TR2011-037

CrossTrack: Robust 3D Tracking from Two Cross-Sectional Views


    •  Hussein, M.; Porikli, F.; Li, R.; Arsian, S., "CrossTrack: Robust 3D Tracking from Two Cross-Sectional Views", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2011.5995429, June 2011, pp. 1041-1048.
      BibTeX Download PDF
      • @inproceedings{Hussein2011jun,
      • author = {Hussein, M. and Porikli, F. and Li, R. and Arsian, S.},
      • title = {CrossTrack: Robust 3D Tracking from Two Cross-Sectional Views},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2011,
      • pages = {1041--1048},
      • month = jun,
      • doi = {10.1109/CVPR.2011.5995429},
      • url = {http://www.merl.com/publications/TR2011-037}
      • }
  • Research Area:

    Computer Vision


One of the challenges in radiotherapy of moving tumors is to determine the location of the tumor accurately. Existing solutions to the problem are either invasive or inaccurate. We introduce a non-invasive solution to the problem by tracking the tumor in 3D using bi-plane ultrasound image sequences. We present CrossTrack, a novel tracking algorithm in this framework. We pose the problem as recursive inference of 3D location and tumor boundary segmentation in the two ultrasound views using the tumor 3D model as a prior. For the segmentation task, a robust graph-based approach is deployed as follows: First, robust segmentation priors are obtained through the tumor 3D model. Second, a unified graph combining information across time and multiple views is constructed with a robust weighting function. For the tracking task, an effective mechanism for recovery from respiration-induced occlusion is introduced. Our experiments show the robustness of CrossTrack in handling challenging tumor shapes and disappearance scenarios, with sub-voxel accuracy, and almost 100% precision and recall, significantly outperforming baseline solutions