Home > Research > Publications & Outputs > RTSDE
View graph of relations

RTSDE: recursive total-sum-distances-based density estimation approach and its application for autonomous real-time video analytics

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

RTSDE : recursive total-sum-distances-based density estimation approach and its application for autonomous real-time video analytics. / Angelov, Plamen; Wilding, Ashley.

2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS). Orlando, FL, USA : IEEE, 2014. p. 81-86.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Angelov, P & Wilding, A 2014, RTSDE: recursive total-sum-distances-based density estimation approach and its application for autonomous real-time video analytics. in 2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS). IEEE, Orlando, FL, USA, pp. 81-86, 2014 IEEE Symposium Series on Computational Intelligence, Orlando, United States, 9/12/14. https://doi.org/10.1109/EALS.2014.7009507

APA

Vancouver

Author

Angelov, Plamen ; Wilding, Ashley. / RTSDE : recursive total-sum-distances-based density estimation approach and its application for autonomous real-time video analytics. 2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS). Orlando, FL, USA : IEEE, 2014. pp. 81-86

Bibtex

@inproceedings{9ab754cd2c914f80a060d5726cd11488,
title = "RTSDE: recursive total-sum-distances-based density estimation approach and its application for autonomous real-time video analytics",
abstract = "In this paper, we propose a new approach to data density estimation based on the total sum of distances from a data point, and the recently introduced Recursive Density Estimation technique. It is suitable for autonomous real-time video analytics problems, and has been specifically designed to be executed very fast; it uses integer-only arithmetic with no divisions and no floating point numbers (no FLOPs), making it particularly useful in situations where a hardware floating point unit may not be available, such as on embedded hardware and digital signalprocessors, allowing for high definition video to be processed for novelty detection in real-time. ",
keywords = "Kernel Density Estimation, recursive density estimation (RDE), background subtraction, novelty detection, video analytics, embedded systems, Digital Signal Processors, integer-only arithmetic, no FLOPs",
author = "Plamen Angelov and Ashley Wilding",
note = "Date of Acceptance 06/09/2014; 2014 IEEE Symposium Series on Computational Intelligence ; Conference date: 09-12-2014 Through 12-12-2014",
year = "2014",
month = dec,
day = "9",
doi = "10.1109/EALS.2014.7009507",
language = "English",
isbn = "9781479944958",
pages = "81--86",
booktitle = "2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - RTSDE

T2 - 2014 IEEE Symposium Series on Computational Intelligence

AU - Angelov, Plamen

AU - Wilding, Ashley

N1 - Date of Acceptance 06/09/2014

PY - 2014/12/9

Y1 - 2014/12/9

N2 - In this paper, we propose a new approach to data density estimation based on the total sum of distances from a data point, and the recently introduced Recursive Density Estimation technique. It is suitable for autonomous real-time video analytics problems, and has been specifically designed to be executed very fast; it uses integer-only arithmetic with no divisions and no floating point numbers (no FLOPs), making it particularly useful in situations where a hardware floating point unit may not be available, such as on embedded hardware and digital signalprocessors, allowing for high definition video to be processed for novelty detection in real-time.

AB - In this paper, we propose a new approach to data density estimation based on the total sum of distances from a data point, and the recently introduced Recursive Density Estimation technique. It is suitable for autonomous real-time video analytics problems, and has been specifically designed to be executed very fast; it uses integer-only arithmetic with no divisions and no floating point numbers (no FLOPs), making it particularly useful in situations where a hardware floating point unit may not be available, such as on embedded hardware and digital signalprocessors, allowing for high definition video to be processed for novelty detection in real-time.

KW - Kernel Density Estimation

KW - recursive density estimation (RDE)

KW - background subtraction

KW - novelty detection

KW - video analytics

KW - embedded systems

KW - Digital Signal Processors

KW - integer-only arithmetic

KW - no FLOPs

U2 - 10.1109/EALS.2014.7009507

DO - 10.1109/EALS.2014.7009507

M3 - Conference contribution/Paper

SN - 9781479944958

SP - 81

EP - 86

BT - 2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS)

PB - IEEE

CY - Orlando, FL, USA

Y2 - 9 December 2014 through 12 December 2014

ER -