3D ISAR Imaging: The Alignment Problem

Jinjian Cai; Marco Martorella; Quanhua Liu; Zegang Ding; Elisa Giusti

doi:10.1109/RADAR41533.2019.171419

3D ISAR Imaging: The Alignment Problem

Jinjian Cai, Marco Martorella, Quanhua Liu, Zegang Ding, Elisa Giusti

Engineering

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

2 Citations (Scopus)

Abstract

Inverse synthetic aperture radar (ISAR) is capable of producing two-dimensional (2D) and three-dimensional (3D) images of noncooperative targets. Compared to 2D ISAR images, 3D ISAR reconstruction can provide not only range and cross-range information, but also the height information of the target, which is of great significance for automatic target recognition (ATR). The alignment between the point-like 3D ISAR reconstructions of targets and the targets' models, such as CAD models, becomes one of the essential issues in ATR by 3D ISAR reconstruction. In this paper, we introduce an approach to address the proposed alignment problem. The alignment problem can be decomposed into two steps, a coarse alignment and an accurate alignment. The coarse alignment can be accomplished by means of the principal component analysis (PCA), while the accurate alignment can be achieved by iteration closest points (ICP) algorithm. In order to simulate real radar scenarios, target self-occlusion and reconstruction errors are taken into consideration. The simulation results verify the validity of the proposed methods.

Original language	English
Title of host publication	2019 International Radar Conference, RADAR 2019
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISBN (Electronic)	9781728126609
DOIs	https://doi.org/10.1109/RADAR41533.2019.171419
Publication status	Published - Sept 2019
Event	2019 International Radar Conference, RADAR 2019 - Toulon, France Duration: 23 Sept 2019 → 27 Sept 2019

Publication series

Name	2019 International Radar Conference, RADAR 2019

Conference

Conference	2019 International Radar Conference, RADAR 2019
Country/Territory	France
City	Toulon
Period	23/09/19 → 27/09/19

Bibliographical note

Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 61771050, in part by the 111 Project of China under Grant B14010, and in part by the Chang Jiang Scholars Programme under Grant No. T2012122.

Publisher Copyright:
© 2019 IEEE.

Keywords

3D ISAR reconstruction
CAD model
Inverse synthetic aperture radar (ISAR)
iteration closest points (ICP)
point cloud alignment
principal component analysis (PCA)

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Signal Processing
Instrumentation

Access to Document

10.1109/RADAR41533.2019.171419

Cite this

@inproceedings{319f8df153ca4f99af961efdfb86c270,

title = "3D ISAR Imaging: The Alignment Problem",

abstract = "Inverse synthetic aperture radar (ISAR) is capable of producing two-dimensional (2D) and three-dimensional (3D) images of noncooperative targets. Compared to 2D ISAR images, 3D ISAR reconstruction can provide not only range and cross-range information, but also the height information of the target, which is of great significance for automatic target recognition (ATR). The alignment between the point-like 3D ISAR reconstructions of targets and the targets' models, such as CAD models, becomes one of the essential issues in ATR by 3D ISAR reconstruction. In this paper, we introduce an approach to address the proposed alignment problem. The alignment problem can be decomposed into two steps, a coarse alignment and an accurate alignment. The coarse alignment can be accomplished by means of the principal component analysis (PCA), while the accurate alignment can be achieved by iteration closest points (ICP) algorithm. In order to simulate real radar scenarios, target self-occlusion and reconstruction errors are taken into consideration. The simulation results verify the validity of the proposed methods.",

keywords = "3D ISAR reconstruction, CAD model, Inverse synthetic aperture radar (ISAR), iteration closest points (ICP), point cloud alignment, principal component analysis (PCA)",

author = "Jinjian Cai and Marco Martorella and Quanhua Liu and Zegang Ding and Elisa Giusti",

note = "Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 61771050, in part by the 111 Project of China under Grant B14010, and in part by the Chang Jiang Scholars Programme under Grant No. T2012122. Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 International Radar Conference, RADAR 2019 ; Conference date: 23-09-2019 Through 27-09-2019",

year = "2019",

month = sep,

doi = "10.1109/RADAR41533.2019.171419",

language = "English",

series = "2019 International Radar Conference, RADAR 2019",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

booktitle = "2019 International Radar Conference, RADAR 2019",

}

Cai, J, Martorella, M, Liu, Q, Ding, Z & Giusti, E 2019, 3D ISAR Imaging: The Alignment Problem. in 2019 International Radar Conference, RADAR 2019., 9078906, 2019 International Radar Conference, RADAR 2019, Institute of Electrical and Electronics Engineers (IEEE), 2019 International Radar Conference, RADAR 2019, Toulon, France, 23/09/19. https://doi.org/10.1109/RADAR41533.2019.171419

TY - GEN

T1 - 3D ISAR Imaging

T2 - 2019 International Radar Conference, RADAR 2019

AU - Cai, Jinjian

AU - Martorella, Marco

AU - Liu, Quanhua

AU - Ding, Zegang

AU - Giusti, Elisa

N1 - Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 61771050, in part by the 111 Project of China under Grant B14010, and in part by the Chang Jiang Scholars Programme under Grant No. T2012122. Publisher Copyright: © 2019 IEEE.

PY - 2019/9

Y1 - 2019/9

N2 - Inverse synthetic aperture radar (ISAR) is capable of producing two-dimensional (2D) and three-dimensional (3D) images of noncooperative targets. Compared to 2D ISAR images, 3D ISAR reconstruction can provide not only range and cross-range information, but also the height information of the target, which is of great significance for automatic target recognition (ATR). The alignment between the point-like 3D ISAR reconstructions of targets and the targets' models, such as CAD models, becomes one of the essential issues in ATR by 3D ISAR reconstruction. In this paper, we introduce an approach to address the proposed alignment problem. The alignment problem can be decomposed into two steps, a coarse alignment and an accurate alignment. The coarse alignment can be accomplished by means of the principal component analysis (PCA), while the accurate alignment can be achieved by iteration closest points (ICP) algorithm. In order to simulate real radar scenarios, target self-occlusion and reconstruction errors are taken into consideration. The simulation results verify the validity of the proposed methods.

AB - Inverse synthetic aperture radar (ISAR) is capable of producing two-dimensional (2D) and three-dimensional (3D) images of noncooperative targets. Compared to 2D ISAR images, 3D ISAR reconstruction can provide not only range and cross-range information, but also the height information of the target, which is of great significance for automatic target recognition (ATR). The alignment between the point-like 3D ISAR reconstructions of targets and the targets' models, such as CAD models, becomes one of the essential issues in ATR by 3D ISAR reconstruction. In this paper, we introduce an approach to address the proposed alignment problem. The alignment problem can be decomposed into two steps, a coarse alignment and an accurate alignment. The coarse alignment can be accomplished by means of the principal component analysis (PCA), while the accurate alignment can be achieved by iteration closest points (ICP) algorithm. In order to simulate real radar scenarios, target self-occlusion and reconstruction errors are taken into consideration. The simulation results verify the validity of the proposed methods.

KW - 3D ISAR reconstruction

KW - CAD model

KW - Inverse synthetic aperture radar (ISAR)

KW - iteration closest points (ICP)

KW - point cloud alignment

KW - principal component analysis (PCA)

UR - http://www.scopus.com/inward/record.url?scp=85084957678&partnerID=8YFLogxK

U2 - 10.1109/RADAR41533.2019.171419

DO - 10.1109/RADAR41533.2019.171419

M3 - Conference contribution

AN - SCOPUS:85084957678

T3 - 2019 International Radar Conference, RADAR 2019

BT - 2019 International Radar Conference, RADAR 2019

PB - Institute of Electrical and Electronics Engineers (IEEE)

Y2 - 23 September 2019 through 27 September 2019

ER -

3D ISAR Imaging: The Alignment Problem

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this