Mohamed Naouai

Line extraction algorithm based on image vectorization

The raster-vector conversion of remote sensing image is a very important task in the extraction and updating of linear objects in cartographic processes. In this paper we present a vectorization method, based on constrained Delaunay triangulation, for line extraction. The constraints are provided by a preprocessing step insuring that these edges belong to line structures in the original image. The vectorization is performed using CDT and resulting triangles are grouped into polygins that make up the vector image. The skeleton of these polygons represents the extracted linear structures. The algorithm is automatic, fast and has very satisfing results when tested on road segments.

Urban road extraction from high-resolution optical satellite images

Road extraction research has always been an active research on automatic identification of remote sensing images. With the availability of high spatial resolution images from new generation commercial sensors, how to extract roads quickly, accurately and automatically has been a cutting-edge problem in remote sensing related fields. In this paper, we present a novel road extraction approach which uses a scale space segmentation and two measures of the shape index to filter all regions from the result of the segmentation. The approach makes full use of spectral and geometric properties of roads in the imagery, and proposes a new algorithm named “Road Segments joint Algorithm” to ensure the continuity of roads.

Measuring rectangularity using GR-signature

Object recognition often operates by making decisions based on the values of several shape properties measured from an image of the object. In this paper, we propose a new exploitation of the Radon Transform using the gradient measurement to generate a new signature (GR-signature) which provides global information of a binary shape regardless its form. We also develop a new method for measuring the rectangularity based on GR-signature. This original approach looks very promising and has several useful properties that keep fundamental geometrical transformations like scale, rotation and translation.

NURBS parameterization: a new method of parameterization using the correlation relationship between nodes

NURBS (Non-uniform rational B-splines) has become the industry standard tools for the representation, design and data exchange of geometric information to be processed and used by computers because of their useful geometrical properties. The problem of the parameterization of data points in NURBS curve/surface has been considered by several of researchers. We propose in this paper a new parameterization method for NURBS approximation. The current methods of parameterization such as centripetal method uses only the previous knot vector to calculate the recent knot. In this paper, we give a new parameterization method based on the correlation of the nodes. This approach inherits the advantages of the relation and position of the knots.

New Metrics to Evaluate Pattern Recognition in Remote Sensing Images

The continuous development of pattern recognition approaches increases the need for evaluation tools to quantify algorithms performance and establish precise inter-algorithm comparison. So far, few performance evaluating metrics in pattern recognition algorithms are known in the literature, especially in remote sensing images. In this paper, four metrics are proposed for this purpose. The advantages and drawbacks of these metrics are first described, then some experimentation results are the presented in order to validate our contribution.