Boosting with stereo features for building facade detection on mobile platforms

Jeffrey A. Delmerico, Jason J. Corso, Philip David

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Boosting has been widely used for discriminative modeling of objects in images. Conventionally, pixel- and patch-based features have been used, but recently, features defined on multilevel aggregate regions were incorporated into the boosting framework, and demonstrated significant improvement in object labeling tasks. In this paper, we further extend the boosting on multilevel aggregates method to incorporate features based on stereo images. Our underlying application is building facade detection on mobile stereo vision platforms. Example features we propose exploit the algebraic constraints of the planar building facades and depth gradient statistics. We've implemented the features and tested the framework on real stereo data.

Original languageEnglish
Title of host publication2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings
Pages46-49
Number of pages4
DOIs
StatePublished - 2010

Publication series

Name2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings

Fingerprint

Dive into the research topics of 'Boosting with stereo features for building facade detection on mobile platforms'. Together they form a unique fingerprint.

Cite this