Efficient Online Structured Output Learning for Keypoint-Based Object Tracking
Sam Hare, Amir Saffari and Philip Torr
In: CVPR 2012, 18-20 June 2012., Rhode Island.
Efﬁcient keypoint-based object detection methods are
used in many real-time computer vision applications. These
approaches often model an object as a collection of keypoints and associated descriptors, and detection then involves ﬁrst constructing a set of correspondences between
object and image keypoints via descriptor matching, and
subsequently using these correspondences as input to a robust geometric estimation algorithm such as RANSAC to
ﬁnd the transformation of the object in the image. In such
approaches, the object model is generally constructed of-
ﬂine, and does not adapt to a given environment at runtime.
Furthermore, the feature matching and transformation estimation stages are treated entirely separately. In this paper,
we introduce a new approach to address these problems by
combining the overall pipeline of correspondence generation and transformation estimation into a single structured
output learning framework.
Following the recent trend of using efﬁcient binary descriptors for feature matching, we also introduce an approach to approximate the learned object model as a collection of binary basis functions which can be evaluated very
efﬁciently at runtime. Experiments on challenging video
sequences show that our algorithm signiﬁcantly improves
over state-of-the-art descriptor matching techniques using
a range of descriptors, as well as recent online learning
|EPrint Type:||Conference or Workshop Item (Paper)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Sunando Sengupta|
|Deposited On:||15 June 2012|