Target detection using FPGA structures

Aleksander Nawrat; Krzysztof Daniec

Target detection using FPGA structures

Department of Automatic Control and Robotics (RAU/RAU3)

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper presents an implementation in the FPGA structure Xilinx HW-V2000-MLTA target detection method using neural network method in the stream possessed from SONY HDR-HClE camera. The technique is designed to run in real-time using off-the-shelf hardware for use on an unmanned vehicle-helicopter. Our methodology is to quickly detect candidate locations using neural network. Additional processing is then applied to the candidate locations in order to eliminate false alarms. This technique have been tested on a set of imagery from a live - test range with outstanding results.

Original language	English
Pages	344-348
Number of pages	5
Publication status	Published - 2006
Event	10th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2006, Jointly with the 12th International Conference on Information Systems Analysis and Synthesis, ISAS 2006 - Orlando, FL, United States Duration: 16 Jul 2006 → 19 Jul 2006

Conference

Conference	10th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2006, Jointly with the 12th International Conference on Information Systems Analysis and Synthesis, ISAS 2006
Country/Territory	United States
City	Orlando, FL
Period	16/07/06 → 19/07/06

Keywords

FPGA
Neural networks
Pattern recognition
Target detection

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Information Systems

Cite this

@conference{0f3180e4cefb4ed38e9ae6129dadfbcc,

title = "Target detection using FPGA structures",

abstract = "This paper presents an implementation in the FPGA structure Xilinx HW-V2000-MLTA target detection method using neural network method in the stream possessed from SONY HDR-HClE camera. The technique is designed to run in real-time using off-the-shelf hardware for use on an unmanned vehicle-helicopter. Our methodology is to quickly detect candidate locations using neural network. Additional processing is then applied to the candidate locations in order to eliminate false alarms. This technique have been tested on a set of imagery from a live - test range with outstanding results.",

keywords = "FPGA, Neural networks, Pattern recognition, Target detection",

author = "Aleksander Nawrat and Krzysztof Daniec",

year = "2006",

language = "English",

pages = "344--348",

note = "10th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2006, Jointly with the 12th International Conference on Information Systems Analysis and Synthesis, ISAS 2006 ; Conference date: 16-07-2006 Through 19-07-2006",

}

Target detection using FPGA structures. / Nawrat, Aleksander ; Daniec, Krzysztof.
2006. 344-348 Paper presented at 10th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2006, Jointly with the 12th International Conference on Information Systems Analysis and Synthesis, ISAS 2006, Orlando, FL, United States.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Target detection using FPGA structures

AU - Nawrat, Aleksander

AU - Daniec, Krzysztof

PY - 2006

Y1 - 2006

N2 - This paper presents an implementation in the FPGA structure Xilinx HW-V2000-MLTA target detection method using neural network method in the stream possessed from SONY HDR-HClE camera. The technique is designed to run in real-time using off-the-shelf hardware for use on an unmanned vehicle-helicopter. Our methodology is to quickly detect candidate locations using neural network. Additional processing is then applied to the candidate locations in order to eliminate false alarms. This technique have been tested on a set of imagery from a live - test range with outstanding results.

AB - This paper presents an implementation in the FPGA structure Xilinx HW-V2000-MLTA target detection method using neural network method in the stream possessed from SONY HDR-HClE camera. The technique is designed to run in real-time using off-the-shelf hardware for use on an unmanned vehicle-helicopter. Our methodology is to quickly detect candidate locations using neural network. Additional processing is then applied to the candidate locations in order to eliminate false alarms. This technique have been tested on a set of imagery from a live - test range with outstanding results.

KW - FPGA

KW - Neural networks

KW - Pattern recognition

KW - Target detection

UR - https://www.scopus.com/pages/publications/84867276740

M3 - Paper

AN - SCOPUS:84867276740

SP - 344

EP - 348

T2 - 10th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2006, Jointly with the 12th International Conference on Information Systems Analysis and Synthesis, ISAS 2006

Y2 - 16 July 2006 through 19 July 2006

ER -

Target detection using FPGA structures

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this