Component Optimization for Image Understanding: A Bayesian Approach

Authors:
Li Cheng;Terry Caelli;Arturo Sanchez-Azofeifa
Affiliations:
-;IEEE;-
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2006

Citing 9
Cited 2

Optimizing templates for finding trees in aerial photographs

Pattern Recognition Letters
Modern Differential Geometry of Curves and Surfaces with Mathematica

Modern Differential Geometry of Curves and Surfaces with Mathematica
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Understanding belief propagation and its generalizations

Exploring artificial intelligence in the new millennium
A Trainable Hierarchical Hidden Markov Tree Model for Color Image Annotation

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Stereo Matching Using Belief Propagation

IEEE Transactions on Pattern Analysis and Machine Intelligence
The automatic recognition of individual trees in aerial images of forests based on a synthetic tree crown image model

The automatic recognition of individual trees in aerial images of forests based on a synthetic tree crown image model
Bayesian stereo matching

Computer Vision and Image Understanding
Multiscale Bayesian segmentation using a trainable context model

IEEE Transactions on Image Processing

3D Scene interpretation by combining probability theory and logic: The tower of knowledge

Computer Vision and Image Understanding
Understanding leaves in natural images - A model-based approach for tree species identification

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.14

Visualization

Abstract

In this paper, the optimizations of three fundamental components of image understanding: segmentation/annotation, 3D sensing (stereo) and 3D fitting, are posed and integrated within a Bayesian framework. This approach benefits from recent advances in statistical learning which have resulted in greatly improved flexibility and robustness. The first two components produce annotation (region labeling) and depth maps for the input images, while the third module integrates and resolves the inconsistencies between region labels and depth maps to fit most likely 3D models. To illustrate the application of these ideas, we have focused on the difficult problem of fitting individual tree models to tree stands which is a major challenge for vision-based forestry inventory systems.