Recent research activity on stereo matching has proved the efficacy of local approaches based on advanced cost aggregation strategies in accurately retrieving 3D information. However, accuracy is typically achieved at expense of computational efficiency, with best methods being far from meeting real-time requirements. On the other side, basic real-time local algorithms relying on a rectangular correlation window suffer from significant ambiguity along depth borders and untextured areas. This work proposes a novel local approach aimed at maximizing the speed-accuracy trade-off by means of an efficient segmentation-based cost aggregation strategy.
Near real-time stereo based on effective cost aggregation / F. Tombari; S. Mattoccia; L. Di Stefano; E. Addimanda. - ELETTRONICO. - 1:(2008), pp. 1-4. (Intervento presentato al convegno 19th International Conference on Pattern Recognition, 2008 (ICPR 2008) tenutosi a Tampa, Florida (USA) nel 8-11 December 2008).
Near real-time stereo based on effective cost aggregation
TOMBARI, FEDERICO;MATTOCCIA, STEFANO;DI STEFANO, LUIGI;
2008
Abstract
Recent research activity on stereo matching has proved the efficacy of local approaches based on advanced cost aggregation strategies in accurately retrieving 3D information. However, accuracy is typically achieved at expense of computational efficiency, with best methods being far from meeting real-time requirements. On the other side, basic real-time local algorithms relying on a rectangular correlation window suffer from significant ambiguity along depth borders and untextured areas. This work proposes a novel local approach aimed at maximizing the speed-accuracy trade-off by means of an efficient segmentation-based cost aggregation strategy.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
