A comparison of 3D interest point descriptors with application to airport baggage object detection in complex CT imagery

被引：85

作者：

Flitton, Greg ^{[1
]}

Breckon, Toby P. ^{[1
]}

Megherbi, Najla ^{[1
]}

机构：

[1] Cranfield Univ, Sch Engn, Appl Math & Comp Grp, Cranfield MK43 0AL, Beds, England

来源：

PATTERN RECOGNITION | 2013年 / 46卷 / 09期

关键词：

CT baggage scan; Threat detection; Object recognition; 3D feature descriptors; CT object recognition; 3D SIFT; ARTIFACTS; SCALE; SIFT; REDUCTION; TRANSFORM; FEATURES; SHAPE;

D O I：

10.1016/j.patcog.2013.02.008

中图分类号：

TP18 [人工智能理论];

学科分类号：

140502 [人工智能];

摘要：

We present an experimental comparison of 3D feature descriptors with application to threat detection in Computed Tomography (CT) airport baggage imagery. The detectors range in complexity from a basic local density descriptor, through local region histograms and three-dimensional (3D) extensions to both to the RIFT descriptor and the seminal SIFT feature descriptor. We show that, in the complex CT imagery domain containing a high degree of noise and imaging artefacts, a specific instance object recognition system using simpler descriptors appears to outperform a more complex RIFT/SIFT solution. Recognition rates in excess of 95% are demonstrated with minimal false-positive rates for a set of exemplar 3D objects. (C) 2013 Elsevier Ltd. All rights reserved.

引用

页码：2420 / 2436

页数：17

共 44 条

[1]

Improving weapon detection in single energy X-ray images through pseudocoloring [J].

Abidi, Besma R. ;

Zheng, Yue ;

Gribok, Andrei V. ;

Abidi, Mongi A. .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2006, 36 (06) :784-796

[2]

Allaire Stephane, 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), P1, DOI 10.1109/CVPRW.2008.4563023

[3]

[Anonymous], 2005, PROC CVPR IEEE

[4]

[Anonymous], 2008, IEEE NUCL SCI S C RE

[5]

[Anonymous], P 4 ALV VIS C

[6]

[Anonymous], 2009, ACM INT C PROCEEDING, DOI DOI 10.1145/1558607.1558630

[7]

[Anonymous], P BRIT MACH VIS C

[8]

LEAST-SQUARES FITTING OF 2 3-D POINT SETS [J].