Abstract | ||
---|---|---|
This work presents a technique for computing dense disparitymaps from a binocular stereo camera system. Themethods are applied in an Augmented Reality setting forcombining real and virtual worlds with proper occlusions.The proposed stereo correspondence technique is based onarea matching and facilitates an efficient strategy by usingthe concept of a three-dimensional similarity accumulator,whereby occlusions are detected and object boundaries areextracted correctly. The main contribution of this paper isthe way we fill the accumulator using absolute differencesof images and computing a mean filter on these differenceimages. This is where the main advantages of the accumulatorapproach can be exploited, since all entries canbe computed in parallel and thus extremely efficient. Additionally,we perform an asymmetric correction step and apost-processing of the disparity maps that maintains objectedges. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ACV.2002.1182186 | WACV |
Keywords | Field | DocType |
main contribution,binocular stereo camera system,proposed stereo correspondence technique,three-dimensional similarity accumulator,absolute differencesof image,main advantage,asymmetric correction step,augmented reality,dense disparity maps,efficient strategy,dense disparitymaps,concurrent computing,real time,layout,virtual worlds,visualization,real time systems,application software,three dimensional | Object detection,Computer vision,Metaverse,Median filter,Pattern recognition,Visualization,Computer science,Augmented reality,Artificial intelligence,Concurrent computing,Application software,Accumulator (structured product) | Conference |
ISBN | Citations | PageRank |
0-7695-1858-3 | 26 | 1.70 |
References | Authors | |
9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jochen Schmidt | 1 | 94 | 6.39 |
Heinrich Niemann | 2 | 1650 | 288.56 |
Sebastian Vogt | 3 | 112 | 12.96 |