Next Article in Journal
Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks
Previous Article in Journal
Correction: Koga, Y., et al. A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation. Remote Sensing 2020, 12, 575
Previous Article in Special Issue
Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Multi-Label Learning based Semi-Global Matching Forest

1
Department of Photogrammetry and Image Analysis, Remote Sensing Technology Institute, German Aerospace Center (DLR), 82234 Wessling, Germany
2
Institute of Computer Graphics and Vision, Graz University of Technology (TU Graz), 8010 Graz, Austria
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(7), 1069; https://doi.org/10.3390/rs12071069 (registering DOI)
Received: 17 March 2020 / Accepted: 24 March 2020 / Published: 26 March 2020
(This article belongs to the Special Issue Point Cloud Processing in Remote Sensing)
Semi-Global Matching (SGM) approximates a 2D Markov Random Field (MRF) via multiple 1D scanline optimizations, which serves as a good trade-off between accuracy and efficiency in dense matching. Nevertheless, the performance is limited due to the simple summation of the aggregated costs from all 1D scanline optimizations for the final disparity estimation. SGM-Forest improves the performance of SGM by training a random forest to predict the best scanline according to each scanline’s disparity proposal. The disparity estimated by the best scanline acts as reference to adaptively adopt close proposals for further post-processing. However, in many cases more than one scanline is capable of providing a good prediction. Training the random forest with only one scanline labeled may limit or even confuse the learning procedure when other scanlines can offer similar contributions. In this paper, we propose a multi-label classification strategy to further improve SGM-Forest. Each training sample is allowed to be described by multiple labels (or zero label) if more than one (or none) scanline gives a proper prediction. We test the proposed method on stereo matching datasets, from Middlebury, ETH3D, EuroSDR image matching benchmark, and the 2019 IEEE GRSS data fusion contest. The result indicates that under the framework of SGM-Forest, the multi-label strategy outperforms the single-label scheme consistently.
Keywords: Semi-Global Matching (SGM); random forests; scanline; multi-label classification; disparity; learning Semi-Global Matching (SGM); random forests; scanline; multi-label classification; disparity; learning
Show Figures

Graphical abstract

MDPI and ACS Style

Xia, Y.; d’Angelo, P.; Tian, J.; Fraundorfer, F.; Reinartz, P. Multi-Label Learning based Semi-Global Matching Forest. Remote Sens. 2020, 12, 1069.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop