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
收藏
页码：2325 / 2328
页数：4
相关论文
共 50 条
  • [1] Optical flow computation on Compute Unified Device Architecture
    Mizukami, Yoshiki
    Tadamura, Katsumi
    14TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS, 2007, : 179 - +
  • [2] Accelerated Optical Flow Function Algorithm Using Compute Unified Device Architecture
    Aziz, Mohd Zafran bin Abdul
    Ibai, Petrus Simon Anak
    Adnan, Syed Farid Syed
    Rohmad, Mohd Saufy
    Bin Makhtar, Ahmad Khushairy
    Ghani, M. A. A.
    INTERNATIONAL SYMPOSIUM ON ROBOTICS AND INTELLIGENT SENSORS 2012 (IRIS 2012), 2012, 41 : 1343 - 1352
  • [3] Parallel Character Reconstruction Expending Compute Unified Device Architecture
    Pal, Anita
    Srivastava, Kamal Kumar
    Kumar, Atul
    ADVANCES IN COMPUTING AND INFORMATION TECHNOLOGY, VOL 2, 2013, 177 : 639 - 648
  • [4] Parallel Computing Model for Assembly Accuracy with Compute Unified Device Architecture
    Su Y.
    Liu H.
    Su Q.
    Jia R.
    Hong J.
    Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University, 2023, 57 (06): : 105 - 114
  • [5] Compute Unified Device Architecture-Based Parallel Dose-Volume Histogram Computation
    Wang, Yangping
    Deng, Chong
    Li, Lian
    Dang, Jianwu
    JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, 2015, 5 (04) : 833 - 840
  • [6] MOTION-BASED REGION GROWING SEGMENTATION OF IMAGE SEQUENCES
    Lu Guanming Bi Houjie Jiang Ping(Department of Information Engineering
    Journal of Electronics(China), 2000, (01) : 53 - 58
  • [7] Bayesian approaches to motion-based image and video segmentation
    Cremers, Daniel
    COMPLEX MOTION, 2007, 3417 : 104 - 123
  • [8] Motion-based segmentation and region tracking in image sequences
    Badenas, J
    Sanchiz, JM
    Pla, F
    PATTERN RECOGNITION, 2001, 34 (03) : 661 - 670
  • [9] SOLUTIONS FOR OPTIMIZING THE PARALLEL REDUCTION ALGORITHM USING THE COMPUTE UNIFIED DEVICE ARCHITECTURE
    Lungu, Ion
    Petrosanu, Dana-Mihaela
    Pirjan, Alexandru
    INTERNATIONAL CONFERENCE ON INFORMATICS IN ECONOMY, 2012, : 7 - +
  • [10] No role for motion blur in either motion detection or motion-based image segmentation
    Wichmann, FA
    Henning, GB
    JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1998, 15 (02): : 297 - 306
12345