Optimal cascade construction for detection using 3D models

被引:0
|
作者
Pong, Hon-Keat [1 ]
Cham, Tat-Jen [1 ]
机构
[1] Nanyang Technol Univ, Sch Comp Engn, Singapore, Singapore
来源
18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS | 2006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
We describe a method for optimal construction of a detection cascade comprising 3D models of increasing level-of-detail (LOD). An LOD 3D model hierarchy of the target object is first generated. By analyzing detection performance of each individual model in the LOD hierarchy, an optimization framework that allows trade-off between speed and accuracy is formulated. The formulation allows models to be explicitly selected for inclusion in the final detection cascade while achieving optimal running time with respect to a target detection performance.
引用
收藏
页码:808 / +
页数:2
相关论文
共 50 条
  • [1] Object detection using a cascade of 3D models
    Pong, HK
    Cham, TJ
    COMPUTER VISION - ACCV 2006, PT II, 2006, 3852 : 284 - 293
  • [2] FLEXIBLE 3D NEIGHBORHOOD CASCADE DEFORMABLE PART MODELS FOR OBJECT DETECTION
    Hung Vu
    Khoa Pho
    Bac Le
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 910 - 914
  • [3] Automated 3D PDM construction using deformable models
    Kaus, MR
    Pekar, V
    Lorenz, C
    Truyen, R
    Lobregt, S
    Richolt, J
    Weese, J
    EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, 2001, : 566 - 572
  • [4] Construction of 3D human distal femoral surface models using a 3D statistical deformable model
    Zhu, Zhonglin
    Li, Guoan
    JOURNAL OF BIOMECHANICS, 2011, 44 (13) : 2362 - 2368
  • [5] Detection of flaws in construction columns using 3D reconstruction and manipulation
    Santos, J
    Longoria, LC
    Palacios, JC
    LINEAR ALGEBRA AND ITS APPLICATIONS, 2001, 339 (1-3) : 195 - 204
  • [6] Recapitulating the tumor ecosystem along the metastatic cascade using 3D culture models
    Kim, Jiyun
    Tanner, Kandice
    FRONTIERS IN ONCOLOGY, 2015, 5
  • [7] A novel framework for automated 3D PDM construction using deformable models
    Zhao, Z
    Teoh, EK
    MEDICAL IMAGING 2005: IMAGE PROCESSING, PT 1-3, 2005, 5747 : 303 - 314
  • [8] Construction of 3D solid vertebral models using convolutional neural networks
    Beskrovny, A. S.
    Bessonov, L., V
    Ivanovo, D., V
    Zolotov, V. S.
    Sidorenko, D. A.
    Kirillova, I., V
    Kossovich, L. Yu
    IZVESTIYA OF SARATOV UNIVERSITY MATHEMATICS MECHANICS INFORMATICS, 2021, 21 (03): : 368 - 378
  • [9] A new scheme for automated 3D PDM construction using deformable models
    Zhao, ZheEn
    Teoh, Eam Khwang
    IMAGE AND VISION COMPUTING, 2008, 26 (02) : 275 - 288
  • [10] FAST FACIAL LANDMARK DETECTION USING CASCADE CLASSIFIERS AND A SIMPLE 3D MODEL
    Liu, Ang
    Du, Yangzhou
    Wang, Tao
    Li, Jianguo
    Li, Eric Q.
    Zhang, Yimin
    Zhao, Yong
    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011, : 845 - 848