Classifying Natural Objects on Outdoor Scenes

Authors:
Anna Bosch;Xavier Muòoz;Joan Martí;Arnau Oliver
Affiliations:
University of Girona, Computer Vision and Robotics Group;University of Girona, Computer Vision and Robotics Group;University of Girona, Computer Vision and Robotics Group;University of Girona, Computer Vision and Robotics Group
Venue:
Proceedings of the 2005 conference on Artificial Intelligence Research and Development
Year:
2005

Citing 6
Cited 0

Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation

International Journal of Computer Vision
Contextual Priming for Object Detection

International Journal of Computer Vision
Outex - New Framework for Empirical Evaluation of Texture Analysis Algorithms

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Multiscale conditional random fields for image labeling

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
A learning framework for object recognition on image understanding

IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose an hybrid and probabilistic classification of image regions belonging to scenes primarily containing natural objects, e.g. sky, trees, etc. as a first step in solving the problem of scene context generation. Therefore, we will focus our work in the problem of image regions labeling to classify every pixel of a given image into one of several predefined classes. Our proposal begins with a top-down control to find the core of objects, which allow us to update the learned models. Moreover, they become the starting seeds for the growing of a set of concurrent active regions which, considering the own region model as well as region and boundary information, obtain an accurate recognition of known regions. Next, a general segmentation extracts the unknown regions by a bottom-up strategy. Finally, a last stage exploits the contextual information to classify initially 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. Experimental results on a wide set of outdoor scene images are shown to evaluate and compare our proposal.