We present a novel operator to be applied at raw matching costs in the context of low level vision tasks such as stereo matching or optical flow. It aims at im- proving matching reliability by efficiently modulating pixel-wise pairing costs, injecting a confidence backed bias before the aggregation step. It works analyzing a noisy estimate of the correspondances in order to fa- vor or prune potential matches. We test the operator by developing a local, realtime stereo matching algorithm and showing that our solution can drastically clean the resulting depth map while also reducing border bleed- ing. Its good performance is also evaluated quanti- tavely by testing the algorithm against the popular Mid- dlebury benchmark where our local greedy implemen- tation is able to obtain results comparable to those of n¨ aive global approaches.

Confidence-based cost modulation for stereo matching

GHERARDI, Riccardo
2008-01-01

Abstract

We present a novel operator to be applied at raw matching costs in the context of low level vision tasks such as stereo matching or optical flow. It aims at im- proving matching reliability by efficiently modulating pixel-wise pairing costs, injecting a confidence backed bias before the aggregation step. It works analyzing a noisy estimate of the correspondances in order to fa- vor or prune potential matches. We test the operator by developing a local, realtime stereo matching algorithm and showing that our solution can drastically clean the resulting depth map while also reducing border bleed- ing. Its good performance is also evaluated quanti- tavely by testing the algorithm against the popular Mid- dlebury benchmark where our local greedy implemen- tation is able to obtain results comparable to those of n¨ aive global approaches.
2008
9781424421749
Stereo Matching; Confidence Measure
File in questo prodotto:
File Dimensione Formato  
icpr08gherardi.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Dominio pubblico
Dimensione 304.43 kB
Formato Adobe PDF
304.43 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/344072
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact