Clustering of Static-Adaptive Correspondences for Deformable Object Tracking

Georg Nebehay and Roman Pflugfelder


We propose a novel method for establishing correspondences on deformable objects for single-target object tracking. The key ingredient is a dissimilarity measure between correspondences that takes into account their geometric compatibility, allowing us to separate inlier correspondences from outliers. We employ both static correspondences from the initial appearance of the object as well as adaptive correspondences from the previous frame to address the stability-plasticity dilemma. The geometric dissimilarity measure enables us to also disambiguate keypoints that are difficult to match. Based on these ideas we build a keypoint-based tracker that outputs rotated bounding boxes. We demonstrate in a rigorous empirical analysis that this tracker outperforms the state of the art on a dataset of 77 sequences.

Published In

Computer Vision and Pattern Recognition, 2015.
Download the PDF PDF logo


Download the code from our GitHub repository.GitHub logo

Project Page

More information is available at the Project page.


    author = {Nebehay, Georg and Pflugfelder, Roman},
    booktitle = {Computer Vision and Pattern Recognition},
    month = jun,
    pages = {2784--2791},
    publisher = {IEEE},
    title = {Clustering of {Static-Adaptive} Correspondences for Deformable Object Tracking},
    year = {2015}
Back to publication list