Semantic Classification in Aerial Imagery by Integrating Appearance and Height Information

@inproceedings{Kluckner2009SemanticCI,
  title={Semantic Classification in Aerial Imagery by Integrating Appearance and Height Information},
  author={Stefan Kluckner and Thomas Mauthner and Peter M. Roth and Horst Bischof},
  booktitle={ACCV},
  year={2009}
}
In this paper we present an efficient technique to obtain accurate semantic classification on the pixel level capable of integrating various modalities, such as color, edge responses, and height information. We propose a novel feature representation based on Sigma Points computations that enables a simple application of powerful covariance descriptors to a multi-class randomized forest framework. Additionally, we include semantic contextual knowledge using a conditional random field formulation… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 50 CITATIONS

Learning to Label Aerial Images from Noisy Data

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Deep multi-task learning for a geographically-regularized semantic segmentation of aerial images

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Machine learning for aerial image labeling

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Semantic classification by covariance descriptors within a randomized forest

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND

FILTER CITATIONS BY YEAR

2009
2019

CITATION STATISTICS

  • 3 Highly Influenced Citations

References

Publications referenced by this paper.
SHOWING 1-10 OF 25 REFERENCES

Learning on lie groups for invariant detection and tracking

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Object categorization by learned universal visual dictionary

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Image Classification using Random Forests and Ferns

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

A metric for covariance matrices

  • W. Foerstner, B. Moonen
  • Technical report, Department of Geodesy and Geoinformatics, Stuttgart University
  • 1999
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Building segmentation for densely built urban regions using aerial LIDAR data

VIEW 1 EXCERPT