Name
Abstract | ||
|---|---|---|
In this paper we describe an advaced segmentation approach for stereo images improving the computation of depth compared to the commonly used straight line segmentation. Using a straight line - circular arc approximation of chain coded lines, the number of primitives is reduced significantly. This approximation low- ers the computational effort as well as the frequency of erro neous matches. Starting with matched pairs of primitives, a dispa rity image is computed containing the initial disparity values f or a sub- sequent block matching algorithm. The output of this algorithm is the partially dense depth image of one aspect of the object. We de- scribe the result of a parallel implementation using object -oriented programming techniques. In segmentation as well as in matching we evaluate color information to improve accuracy and reliability of the depth values. The algorithms are part of a system computing depth from monocular image sequences. Taking a sequence of different views by a camera mounted to a robot hand, each two consecutive images are considered as a stereo image. The depth images computed from these stereo images are fused to one com- plete depth map of the object surface. The results show substantial improvements in comparison to a monochrome system with respect to speed, accuracy, and completeness. |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/ICASSP.1997.595464 | ICASSP |
Keywords | Field | DocType |
edge detection,image colour analysis,image matching,image segmentation,image sequences,object-oriented programming,stereo image processing,advanced segmentation approach,arc segmentation,block matching algorithm,chain coded lines,color information,depth images,depth recovery,disparity image,line segmentation,matched pairs of primitives,monocular image sequences,object surface,object-oriented programming,parallel implementation,partially dense depth image,stereo images,straight line-circular arc approximation | Line (geometry),Computer vision,Block-matching algorithm,Scale-space segmentation,Pattern recognition,Segmentation,Range segmentation,Computer science,Edge detection,Image segmentation,Artificial intelligence,Depth map | Conference |
Volume | ISBN | Citations |
4 | 0-8186-7919-0 | 0 |
PageRank | References | Authors |
0.34 | 7 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| R. Beb | 1 | 0 | 0.34 |
| D. Paulus | 2 | 64 | 6.46 |
| M. Harbeck | 3 | 0 | 0.34 |