Segmentation-based multi-class semantic object detection

Abstract : In this paper we study the problem of the detection of semantic objects from known categories in images. Unlike existing techniques which operate at the pixel or at a patch level for recognition, we propose to rely on the categorization of image segments. Recent work has highlighted that image segments provide a sound support for visual object class recognition. In this work, we use image segments as primitives to extract robust features and train detection models for a predefined set of categories. Several segmentation algorithms are benchmarked and their performances for segment recognition are compared. We then propose two methods for enhancing the segments classification, one based on the fusion of the classification results obtained with the different segmentations, the other one based on the optimization of the global labelling by correcting local ambiguities between neighbor segments. We use as a benchmark the Microsoft MSRC-21 image database and show that our method competes with the current state-of-the-art.
Document type :
Journal articles
Complete list of metadatas

Cited literature [35 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00572863
Contributor : Jenny Benois-Pineau <>
Submitted on : Wednesday, March 2, 2011 - 1:32:55 PM
Last modification on : Thursday, January 11, 2018 - 6:20:17 AM
Long-term archiving on : Tuesday, May 31, 2011 - 2:44:08 AM

File

template.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Remi Vieux, Jenny Benois-Pineau, Jean-Philippe Domenger, Achille Braquelaire. Segmentation-based multi-class semantic object detection. Multimedia Tools and Applications, Springer Verlag, 2011, pp.1 - 22. ⟨10.1007/s11042-010-0611-2⟩. ⟨hal-00572863⟩

Share

Metrics

Record views

286

Files downloads

596