Probabilistic image models for object recognition and pose estimation

被引：0
|
作者：
Hornegger, J [1 ]
Niemann, H [1 ]
机构：
[1] Univ Erlangen Nurnberg, Inst Informat, D-91058 Erlangen, Germany
来源：
STATE-OF-THE-ART IN CONTENT-BASED IMAGE AND VIDEO RETRIEVAL | 2001年 / 22卷
关键词：
probabilistic object models; statistical object recognition;
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：
In this chapter we describe ongoing research that seeks to solve the object recognition and localization problem using a probabilistic framework. Computing statistical object models and calculating pose parameters are considered as nonlinear estimation problems. Recognition is done according to Bayes rule. We give an overview of a wide range of statistical models including a new modeling scheme for intensity images. This novel model avoids feature segmentation and it is discussed in detail including the description of the mathematical framework as well as the experimental evaluation.
引用
收藏
页码：125 / 142
页数：18
相关论文
共 50 条
  • [21] Three-dimensional model-based object recognition and pose estimation using probabilistic principal surfaces
    Chang, KY
    Ghosh, J
    [J]. APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN IMAGE PROCESSING V, 2000, 3962 : 192 - 203
  • [22] A probabilistic framework for object search with 6-DOF pose estimation
    Ma, Jeremy
    Chung, Timothy H.
    Burdick, Joel
    [J]. INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2011, 30 (10): : 1209 - 1228
  • [23] Factorization of view-object manifolds for joint object recognition and pose estimation
    Zhang, Haopeng
    El-Gaaly, Tarek
    Elgammal, Ahmed
    Jiang, Zhiguo
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2015, 139 : 89 - 103
  • [24] Object recognition and pose estimation for industrial applications: A cascade system
    Rocha, Luis F.
    Ferreira, Marcos
    Santos, V.
    Moreira, A. Paulo
    [J]. ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2014, 30 (06) : 605 - 621
  • [25] Invariant Object Recognition and Pose Estimation with Slow Feature Analysis
    Franzius, Mathias
    Wilbert, Niko
    Wiskott, Laurenz
    [J]. NEURAL COMPUTATION, 2011, 23 (09) : 2289 - 2323
  • [26] A fast discriminant approach to active object recognition and pose estimation
    Laporte, C
    Brooks, R
    Arbel, T
    [J]. PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 3, 2004, : 91 - 94
  • [27] Combination of foveal and peripheral vision for object recognition and pose estimation
    Björkman, M
    Kragic, D
    [J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1- 5, PROCEEDINGS, 2004, : 5135 - 5140
  • [28] JOINT POSE ESTIMATION AND ACTION RECOGNITION IN IMAGE GRAPHS
    Raja, Kumar
    Laptev, Ivan
    Perez, Patrick
    Oisel, Lionel
    [J]. 2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011, : 25 - 28
  • [29] OBJECT POSE ESTIMATION IN MONOCULAR IMAGE USING MODIFIED FDCM
    Dabbour, Abd Alrazzak
    Habib, Rabie
    Saii, Mariam
    [J]. COMPUTER SCIENCE-AGH, 2020, 21 (01): : 97 - 112
  • [30] Object tracking and pose estimation using light-field object models
    Zobel, M
    Fritz, M
    Scholz, I
    [J]. VISION MODELING, AND VISUALIZATION 2002, PROCEEDINGS, 2002, : 371 - 378
12345