Abstract | ||
---|---|---|
This paper introduces the idea of temporally extending results of a stereo algorithm in order to improve the algorithm''s performance. This approach anticipates the changes between two consecutive depth maps resulting from the motion of the cameras. Uncertainties in motion are accounted for by computation of an ambiguity area and a resulting disparity range for each pixel. The computation is used to verify and refine the anticipated values, rather than calculate them without prior knowledge. The paper compares the performance of the algorithm under different constraints on motion. Speedups of up to 400\% are achieved without significant errors. |
Year | DOI | Venue |
---|---|---|
1997 | 10.1109/ROBOT.1997.619163 | ICRA |
Keywords | Field | DocType |
stereo algorithm,consecutive depth map,resulting disparity range,ambiguity area,anticipated value,prior knowledge,temporally coherent stereo,different constraint,significant error,depth map,computer vision,stereo vision,robustness,uncertainty,computer science,mobile robots,path planning,high performance computing | Structure from motion,Motion planning,Stereo cameras,Computer vision,Computer science,Pixel,Artificial intelligence,Ambiguity,Mobile robot,Computer stereo vision,Computation | Conference |
Volume | Issue | ISSN |
3 | 1 | 1050-4729 |
Citations | PageRank | References |
1 | 0.39 | 6 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vladimir Tucakov | 1 | 421 | 28.31 |
D. G. Lowe | 2 | 15718 | 1413.60 |