From images to shape models for object detection

Vittorio Ferrari 1 Frédéric Jurie 2 Cordelia Schmid 3
2 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
3 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and can localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the boundaries of objects, rather than just their bounding-boxes. This is achieved by a novel technique for learning a shape model of an object class given images of example instances. Furthermore, we also integrate Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately and does not need segmented examples for training (only bounding-boxes).
Document type :
Journal articles
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download

https://hal.inria.fr/inria-00548643
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 10:23:55 AM
Last modification on : Tuesday, April 2, 2019 - 1:35:00 AM
Long-term archiving on : Monday, March 21, 2011 - 3:27:05 AM

File

FJS10.pdf
Files produced by the author(s)

Identifiers

Citation

Vittorio Ferrari, Frédéric Jurie, Cordelia Schmid. From images to shape models for object detection. International Journal of Computer Vision, Springer Verlag, 2010, 87 (3), pp.284-303. ⟨10.1007/s11263-009-0270-9⟩. ⟨inria-00548643⟩

Share

Metrics

Record views

829

Files downloads

778