A Novel Hardware-Oriented Stereo Matching Algorithm and Its Architecture Design in FPGA - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

A Novel Hardware-Oriented Stereo Matching Algorithm and Its Architecture Design in FPGA

Yanzhe Li
  • Fonction : Auteur
  • PersonId : 1025762
Kai Huang
  • Fonction : Auteur
  • PersonId : 928507
Luc Claesen
  • Fonction : Auteur
  • PersonId : 990886

Résumé

Stereo matching is a crucial step to extract depth information from stereo images. However, it is still challenging to achieve good performance in both speed and accuracy for various stereo vision applications. In this contribution, a hardware-compatible stereo matching algorithm is proposed and its associated hardware implementation is also presented. The proposed algorithm can produce high-quality disparity maps with the combined use of the mini-census transform, segmentation-based adaptive support weight and effective refinement. Moreover, the proposed architecture is optimized as a fully pipelined and scalable hardware system. Implemented on an Altera Stratix-IV FPGA board, it can achieve 65 frames per second (fps) for 1024 $$\times $$ 768 stereo images and a 64 pixel disparity range. The proposed system is evaluated on the Middlebury benchmark and the average error rate is 6.56%. The experimental results indicate that the accuracy is competitive with some state-of-the-art software implementations.
Fichier principal
Vignette du fichier
456609_1_En_11_Chapter.pdf (2.08 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01675199 , version 1 (04-01-2018)

Licence

Paternité

Identifiants

Citer

Yanzhe Li, Kai Huang, Luc Claesen. A Novel Hardware-Oriented Stereo Matching Algorithm and Its Architecture Design in FPGA. 24th IFIP/IEEE International Conference on Very Large Scale Integration - System on a Chip (VLSISOC), Sep 2016, Tallinn, Estonia. pp.213-232, ⟨10.1007/978-3-319-67104-8_11⟩. ⟨hal-01675199⟩
476 Consultations
107 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More