Zur Hauptnavigation wechseln Zur Suche wechseln Zum Hauptinhalt wechseln

CNN-based Cost Volume Analysis as Confidence Measure for Dense Matching

  • Max Mehltretter*
  • , Christian Heipke
  • *Korrespondierende*r Autor*in für diese Arbeit

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Abstract

Due to its capability to identify erroneous disparity assignments in dense stereo matching, confidence estimation is beneficial for a wide range of applications, e.g. autonomous driving, which needs a high degree of confidence as mandatory prerequisite. Especially, the introduction of deep learning based methods resulted in an increasing popularity of this field in recent years, caused by a significantly improved accuracy. Despite this remarkable development, most of these methods rely on features learned from disparity maps only, not taking into account the corresponding 3-dimensional cost volumes. However, it was already demonstrated that with conventional methods based on hand-crafted features this additional information can be used to further increase the accuracy. In order to combine the advantages of deep learning and cost volume based features, in this paper, we propose a novel Convolutional Neural Network (CNN) architecture to directly learn features for confidence estimation from volumetric 3D data. An extensive evaluation on three datasets using three common dense stereo matching techniques demonstrates the generality and state-of-the-art accuracy of the proposed method.

OriginalspracheEnglisch
Titel des Sammelwerks2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten2070-2079
Seitenumfang10
ISBN (elektronisch)978-1-7281-5023-9
ISBN (Print)978-1-7281-5024-6
DOIs
PublikationsstatusVeröffentlicht - Okt. 2019
Veranstaltung2019 IEEE/CVF 17th International Conference on Computer Vision Workshop (ICCVW) - Seoul, Südkorea
Dauer: 27 Okt. 201928 Okt. 2019

Publikationsreihe

NameIEEE International Conference on Computer Vision workshops
ISSN (Print)2473-9936
ISSN (elektronisch)2473-9944

Konferenz

Konferenz2019 IEEE/CVF 17th International Conference on Computer Vision Workshop (ICCVW)
KurztitelICCVW
Land/GebietSüdkorea
OrtSeoul
Zeitraum27 Okt. 201928 Okt. 2019

ASJC Scopus Sachgebiete

  • Angewandte Informatik
  • Maschinelles Sehen und Mustererkennung

Dieses zitieren