Initiation and tracking of dim target via fusion of feature probabilities with CNN-UM

Hyongsuk Kim, T. Roska, Leon O. Chua, Frank Werblin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

CNN-UM-based automatic target initiation and tracking algorithm with the fusion of feature probabilities has been developed. The probability for each feature is created in the region of influence depending on the reliability and the strength of the feature. For computing the confidence of target, a fusion algorithm employing products of weighted sums of feature probabilities is proposed. New target initiation is done through the temporal accumulation of such confidence and the target decision is done with the confidence value obtained through the probability fusion. Due to the utilization of multiple features of target, robustness of target detection is possessed. On-chip experimental results are included in this paper.

Original languageEnglish
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
Volume1
Publication statusPublished - 2002
Event2002 IEEE International Symposium on Circuits and Systems - Phoenix, AZ, United States
Duration: May 26 2002May 29 2002

Other

Other2002 IEEE International Symposium on Circuits and Systems
CountryUnited States
CityPhoenix, AZ
Period5/26/025/29/02

Fingerprint

Fusion reactions
Target tracking

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Kim, H., Roska, T., Chua, L. O., & Werblin, F. (2002). Initiation and tracking of dim target via fusion of feature probabilities with CNN-UM. In Proceedings - IEEE International Symposium on Circuits and Systems (Vol. 1)

Initiation and tracking of dim target via fusion of feature probabilities with CNN-UM. / Kim, Hyongsuk; Roska, T.; Chua, Leon O.; Werblin, Frank.

Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 1 2002.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, H, Roska, T, Chua, LO & Werblin, F 2002, Initiation and tracking of dim target via fusion of feature probabilities with CNN-UM. in Proceedings - IEEE International Symposium on Circuits and Systems. vol. 1, 2002 IEEE International Symposium on Circuits and Systems, Phoenix, AZ, United States, 5/26/02.
Kim H, Roska T, Chua LO, Werblin F. Initiation and tracking of dim target via fusion of feature probabilities with CNN-UM. In Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 1. 2002
Kim, Hyongsuk ; Roska, T. ; Chua, Leon O. ; Werblin, Frank. / Initiation and tracking of dim target via fusion of feature probabilities with CNN-UM. Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 1 2002.
@inproceedings{df5e3bbc4c984341a7541963c803813a,
title = "Initiation and tracking of dim target via fusion of feature probabilities with CNN-UM",
abstract = "CNN-UM-based automatic target initiation and tracking algorithm with the fusion of feature probabilities has been developed. The probability for each feature is created in the region of influence depending on the reliability and the strength of the feature. For computing the confidence of target, a fusion algorithm employing products of weighted sums of feature probabilities is proposed. New target initiation is done through the temporal accumulation of such confidence and the target decision is done with the confidence value obtained through the probability fusion. Due to the utilization of multiple features of target, robustness of target detection is possessed. On-chip experimental results are included in this paper.",
author = "Hyongsuk Kim and T. Roska and Chua, {Leon O.} and Frank Werblin",
year = "2002",
language = "English",
volume = "1",
booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",

}

TY - GEN

T1 - Initiation and tracking of dim target via fusion of feature probabilities with CNN-UM

AU - Kim, Hyongsuk

AU - Roska, T.

AU - Chua, Leon O.

AU - Werblin, Frank

PY - 2002

Y1 - 2002

N2 - CNN-UM-based automatic target initiation and tracking algorithm with the fusion of feature probabilities has been developed. The probability for each feature is created in the region of influence depending on the reliability and the strength of the feature. For computing the confidence of target, a fusion algorithm employing products of weighted sums of feature probabilities is proposed. New target initiation is done through the temporal accumulation of such confidence and the target decision is done with the confidence value obtained through the probability fusion. Due to the utilization of multiple features of target, robustness of target detection is possessed. On-chip experimental results are included in this paper.

AB - CNN-UM-based automatic target initiation and tracking algorithm with the fusion of feature probabilities has been developed. The probability for each feature is created in the region of influence depending on the reliability and the strength of the feature. For computing the confidence of target, a fusion algorithm employing products of weighted sums of feature probabilities is proposed. New target initiation is done through the temporal accumulation of such confidence and the target decision is done with the confidence value obtained through the probability fusion. Due to the utilization of multiple features of target, robustness of target detection is possessed. On-chip experimental results are included in this paper.

UR - http://www.scopus.com/inward/record.url?scp=0036283461&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036283461&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0036283461

VL - 1

BT - Proceedings - IEEE International Symposium on Circuits and Systems

ER -