Item


Using appearance and context for outdoor scene object classification

We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal

© IEEE International Conference on Robotics and Automation : 2001 : Proceedings 2001 ICRA, 2005, vol. 2

IEEE

Author: Bosch Rué, Anna
Muñoz Pujol, Xavier
Martí Bonmatí, Joan
Date: 2005
Abstract: We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal
Format: application/pdf
Citation: Bosch Rué, A., Muñoz Pujol, X. i Martí Bonmatí, J. (2001). Positioning an underwater vehicle through image mosaicking. IEEE International Conference on Robotics and Automation : 2001 : Proceedings 2001 ICRA, 3, 2779 - 2784. Recuperat 18 maig 2010, a http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=933043
ISBN: 0-7803-6576-3
ISSN: 1050-4729
Document access: http://hdl.handle.net/10256/2311
Language: eng
Publisher: IEEE
Collection: Reproducció digital del document publicat a: http://dx.doi.org/10.1109/ROBOT.2001.933043
Articles publicats (D-ATC)
Is part of: © IEEE International Conference on Robotics and Automation : 2001 : Proceedings 2001 ICRA, 2005, vol. 2
Rights: Tots els drets reservats
Subject: Discriminació visual
Imatges -- Processament
Imatges -- Segmentació
Reconeixement òptic de formes
Visió per ordinador
Computer vision
Image processing
Imaging segmentation
Optical pattern recognition
Visual discrimination
Title: Using appearance and context for outdoor scene object classification
Type: info:eu-repo/semantics/article
Repository: DUGiDocs

Subjects

Authors