We present a novel scheme for discarding wide-baseline mismatches. Based on a general two-frame wide-baseline matching model, the proposed algorithm first generates match clusters that are topologically invariable between frames, and then discards mismatches from clusters. Experimental results demonstrate that our algorithm can effectively extract high-precision scale-invariant feature transform (SIFT) matches from low-precision initial SIFT matches for wide-baseline image pairs. Furthermore, the algorithm always performs best or close to best in the comparison, indicating that it is more robust than other methods for discarding wide-baseline mismatches.
Wide baseline stereo correspondence has become a challenging and attractive problem in computer vision and its related
applications. Getting high correct ratio initial matches is a very important step of general wide baseline stereo
correspondence algorithm. Ferrari et al. suggested a voting scheme called topological filter in [3] to discard mismatches
from initial matches, but they didn't give theoretical analysis of their method. Furthermore, the parameter of their
scheme was uncertain. In this paper, we improved Ferraris' method based on our theoretical analysis, and presented a
novel scheme called topologically clustering to discard mismatches. The proposed method has been tested using many
famous wide baseline image pairs and the experimental results showed that the developed method can efficiently extract
high correct ratio matches from low correct ratio initial matches for wide baseline image pairs.
An airborne vehicle such as a tactical missile must avoid obstacles like towers, tree branches, mountains and building
across the flight path. So the ability to detect and locate obstacles using on-board sensors is an essential step in the
autonomous navigation of aircraft low-altitude flight. This paper describes a novel method to detect and locate obstacles
using a sequence of images from a passive sensor (TV, FLIR). We model 3D scenes in the field-of-view (FOV) as a
collection of approximately planar layers that corresponds to the background and obstacles respectively. So each pixel
within a layer can have the same 2D affine motion model which depends on the relative depth of the layer. We formulate
the prior assumptions about the layers and scene within a Bayesian decision making framework which is used to
automatically determine the assignment of individual pixels to layers. Then, a generalized expectation maximization
(EM) method is used to find the MAP solution. Finally, simulation results demonstrate that this method is successful.
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.