Silhouette-based occluded object recognition through curvature scale space

被引:24
|
作者
Mokhtarian, F
机构
[1] Ctr. Vis., Speech, and Sign. Proc., Dept. of Electron. and Elec. Eng., University of Surrey, Guildford
[2] John Hopkins University, Baltimore, MD
[3] University of British Columbia, Vancouver, BC
[4] Schlumberger-Doll Research Lab., Ridgefield, CT
[5] NTT Basic Research Labs., Tokyo
[6] Ctr. Vis., Speech, and Sign. Proc., Dept. of Electron. and Elec. Eng., University of Surrey
关键词
shape representation; curvature scale space; multi-scale segmentation; object recognition; occlusion;
D O I
10.1007/s001380050062
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A complete and practical system for occluded object recognition has been developed which is very robust with respect to noise and local deformations of shape (due to weak perspective distortion, segmentation errors and non-rigid material) as well as scale, position and orientation changes of the objects. The system has been tested on a wide variety of fret-form 3D objects. An industrial application is envisaged where a fixed camera and a light-box are utilized to obtain images. Within the constraints of the system, every rigid 3D object can be modeled by a limited number of classes of 2D contours corresponding to the object's resting positions on the light-box. The contours in each class are related to each other by a 2D similarity transformation. The Curvature Scale Space technique [26, 28] is then used to obtain a novel multi-scale segmentation of the image and the model contours. Object indexing [16, 32, 36] is used to narrow down the search space. An efficient local matching algorithm is utilized to select the best matching models.
引用
收藏
页码:87 / 97
页数:11
相关论文
共 50 条
  • [1] Silhouette-based occluded object recognition through curvature scale space
    Univ of Surrey, Guildford, United Kingdom
    [J]. Mach Vision Appl, 3 (87-97):
  • [2] Silhouette-based occluded object recognition through curvature scale space
    Farzin Mokhtarian
    [J]. Machine Vision and Applications, 1997, 10 : 87 - 97
  • [3] SILHOUETTE-BASED ISOLATED OBJECT RECOGNITION THROUGH CURVATURE SCALE-SPACE
    MOKHTARIAN, F
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1995, 17 (05) : 539 - 544
  • [4] Silhouette-based method for object classification and human action recognition in video
    Dedeoglu, Yigithan
    Toreyin, B. Ugur
    Gudukbay, Ugur
    Cetin, A. Enis
    [J]. COMPUTER VISION IN HUMAN-COMPUTER INTERACTION, 2006, 3979 : 64 - 77
  • [5] Evaluation of a hypothesizer for silhouette-based 3-D object recognition
    Super, BJ
    Lu, H
    [J]. PATTERN RECOGNITION, 2003, 36 (01) : 69 - 78
  • [6] Silhouette-based Object Phenotype Recognition using 3D Shape Priors
    Chen, Yu
    Kim, Tae-Kyun
    Cipolla, Roberto
    [J]. 2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2011, : 25 - 32
  • [7] Silhouette-based gait recognition via deterministic learning
    Zeng, Wei
    Wang, Cong
    Yang, Feifei
    [J]. PATTERN RECOGNITION, 2014, 47 (11) : 3568 - 3584
  • [8] Set Residual Network for Silhouette-Based Gait Recognition
    Hou, Saihui
    Liu, Xu
    Cao, Chunshui
    Huang, Yongzhen
    [J]. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2021, 3 (03): : 384 - 393
  • [9] Gait Recognition using Partial Silhouette-based Approach
    Shaikh, Soharab Hossain
    Saeed, Khalid
    Chaki, Nabendu
    [J]. 2014 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND INTEGRATED NETWORKS (SPIN), 2014, : 101 - 106
  • [10] A Comprehensive Study on the Evaluation of Silhouette-Based Gait Recognition
    Hou, Saihui
    Fan, Chao
    Cao, Chunshui
    Liu, Xu
    Huang, Yongzhen
    [J]. IEEE TRANSACTIONS ON BIOMETRICS, BEHAVIOR, AND IDENTITY SCIENCE, 2023, 5 (02): : 196 - 208