motion is detected and the motion paths are trained, building up a model of normal behaviour. Feed-forward neural networks are here used for learning. Second, abnormal motion is detected by comparing the current observed motion to the stored model. A complete demonstration system is implemented to detect abnormal paths of persons moving in an indoor space. As platform we used a wireless smart camera system containing an SIMD (Single. Instruction Multiple-Data) processor for real-time detection of moving persons and an 8051 microcontroller for implementing the neural network. The 8051 also functions as camera host to broadcast abnormal events using Zig Bee to a main network system.

U2 - 10.1109/ICDSC.2009.5289359

DO - 10.1109/ICDSC.2009.5289359

M3 - Paper in conference proceeding

SN - 978-1-4244-4620-9

SP - 410

EP - 416

BT - Third ACM/IEEE International Conference on Distributed Smart Cameras, 2009. ICDSC 2009

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd ACM/IEEE International Conference on Distributed Smart Cameras

Y2 - 30 August 2009 through 2 September 2009

ER -

Abnormal Motion Detection in a Real-Time Smart Camera System

Abstract

Conference

Subject classification (UKÄ)

Access to Document

Fingerprint

Cite this