A PARALLEL MAPPING OF OPTICAL FLOW TO COMPUTE UNIFIED DEVICE ARCHITECTURE FOR MOTION-BASED IMAGE SEGMENTATION

被引：3

作者：

Kuchnio, Peter ^{[1
]}

Capson, David W. ^{[1
]}

机构：

[1] McMaster Univ, Dept Elect & Comp Engn, Hamilton, ON L8S 4L8, Canada

来源：

2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6 | 2009年

关键词：

CUDA; Parallel Optical Flow Algorithm; Motion-based Image Segmentation;

D O I：

10.1109/ICIP.2009.5414402

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A correlation-based optical flow algorithm using Compute Unified Device Architecture (CUDA) technology to achieve fast motion-based image segmentation is described. Using CUDA, a 240 processor GPU implementation of an optimized correlation-based optical flow algorithm allows segmentation to be achieved at high frame rates on high-resolution video sequences. Details of the mapping of the optical flow segmentation algorithm onto the CUDA architecture as well as performance results are given. The performance of the algorithm is further characterized as a function of the search and correlation window radii.

引用

页码：2325 / 2328

页数：4

共 50 条

[41] A Motion-Based Tracking System Using the Lucas-Kanade Optical Flow Method
Leonida, Karl Leyven
Sevilla, Karla Veronica
Mantises, Cyrel O.
2022 14TH INTERNATIONAL CONFERENCE ON COMPUTER AND AUTOMATION ENGINEERING (ICCAE 2022), 2022, : 86 - 90
[42] Spatio-temporal continuous wavelet transforms for motion-based segmentation in real image sequences.
Kong, MQ
Leduc, JP
Ghosh, BK
Wickerhauser, VM
1998 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING - PROCEEDINGS, VOL 2, 1998, : 662 - 666
[43] An overview of optical flow-based approaches for motion segmentation
Anthwal, Shivangi
Ganotra, Dinesh
IMAGING SCIENCE JOURNAL, 2019, 67 (05): : 284 - 294
[44] Compute Unified Device Architecture (CUDA) Based Finite-Difference Time-Domain (FDTD) Implementation
Demir, Veysel
Elsherbeni, Atef Z.
APPLIED COMPUTATIONAL ELECTROMAGNETICS SOCIETY JOURNAL, 2010, 25 (04): : 303 - 314
[45] GPU Compute Unified Device Architecture (CUDA)-based Parallelization of the RRTMG Shortwave Rapid Radiative Transfer Model
Mielikainen, Jarno
Price, Erik
Huang, Bormin
Huang, Hung-Lung Allen
Lee, Tsengdar
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2016, 9 (02) : 921 - 931
[46] Parallel Architecture for Hierarchical Optical Flow Estimation Based on FPGA
Barranco, Francisco
Tomasi, Matteo
Diaz, Javier
Vanegas, Mauricio
Ros, Eduardo
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2012, 20 (06) : 1058 - 1067
[47] New Optical Flow Approach for Motion Segmentation Based on Gamma Distribution
Jung, Cheolkon
Jiao, Licheng
Gong, Maoguo
ADVANCES IN MULTIMEDIA MODELING, PROCEEDINGS, 2010, 5916 : 444 - 453
[48] Video segmentation based on watershed algorithm and optical flow motion estimation
Hsu, WL
Shih, CWJ
MULTIMEDIA STORAGE AND ARCHIVING SYSTEMS IV, 1999, 3846 : 56 - 66
[49] Image Sequence Interpolation Based on Optical Flow, Segmentation, and Optimal Control
Chen, Kanglin
Lorenz, Dirk A.
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2012, 21 (03) : 1020 - 1030
[50] Motion Detection Based on Optical Flow and Self-adaptive Threshold Segmentation
Wei, Shui-gen
Yang, Lei
Chen, Zhen
Liu, Zhen-feng
CEIS 2011, 2011, 15

← 1 2 3 4 5 →