A comparison of two Monte Carlo algorithms for 3D vehicle trajectory reconstruction in roundabouts

被引：8

作者：

Romanoni, Andrea ^{[1
]}

Mussone, Lorenzo ^{[2
]}

Rizzi, Davide ^{[1
]}

Matteucci, Matteo ^{[1
]}

机构：

[1] Politecn Milan, DEIB, I-20133 Milan, Italy

[2] Politecn Milan, ABC, I-20133 Milan, Italy

来源：

PATTERN RECOGNITION LETTERS | 2015年 / 51卷

关键词：

Vehicular trajectory; 3D visual tracking; Monte Carlo smoothing; Model based tracking; OBJECT TRACKING;

D O I：

10.1016/j.patrec.2014.09.003

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Visual vehicular trajectory analysis and reconstruction represent two relevant tasks both for safety and capacity concerns in road transportation. Especially in the presence of roundabouts, the perspective effects on vehicles projection on the image plane can be overcome by reconstructing their 3D positions with a 3D tracking algorithm. In this paper we compare two different Monte Carlo approaches to 3D model-based tracking: the Viterbi algorithm and the Particle Smoother. We tested the algorithms on a simulated dataset and on real data collected in one working roundabout with two different setups (single and multiple cameras). The Viterbi algorithm estimates the Maximum A-Posteriori solution from a sample based state discretization, but, thanks to its continuous state representation, the Particle Smoother overcomes the Viterbi algorithm showing better performance and accuracy. (C) 2014 Elsevier B.V. All rights reserved.

引用

页码：79 / 85

页数：7

共 50 条

[21] Photon Propagation Correction in 3D Photoacoustic Image Reconstruction using Monte Carlo Simulation
Cheong, Yaw Jye
Stantz, Keith M.
PHOTONS PLUS ULTRASOUND: IMAGING AND SENSING 2010, 2010, 7564
[22] Data rebinning and reconstruction in 3D PET/CT oncological studies: a Monte Carlo evaluation
Rizzo, G
Castiglioni, I
Russo, G
Gilardi, MC
Panzacchi, A
Fazio, F
2004 IEEE NUCLEAR SCIENCE SYMPOSIUM CONFERENCE RECORD, VOLS 1-7, 2004, : 3109 - 3112
[23] Effect of noise and modeling errors on the reliability of fully 3D Monte Carlo reconstruction in SPECT
Lazaro, D
El Bitar, Z
Breton, V
Buvat, I
2004 IEEE NUCLEAR SCIENCE SYMPOSIUM CONFERENCE RECORD, VOLS 1-7, 2004, : 2534 - 2537
[24] 3D Semantic Trajectory Reconstruction from 3D Pixel Continuum
Yoon, Jae Shin
Li, Ziwei
Park, Hyun Soo
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 5060 - 5069
[25] A comparison of 3D static light-scattering experiments with Monte Carlo simulations
Aberle, LB
Kleemeier, M
Hülstede, P
Wiegand, S
Schröer, W
Staude, W
JOURNAL OF PHYSICS D-APPLIED PHYSICS, 1999, 32 (01) : 22 - 29
[26] MONTE-CARLO STUDY OF 3D VESICLES
ORLANDINI, E
TESI, MC
PHYSICA A, 1992, 185 (1-4): : 160 - 165
[27] 3D Ising nonuniversality: A Monte Carlo study
Schulte, M
Drope, C
INTERNATIONAL JOURNAL OF MODERN PHYSICS C, 2005, 16 (08): : 1217 - 1224
[28] 3D Vehicle Trajectory Reconstruction in Monocular Video Data Using Environment Structure Constraints
Bullinger, Sebastian
Bodensteiner, Christoph
Arens, Michael
Stiefelhagen, Rainer
COMPUTER VISION - ECCV 2018, PT X, 2018, 11214 : 36 - 51
[29] Application of Monte Carlo Algorithms to Cardiac Imaging Reconstruction
Zhou, J.
Leja, A. G.
Salvatori, M.
Della Latta, D.
Di Fulvio, A.
CURRENT PHARMACEUTICAL DESIGN, 2021, 27 (16) : 1960 - 1972
[30] Geometric algorithms for 3D interface reconstruction
Ahn, Hyung Taek
Shashkov, Mikhail
PROCEEDINGS OF THE 16TH INTERNATIONAL MESHING ROUNDTABLE, 2008, : 405 - +

← 1 2 3 4 5 →