Roundabout Curvature Bounding box Data

2D Map is collection of pure lines which are connected to form different features like roundabouts, culdisec, buildings, special figures..etc. In real Maps these lines are created using the latitude and longitude. The idea in this letter identify and validate the roundabouts using the geometry of the Map features by spline technique where the geometries is pass over the non rational uniform B spline function to get the knot vectors and hence the new control points, then the curvature($\kappa$) is calculated and hence the radius. Validation of the roundabout is done using a technique where bounding box of roundabout geometry is created and best fitted Eclipse or circle is carved.In case of eclipse, two radius are considered and average out. Finally, radius is bounded in between the threshold and checked with the calculated once. With threshold of 10 meters around 92.2 % of roundabouts in Europe were validated. Improvement of approx. 12.2 % in the deterministic technique have been achieved with reference to prior art, which detect the roundabout in determinitic way to 80 %.This dataset is the comparision between the splines radius and the bounding box approach(describes above) for few admins from western Europe and Eastern europe.