Neural network classifiers for automated video surveillance

Tony Jan; Massimo Piccardi; Thomas Hintz

doi:10.1109/NNSP.2003.1318072

Neural network classifiers for automated video surveillance

Tony Jan, Massimo Piccardi, Thomas Hintz

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

4 Citations (Scopus)

Abstract

In automated visual surveillance applications, detection of suspicious human behaviors is of great practical importance. However due to random nature of human movements, reliable classification of suspicious human movements can be very difficult. Artificial Neural Network (ANN) classifiers can perform well however their computational requirements can be very large for real time implementation. In this paper, a data-based modeling neural network such as Modified Probabilistic Neural Network (MPNN) is introduced which partitions the decision space nonlinearly in order to achieve reliable classification, however still with acceptable computations. The experiment shows that the compact MPNN attains good classification performance compared to t h a t of other larger conventional neural network based classifiers such as Multilayer Perceptron (MLP) and Self Organising Map (SOM).

Original language	English
Title of host publication	2003 IEEE 13th Workshop on Neural Networks for Signal Processing, NNSP 2003
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	729-738
Number of pages	10
ISBN (Electronic)	0780381777
DOIs	https://doi.org/10.1109/NNSP.2003.1318072
Publication status	Published - 2003
Externally published	Yes
Event	13th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2003 - Toulouse, France Duration: 17 Sept 2003 → 19 Sept 2003

Publication series

Name	Neural Networks for Signal Processing - Proceedings of the IEEE Workshop
Volume	2003-January

Conference

Conference	13th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2003
Country/Territory	France
City	Toulouse
Period	17/09/03 → 19/09/03

Access to Document

10.1109/NNSP.2003.1318072

Cite this

Jan, T., Piccardi, M., & Hintz, T. (2003). Neural network classifiers for automated video surveillance. In 2003 IEEE 13th Workshop on Neural Networks for Signal Processing, NNSP 2003 (pp. 729-738). Article 1318072 (Neural Networks for Signal Processing - Proceedings of the IEEE Workshop; Vol. 2003-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NNSP.2003.1318072

@inproceedings{15c0698d11974f92adaec906418d731e,

title = "Neural network classifiers for automated video surveillance",

abstract = "In automated visual surveillance applications, detection of suspicious human behaviors is of great practical importance. However due to random nature of human movements, reliable classification of suspicious human movements can be very difficult. Artificial Neural Network (ANN) classifiers can perform well however their computational requirements can be very large for real time implementation. In this paper, a data-based modeling neural network such as Modified Probabilistic Neural Network (MPNN) is introduced which partitions the decision space nonlinearly in order to achieve reliable classification, however still with acceptable computations. The experiment shows that the compact MPNN attains good classification performance compared to t h a t of other larger conventional neural network based classifiers such as Multilayer Perceptron (MLP) and Self Organising Map (SOM).",

author = "Tony Jan and Massimo Piccardi and Thomas Hintz",

note = "Publisher Copyright: {\textcopyright} 2003 IEEE.; 13th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2003 ; Conference date: 17-09-2003 Through 19-09-2003",

year = "2003",

doi = "10.1109/NNSP.2003.1318072",

language = "English",

series = "Neural Networks for Signal Processing - Proceedings of the IEEE Workshop",

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

pages = "729--738",

booktitle = "2003 IEEE 13th Workshop on Neural Networks for Signal Processing, NNSP 2003",

}

Jan, T, Piccardi, M & Hintz, T 2003, Neural network classifiers for automated video surveillance. in 2003 IEEE 13th Workshop on Neural Networks for Signal Processing, NNSP 2003., 1318072, Neural Networks for Signal Processing - Proceedings of the IEEE Workshop, vol. 2003-January, Institute of Electrical and Electronics Engineers Inc., pp. 729-738, 13th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2003, Toulouse, France, 17/09/03. https://doi.org/10.1109/NNSP.2003.1318072

Neural network classifiers for automated video surveillance. / Jan, Tony; Piccardi, Massimo; Hintz, Thomas.
2003 IEEE 13th Workshop on Neural Networks for Signal Processing, NNSP 2003. Institute of Electrical and Electronics Engineers Inc., 2003. p. 729-738 1318072 (Neural Networks for Signal Processing - Proceedings of the IEEE Workshop; Vol. 2003-January).

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

TY - GEN

T1 - Neural network classifiers for automated video surveillance

AU - Jan, Tony

AU - Piccardi, Massimo

AU - Hintz, Thomas

PY - 2003

Y1 - 2003

N2 - In automated visual surveillance applications, detection of suspicious human behaviors is of great practical importance. However due to random nature of human movements, reliable classification of suspicious human movements can be very difficult. Artificial Neural Network (ANN) classifiers can perform well however their computational requirements can be very large for real time implementation. In this paper, a data-based modeling neural network such as Modified Probabilistic Neural Network (MPNN) is introduced which partitions the decision space nonlinearly in order to achieve reliable classification, however still with acceptable computations. The experiment shows that the compact MPNN attains good classification performance compared to t h a t of other larger conventional neural network based classifiers such as Multilayer Perceptron (MLP) and Self Organising Map (SOM).

AB - In automated visual surveillance applications, detection of suspicious human behaviors is of great practical importance. However due to random nature of human movements, reliable classification of suspicious human movements can be very difficult. Artificial Neural Network (ANN) classifiers can perform well however their computational requirements can be very large for real time implementation. In this paper, a data-based modeling neural network such as Modified Probabilistic Neural Network (MPNN) is introduced which partitions the decision space nonlinearly in order to achieve reliable classification, however still with acceptable computations. The experiment shows that the compact MPNN attains good classification performance compared to t h a t of other larger conventional neural network based classifiers such as Multilayer Perceptron (MLP) and Self Organising Map (SOM).

UR - http://www.scopus.com/inward/record.url?scp=84925683655&partnerID=8YFLogxK

U2 - 10.1109/NNSP.2003.1318072

DO - 10.1109/NNSP.2003.1318072

M3 - Conference contribution

AN - SCOPUS:84925683655

T3 - Neural Networks for Signal Processing - Proceedings of the IEEE Workshop

SP - 729

EP - 738

BT - 2003 IEEE 13th Workshop on Neural Networks for Signal Processing, NNSP 2003

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2003

Y2 - 17 September 2003 through 19 September 2003

ER -

Neural network classifiers for automated video surveillance

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this