Semantic Stereo for Incidental Satellite Images

Bosch, Marc; Foster, Kevin; Christie, Gordon; Wang, Sean; Hager, Gregory D.; Brown, Myron

doi:10.1109/wacv.2019.00167

Cited by 135 publications

(104 citation statements)

References 35 publications

Supporting

Mentioning

104

Contrasting

Order By: Relevance

“…We employ the IARPA Multi-View Stereo 3D Mapping Challenge dataset [2], which includes 47 DigitalGlobe WorldView-3 images, with 30 cm nadir resolution, collected between 2014 and 2016 over Buenos Aires; and the dataset comprised in the 2019 IEEE GRSS Data Fusion Contest [17,1] with 26 DigitalGlobe WorldView-3 images collected between 2014 and 2016 over Jacksonville. The completeness (percentage of points where the absolute difference is less than 1 meter) of the output models with respect to the lidar ground truth is used as the main evaluation metric to assess the performance of the different methods.…”

Section: Introductionmentioning

confidence: 99%

To Bundle Adjust or Not: A Comparison of Relative Geolocation Correction Strategies for Satellite Multi-View Stereo

Marí

Franchis²,

Meinhardt-Llopis³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

The generation of up-to-date accurate 3D models from multi-view satellite images has recently become a hot research topic. A well-known challenge of this problem is to put all cameras into a common frame of reference, since depending on the satellite geopositioning equipment the camera parameters may contain errors of up to tens of meters on the ground. In this context, bundle adjustment based techniques, relying on the identification of a set of tie-points and the correction of the camera models to make them coincident, have become a generally accepted practice. However, new approaches capable of producing state-of-the-art results without the use of prior bundle adjustment have also been proposed. This work aims to compare both strategies and assess the practical impact of using bundle adjustment for 3D reconstruction from multi-view satellite images.

show abstract

Section: Introductionmentioning

confidence: 99%

To Bundle Adjust or Not: A Comparison of Relative Geolocation Correction Strategies for Satellite Multi-View Stereo

Marí

Franchis²,

Meinhardt-Llopis³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

show abstract

“…The 2019 IEEE GRSS data fusion contest provides the grss_dfc_2019 dataset [41], a subset of the Urban Semantic 3D (US3D) [17] data, including multi-view, multi-band satellite images and ground truth geometric and semantic labels. Several tasks are designed to reconstruct both a 3D geometric model and a segmentation of semantic classes for urban scenes, aiming at further supporting the research in stereo and semantic 3D reconstruction using machine intelligence and deep learning.…”

Section: Satellite Dataset Experimentsmentioning

confidence: 99%

“…Afterwards, the standard SGM and SGM-Forest are recapped in Section 3, followed by our extension of SGM-Forest based on multi-label classification. In Section 4, the methods are tested on two close-range stereo matching datasets, Middlebury and ETH3D benchmarks [12][13][14][15], an airborne dataset, EuroSDR image matching benchmark [16], and a satellite dataset from the 2019 IEEE GRSS data fusion contest [17,18]. The comparison is recorded between original SGM-Forest based on single-label classification (termed SGM-ForestS for the follow-up) and our proposed implementation based on multi-label classification (termed SGM-ForestM).…”

Section: Introductionmentioning

confidence: 99%

Multi-Label Learning based Semi-Global Matching Forest

et al. 2020

View full text Add to dashboard Cite

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.

show abstract

“…The contest made use of Urban Semantic 3D data, a large-scale public data set ( Figure 1) [15]. More than 320 GB of data have been released for training and evaluation, covering approximately 20 km 2 ◗ Track 3: In the multiview semantic stereo challenge, the goal was to predict semantic labels and a DSM, given multiple images for each geographic tile.…”

Section: The 2019 Dfcmentioning

confidence: 99%