We present a method for estimating the global uncertainty of epipolar geometry with applications to autonomous
vehicle navigation. Such uncertainty information is necessary for making informed decisions regarding the
confidence of a motion estimate, since we must otherwise accept the estimate without any knowledge of the
probability that the estimate is in error. For example, we may wish to fuse visual estimates with information
from GPS and inertial sensors, but without uncertainty information, we have no principled way to do so. Ideally,
we would perform a full search over the 7-dimensional space of fundamental matrices to yield an estimate and its
related uncertainty. However, searching this space is computationally infeasible. As a compromise between fully
representing posterior likelihood over this space and producing a single estimate, we represent the uncertainty
over the space of translation directions in a calibrated framework. In contrast to finding a single estimate,
representing the posterior likelihood is always a well-posed problem, albeit an often computationally challenging
one. Given the posterior likelihood, we derive a confidence interval around the motion estimate. We verify the
correctness of the confidence interval using synthetic data and show examples of uncertainty estimates using
vehicle-mounted camera sequences.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.