Viewpoint Adaptation for Person Detection
Abstract
An object detector performs suboptimally when applied to image data taken from a viewpoint
different from the one with which it was trained. In this paper, we present a viewpoint
adaptation algo- rithm that allows a trained single-view person detector to be adapted
to a new, distinct viewpoint. We first illustrate how a feature space trans- formation
can be inferred from a known homography between the source and target viewpoints.
Second, we show that a variety of trained clas- sifiers can be modified to behave
as if that transformation were applied to each testing instance. The proposed algorithm
is evaluated on a new synthetic multi-view dataset as well as images from the PETS
2007 and CAVIAR datasets, yielding substantial performance improvements when adapting
single-view person detectors to new viewpoints while increas- ing the detector frame
rate. This work has the potential to improve person detection performance for cameras
at non-standard viewpoints while simplifying data collection and feature extraction
Type
Other articlePermalink
https://hdl.handle.net/10161/13502Published Version (Please cite this version)
10.7924/G87P8W96Collections
More Info
Show full item recordScholars@Duke
Patrick Wang
Adjunct Assistant Professor in the Department of Electrical and Computer Engineering

Articles written by Duke faculty are made available through the campus open access policy. For more information see: Duke Open Access Policy
Rights for Collection: Scholarly Articles
Works are deposited here by their authors, and represent their research and opinions, not that of Duke University. Some materials and descriptions may include offensive content. More info