MTStereo 2.0: Accurate Stereo Depth Estimation via Max-Tree Matching

Rafaël Brandt*, Nicola Strisciuglio, Nicolai Petkov

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems. State-of-the-art stereo matching methods based on convolutional neural networks require intensive computations on GPUs and are difficult to deploy on embedded systems. In this paper, we propose MTStereo2.0, an improved version of the MTStereo stereo matching method, which includes a more robust context-driven cost function, better detection of incorrect matches and the computation of disparity at pixel level. MTStereo provides accurate sparse and semi-dense depth estimation and does not require intensive GPU computations. We tested it on several benchmark data sets, namely KITTI 2015, Driving, FlyingThings3D, Middlebury 2014, Monkaa and the TrimBot2020 garden data sets, and achieved competitive accuracy. The code is available at https://github.com/rbrandt1/MaxTreeS.

Original languageEnglish
Title of host publicationComputer Analysis of Images and Patterns - 19th International Conference, CAIP 2021, Proceedings
EditorsNicolas Tsapatsoulis, Andreas Panayides, Theo Theocharides, Andreas Lanitis, Andreas Lanitis, Constantinos Pattichis, Constantinos Pattichis, Mario Vento
PublisherSpringer
Pages110-119
Number of pages10
ISBN (Electronic)978-3-030-89128-2
ISBN (Print)978-3-030-89127-5
DOIs
Publication statusPublished - 2021
Event19th International Conference on Computer Analysis of Images and Patterns, CAIP 2021 - Virtual, Online
Duration: 28-Sept-202130-Sept-2021

Publication series

NameLecture Notes in Computer Science
Volume13052
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference19th International Conference on Computer Analysis of Images and Patterns, CAIP 2021
CityVirtual, Online
Period28/09/202130/09/2021

Keywords

  • Max-Tree
  • Stereo matching

Fingerprint

Dive into the research topics of 'MTStereo 2.0: Accurate Stereo Depth Estimation via Max-Tree Matching'. Together they form a unique fingerprint.

Cite this