TY - JOUR

T1 - Junction extraction by artificial neural network system

T2 - 2002 International Symposium of ISPRS Commission III on Photogrammetric Computer Vision, PCV 2002

AU - Barsi, Arpad

AU - Heipke, Christian

AU - Willrich, Felicitas

N1 - Funding Information: The authors are grateful for the financial support to the Alexander von Humboldt Foundation, for the data to the Federal Agency for Cartography and Geodesy and the Hungarian Higher Education Research and Development Project.

PY - 2002

Y1 - 2002

N2 - The paper presents a road junction operator, which was developed for medium resolution black-and-white orthoimages. The operator uses a feed-forward neural network applied for a running window to decide whether it contains a 3- or 4-arm road junction or not. The training set was created by a data analysis based feature selection. The best features took part in the training of 3-layer neural networks. The features are coming from the central kernel of the window (raster data) and from edge detection (vector data). The vectorized edges are only kept for training, if they are going through the central circle, which represents the junction central in a rotation invariant way. The edges fulfilling the circle criterion are applied to derive features, like edge length and direction measures. A set of identically structured networks with varied parameters was generated and trained by an efficient optimization algorithm. The evaluation of the networks was carried out in in-sample tests, where the main traditional methods are compared to the neural solution. The out-of-sample test was performed by real image chips with different rotations. The obtained results demonstrate the principal feasibility of the developed method.

AB - The paper presents a road junction operator, which was developed for medium resolution black-and-white orthoimages. The operator uses a feed-forward neural network applied for a running window to decide whether it contains a 3- or 4-arm road junction or not. The training set was created by a data analysis based feature selection. The best features took part in the training of 3-layer neural networks. The features are coming from the central kernel of the window (raster data) and from edge detection (vector data). The vectorized edges are only kept for training, if they are going through the central circle, which represents the junction central in a rotation invariant way. The edges fulfilling the circle criterion are applied to derive features, like edge length and direction measures. A set of identically structured networks with varied parameters was generated and trained by an efficient optimization algorithm. The evaluation of the networks was carried out in in-sample tests, where the main traditional methods are compared to the neural solution. The out-of-sample test was performed by real image chips with different rotations. The obtained results demonstrate the principal feasibility of the developed method.

KW - Artificial Neural Networks

KW - Automatic Object Extraction

KW - Road Junctions

UR - http://www.scopus.com/inward/record.url?scp=85052392857&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85052392857

VL - 34

JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SN - 1682-1750

Y2 - 9 September 2002 through 13 September 2002

ER -