Generic Object Class Detection using Feature Maps
2011 (English)In: Proceedings of Scandinavian Conference on Image Analysis, 2011, 348-359 p.Conference paper (Refereed)
In this paper we describe an object class model and a detection scheme based on feature maps, i.e. binary images indicating occurrences of various local features. Any type of local feature and any number of features can be used to generate feature maps. The choice of which features to use can thus be adapted to the task at hand, without changing the general framework. An object class is represented by a boosted decision tree classifier (which may be cascaded) based on normalized distances to feature occurrences. The resulting object class model is essentially a linear combination of a set of flexible configurations of the features used. Within this framework we present an efficient detection scheme that uses a hierarchical search strategy. We demonstrate experimentally that this detection scheme yields a significant speedup compared to sliding window search. We evaluate the detection performance on a standard dataset , showing state of the art results. Features used in this paper include edges, corners, blobs and interest points.
Place, publisher, year, edition, pages
2011. 348-359 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 6688
AdaBoost, decision tree, detector, distance transform, SIFT
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-38596DOI: 10.1007/978-3-642-21227-7_33ISI: 000308543900033ScopusID: 2-s2.0-79957517130ISBN: 978-364221226-0OAI: oai:DiVA.org:kth-38596DiVA: diva2:437457
17th Scandinavian Conference on Image Analysis, SCIA 2011; Ystad; 23 May 2011 through 27 May 2011
FunderICT - The Next Generation
QC 201108302011-08-292011-08-292013-04-19Bibliographically approved