| X.Y.Jiang, H.Bunke, "Robust edge detection in range images based on scan line approximation," Technical Report IAM96 -016, Dept. of Computer Science, Univ. of Bern, 1996. |
....marked edges are sequentially labeled to create a segmented image. 2. 3 Scan Line Grouping Segmentation Algorithm This algorithm is selected due to its better segmentation performance and computational expense according to the comparison result in [5] The steps of this algorithm are as follows [6,7]: 1. Scan line approximation technique The only assumption made by scan line approximation is that an image row or column corresponds to a curve in a three dimensional plane that results from the intersection of the plane with the surfaces of objects in the scene. This assumption is satisfied by ....
X.Y.Jiang, H.Bunke, "Robust edge detection in range images based on scan line approximation," Technical Report IAM96 -016, Dept. of Computer Science, Univ. of Bern, 1996.
....its corresponding region. 3.1. University of Bern Segmentation The University of Bern (or UB) procedure is classically used with dense 3 D range images obtained from laser range finders [4] It is based on a scan line approximation which exploits the scan line structure of the image [7] and segments images by extracting planar surfaces. The idea is that, in the ideal case, the points on a scan line that belong to a planar surface form a straight 3 D line segment. On the other hand, all points on a straight 3 D line segment surely belong to the same planar surface. Within UB, ....
X. Jiang and H. Bunke. Robust edge detection in range images based on scan line approximation. Technical Report IAM-96-016, University of Bern, 1996.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC