ColourFAST: GPU-based Feature Point Detection and Tracking on Mobile Devices

被引:0
|
作者
Ensor, Andrew [1 ]
Hall, Seth [1 ]
机构
[1] AUT Univ, Sch Comp & Math Sci, Auckland, New Zealand
来源
PROCEEDINGS OF 2013 28TH INTERNATIONAL CONFERENCE ON IMAGE AND VISION COMPUTING NEW ZEALAND (IVCNZ 2013) | 2013年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A realtime feature point detection algorithm called ColourFAST is introduced. ColourFAST extracts vector-based feature strength and direction measures from the colour channels of any pixel in an image. The extracted information is applied to create an effective feature point tracker. These feature point. and tracker algorithms have a pipeline design optimized for GPU processors. Results are provided for an implementation on mobile devices developed using programmable shaders. Its performance demonstrates several improvements over conventional FAST feature point detection and Lucas-Kanade tracking.
引用
收藏
页码:124 / 129
页数:6
相关论文
共 50 条
  • [41] GPU-based aim point optimization for solar tower power plants
    Oberkirsch, Laurin
    Quinto, Daniel Maldonado
    Schwarzbozl, Peter
    Hoffschmidt, Bernhard
    SOLAR ENERGY, 2021, 220 : 1089 - 1098
  • [42] A GPU-based implementation of Motion Detection from a Moving Platform
    Yu, Qian
    Medioni, Gerard
    2008 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, VOLS 1-3, 2008, : 1078 - 1083
  • [43] A GPU-based machine learning approach for detection of botnet attacks
    Motylinski, Michal
    MacDermott, Aine
    Iqbal, Farkhund
    Shah, Babar
    COMPUTERS & SECURITY, 2022, 123
  • [44] GPU-based parallel collision detection for fast motion planning
    Pan, Jia
    Manocha, Dinesh
    INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2012, 31 (02): : 187 - 200
  • [45] GPU-BASED FLUID SIMULATION WITH FAST COLLISION DETECTION ON BOUNDARIES
    Wu, Jiawen
    Zhang, Fengquan
    Shen, Xukun
    INTERNATIONAL JOURNAL OF MODELING SIMULATION AND SCIENTIFIC COMPUTING, 2012, 3 (01)
  • [46] Signature Identification via Efficient Feature Selection and GPU-based SVM Classifier
    Ribeiro, Bernardete
    Lopes, Noel
    Goncalves, Joao
    PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, : 1138 - 1145
  • [47] GPU-Based Genetic Programming for Faster Feature Extraction in Binary Image Classification
    Zhang, Rui
    Sun, Yanan
    Zhang, Mengjie
    IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2024, 28 (06) : 1590 - 1604
  • [48] GPU-based smooth free-form deformation with sharp feature awareness
    Cui, Yuanmin
    Feng, Jieqing
    COMPUTER AIDED GEOMETRIC DESIGN, 2015, 35-36 : 69 - 81
  • [49] GPU-based chromatic co-occurrence matrices for tracking moving objects
    Issam Elafi
    Mohamed Jedra
    Noureddine Zahid
    Journal of Real-Time Image Processing, 2020, 17 : 1197 - 1210
  • [50] A FEATURE-BASED OBJECT TRACKING APPROACH FOR REALTIME IMAGE PROCESSING ON MOBILE DEVICES
    Fan, Lixin
    Riihimaki, Mikko
    Kunttu, Iivari
    2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, : 3921 - 3924