Math @ Duke

Publications [#332374] of John Harer
Papers Published
 Tralie, CJ; Smith, A; Borggren, N; Hineman, J; Bendich, P; Zulch, P; Harer, J, Geometric CrossModal Comparison of Heterogeneous Sensor Data,
Proceedings of the 39th Ieee Aerospace Conference, vol. 2018March
(March, 2018),
pp. 110, IEEE, ISBN 9781538620144 [doi]
(last updated on 2021/10/21)
Abstract: In this work, we address the problem of crossmodal comparison of aerial data
streams. A variety of simulated automobile trajectories are sensed using two
different modalities: fullmotion video, and radiofrequency (RF) signals
received by detectors at various locations. The information represented by the
two modalities is compared using selfsimilarity matrices (SSMs) corresponding
to timeordered point clouds in feature spaces of each of these data sources;
we note that these feature spaces can be of entirely different scale and
dimensionality. Several metrics for comparing SSMs are explored, including a
cuttingedge timewarping technique that can simultaneously handle local time
warping and partial matches, while also controlling for the change in geometry
between feature spaces of the two modalities. We note that this technique is
quite general, and does not depend on the choice of modalities. In this
particular setting, we demonstrate that the crossmodal distance between SSMs
corresponding to the same trajectory type is smaller than the crossmodal
distance between SSMs corresponding to distinct trajectory types, and we
formalize this observation via precisionrecall metrics in experiments.
Finally, we comment on promising implications of these ideas for future
integration into multiplehypothesis tracking systems.


dept@math.duke.edu
ph: 919.660.2800
fax: 919.660.2821
 
Mathematics Department
Duke University, Box 90320
Durham, NC 277080320

