Ball-Scale Based Hierarchical Multi-Object Recognition in 3D Medical Images

被引:4
|
作者
Bagci, Ulas [1 ]
Udupa, Jayaram K. [2 ]
Chen, Xinjian [3 ]
机构
[1] Univ Nottingham, CMIAG, Nottingham, England
[2] Univ Penn, Dept Radiol, Med Image Proc Grp, Philadelphia, PA 19104 USA
[3] NIH, Ctr Clin, Diagnost Radiol Dept, Bethesda, MD 20892 USA
来源
关键词
Object Recognition; Ball-Scale; Active Shape Modeling; Principal Component Analysis; Hierarchical Recognition; Image Segmentation; SEGMENTATION;
D O I
10.1117/12.839920
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
This paper investigates, using prior shape models and the concept of ball scale (b-scale), ways of automatically recognizing objects in 3D images without performing elaborate searches or optimization. That is, the goal is to place the model in a single shot close to the right pose (position, orientation, and scale) in a given image so that the model boundaries fall in the close vicinity of object boundaries in the image. This is achieved via the following set of key ideas: (a) A semi-automatic way of constructing a multi-object shape model assembly. (b) A novel strategy of encoding, via b-scale, the pose relationship between objects in the training images and their intensity patterns captured in b-scale images. (c) A hierarchical mechanism of positioning the model, in a one-shot way, in a given image from a knowledge of the learnt pose relationship and the b-scale image of the given image to be segmented. The evaluation results on a set of 20 routine clinical abdominal female and male CT data sets indicate the following: (1) Incorporating a large number of objects improves the recognition accuracy dramatically. (2) The recognition algorithm can be thought as a hierarchical framework such that quick replacement of the model assembly is defined as coarse recognition and delineation itself is known as finest recognition. (3) Scale yields useful information about the relationship between the model assembly and any given image such that the recognition results in a placement of the model close to the actual pose without doing any elaborate searches or optimization. (4) Effective object recognition can make delineation most accurate.
引用
收藏
页数:12
相关论文
共 50 条
  • [31] Fuzzy object detection in 3D medical images
    Wang, H
    Zhuang, TG
    Jiang, DZ
    Zhang, H
    Liu, WY
    Bacelar, A
    Magnin, IE
    Gimenez, G
    NONLINEAR IMAGE PROCESSING VIII, 1997, 3026 : 155 - 163
  • [32] Multi-resolution mesh based 3D object recognition
    Li, Qing
    Zhou, Man-Li
    Liu, Jian
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2001, 29 (07): : 891 - 894
  • [33] Multi-resolution mesh based 3D object recognition
    Li, Q
    Zhou, ML
    Liu, J
    IEEE WORKSHOP ON COMPUTER VISION BEYOND THE VISIBLE SPECTRUM: METHODS AND APPLICATIONS, PROCEEDINGS, 2000, : 37 - 43
  • [34] 3D Multi-object Detection and Tracking with Sparse Stationary LiDAR
    Zhang, Meng
    Pan, Zhiyu
    Feng, Jianjiang
    Zhou, Jie
    PATTERN RECOGNITION AND COMPUTER VISION, PT I, 2021, 13019 : 16 - 28
  • [35] 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
    Weng, Xinshuo
    Wang, Jianren
    Held, David
    Kitani, Kris
    2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 10359 - 10366
  • [36] Motion Compensation Optimization Method for 3D Multi-Object Tracking
    Wang S.-H.
    Zhang Y.
    Shen J.-N.
    Ji J.-M.
    Zhang Y.-Y.
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2024, 52 (02): : 528 - 539
  • [37] Learnable Online Graph Representations for 3D Multi-Object Tracking
    Zaech, Jan-Nico
    Liniger, Alexander
    Dai, Dengxin
    Danelljan, Martin
    Van Gool, Luc
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02): : 5103 - 5110
  • [38] EagerMOT: 3D Multi-Object Tracking via Sensor Fusion
    Kim, Aleksandr
    Osep, Aljosa
    Leal-Taixe, Laura
    2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 11315 - 11321
  • [39] Multi-Object tracking of 3D cuboids using aggregated features
    Muresan, Mircea Paul
    Nedevschi, Sergiu
    2019 IEEE 15TH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTER COMMUNICATION AND PROCESSING (ICCP 2019), 2019, : 11 - 18
  • [40] Fast display method for rendering 3D multi-object image
    Guo, Junfeng
    Cai, Yuanlong
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design & Computer Graphics, 1996, 8 (02):