Concealed object detection with radiometric imaging

Author

Yeom, Seokwon ; Lee, Dong-Su ; Son, Jung-Young ; Jung, Min-Kyoo ; Jang, Yushin ; Jung, Sang-Won ; Lee, Seok-Jae

Author_Institution

Div. of Comput. & Commun. Eng., Daegu Univ., Gyeongsan, South Korea

fYear

2011

fDate

26-30 Sept. 2011

Firstpage

1

Lastpage

4

Abstract

A passive millimeter wave imaging system can detect concealed objects under clothing. In this paper, we address realtime outdoor concealed-object detection and segmentation with a radiometric imaging system. The radiometric imaging system operates around 94 GHz to generate images with a 1 Hz frame rate. Multilevel segmentation clusters pixels according to a Gaussian mixture model. Experimental results confirm that the presented method can recognize a concealed gun carried by a moving human subject.

Keywords

Gaussian processes; image segmentation; millimetre wave imaging; object detection; radiometry; Gaussian mixture model; concealed object detection; concealed objects; multilevel segmentation; outdoor concealed-object detection; outdoor concealed-object segmentation; passive millimeter wave imaging system; radiometric imaging system; Bayesian methods; Clustering algorithms; Fitting; Image segmentation; Imaging; Millimeter wave radar; Gaussian mixture modeling; concealed object detection; image segmentation; passive millimeter; unsupervised learing;

fLanguage

English

Publisher

ieee

Conference_Titel

Synthetic Aperture Radar (APSAR), 2011 3rd International Asia-Pacific Conference on

Conference_Location

Seoul

Print_ISBN

978-1-4577-1351-4

Type

conf

Filename

6086934