BAYESIAN BASED 3D SHAPE RECONSTRUCTION FROM VIDEO

被引：1

作者：

Ghosh, Nirmalya ^{[1
]}

Bhanu, Bir ^{[1
]}

机构：

[1] Univ Calif Riverside, CRIS, Riverside, CA 92521 USA

来源：

2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5 | 2008年

关键词：

Learning; 3D shape from video;

D O I：

10.1109/ICIP.2008.4711964

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In a video sequence with a 3D rigid object moving, changing shapes of the 2D projections provide interrelated spatio-temporal cues for incremental 3D shape reconstruction. This paper describes a probabilistic approach for intelligent view-integration to build 3D model of vehicles from traffic videos collected from an uncalibrated static camera. The proposed Bayesian net framework allows the handling of uncertainties in a systematic manner. The performance is verified with several types of vehicles in different videos.

引用

页码：1152 / 1155

页数：4

共 16 条

[1]

ATKINSON G, IEEE ICCV 05, P309

[2]

BARBU A, ICCV 05, P572

[3] Partial surface integration based on variational implicit functions and surfaces for 3D model building [J].

Claes, P ;

Vandermeulen, D ;

Van Gool, L ;

Suetens, R .

FIFTH INTERNATIONAL CONFERENCE ON 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS, 2005, :31-38

[4]

GHOSH N, ICPR 06, P272

[5] Detection and classification of vehicles [J].

Gupte, S ;

Masoud, O ;

Martin, RFK ;

Papanikolopoulos, NP .

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2002, 3 (01) :37-47

[6]

HAN D, IEEE ICCV 2005 VS PT

[7]

Hartley Richard., 2017, Multiple View Geometry in Computer Vision

[8]

HORNUNG A, IEEE CVPR 06, P503

[9]

HUANG PH, IEEE CVPR 06, P379

[10] Expandable Bayesian networks for 3D object description from multiple views and multiple mode inputs [J].

Kim, ZW ;

Nevatia, R .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (06) :769-774

← 1 2 →