Simultaneous 3D Reconstruction for Water Surface and Underwater Scene

Qian, Yiming; Zheng, Yinqiang; Gong, Minglun; Yang, Yee‐Hong

doi:10.1007/978-3-030-01219-9_46

Cited by 27 publications

(15 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The procedure was applied in real world and the comparison of the corrected depths with measured depths at 658 points showed a mean error and standard deviation of 0.06 m and 0.36 m, respectively, for a measured depth range of 3.4 m to 0.2 m. The same approach was also applied in [39] for refraction correction on bathymetry derived from a WorldView-2 stereopair. Results suggested a mean error of 0.03 m and an RMSE of 1.18 m. In [40], authors presented a first approach for simultaneously recovering the 3D shape of both the wavy water surface and the moving underwater scene, and tested over both synthetic and real data. There, after acquiring the correspondences across different views, the unknown water surface and underwater scene were estimated through minimizing an objective function under a normal consistency constraint.…”

Section: Analytical and Image-based Refraction Correctionmentioning

confidence: 99%

DepthLearn: Learning to Correct the Refraction on Point Clouds Derived from Aerial Imagery for Accurate Dense Shallow Water Bathymetry Based on SVMs-Fusion with LiDAR Point Clouds

et al. 2019

View full text Add to dashboard Cite

The determination of accurate bathymetric information is a key element for near offshore activities; hydrological studies, such as coastal engineering applications, sedimentary processes, hydrographic surveying, archaeological mapping and biological research. Through structure from motion (SfM) and multi-view-stereo (MVS) techniques, aerial imagery can provide a low-cost alternative compared to bathymetric LiDAR (Light Detection and Ranging) surveys, as it offers additional important visual information and higher spatial resolution. Nevertheless, water refraction poses significant challenges on depth determination. Till now, this problem has been addressed through customized image-based refraction correction algorithms or by modifying the collinearity equation. In this article, in order to overcome the water refraction errors in a massive and accurate way, we employ machine learning tools, which are able to learn the systematic underestimation of the estimated depths. In particular, an SVR (support vector regression) model was developed, based on known depth observations from bathymetric LiDAR surveys, which is able to accurately recover bathymetry from point clouds derived from SfM-MVS procedures. Experimental results and validation were based on datasets derived from different test-sites, and demonstrated the high potential of our approach. Moreover, we exploited the fusion of LiDAR and image-based point clouds towards addressing challenges of both modalities in problematic areas.

show abstract

Section: Analytical and Image-based Refraction Correctionmentioning

confidence: 99%

DepthLearn: Learning to Correct the Refraction on Point Clouds Derived from Aerial Imagery for Accurate Dense Shallow Water Bathymetry Based on SVMs-Fusion with LiDAR Point Clouds

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Qian et al. [12] presented the first approach for simultaneously recovering the 3D shape of both a wavy water surface and a moving underwater scene. Xu et al.…”

Section: Related Workmentioning

confidence: 99%

Occluded-Object 3D Reconstruction Using Camera Array Synthetic Aperture Imaging

Pei

et al. 2019

Sensors

View full text Add to dashboard Cite

With the three-dimensional (3D) coordinates of objects captured by a sequence of images taken in different views, object reconstruction is a technique which aims to recover the shape and appearance information of objects. Although great progress in object reconstruction has been made over the past few years, object reconstruction in occlusion situations remains a challenging problem. In this paper, we propose a novel method to reconstruct occluded objects based on synthetic aperture imaging. Unlike most existing methods, which either assume that there is no occlusion in the scene or remove the occlusion from the reconstructed result, our method uses the characteristics of synthetic aperture imaging that can effectively reduce the influence of occlusion to reconstruct the scene with occlusion. The proposed method labels occlusion pixels according to variance and reconstructs the 3D point cloud based on synthetic aperture imaging. Accuracies of the point cloud are tested by calculating the spatial difference between occlusion and non-occlusion conditions. The experiment results show that the proposed method can handle the occluded situation well and demonstrates a promising performance.

show abstract

“…Chang and Chen proposed a basic geometric model for underwater multi-view 3D reconstruction with the solution [6]. Recently, Qian et al achieved simultaneous reconstruction of underwater shape and wavy refractive surface using 9 cameras [18]. They computed surface normals in two different ways including Snell's law and quadric surface fitting, and applied optimization to make them consistent.…”

Section: Related Workmentioning

confidence: 99%

“…There are some work concentrating on refractive interface parameter estimation rather than underwater or background shape reconstruction [15,18,23,14,21]. Morris and Kutulakos proposed refraction stereo for reconstructing a wavy liquid surface from known 2D-3D correspondences [15], which was extended by Qian et al using a regularizer to improve the accuracy [18]. Wetzstein et al reconstructed static transparent objects and dynamic liquid with light field probes [23].…”

Section: Related Workmentioning

confidence: 99%

Unified Underwater Structure-from-Motion

Ichimaru

Taguchi

Kawasaki

2019

2019 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

This paper shows that accurate underwater 3D shape reconstruction is possible using a single camera, observing a target through a refractive interface. We provide unified reconstruction techniques for a variety of scenarios such as single static camera and moving refractive interface, single moving camera and static refractive interface, and single moving camera and moving refractive interface. In our basic setup, we assume that the refractive interface is planar, and simultaneously estimate the unknown transformations of the planar interface and the camera, and the unknown target shape using bundle adjustment. We also extend it to relax the planarity assumption, which enables us to use waves of the refractive interface for the reconstruction task. Experiments with real data show the superiority of our method to existing methods.

show abstract

Simultaneous 3D Reconstruction for Water Surface and Underwater Scene

Cited by 27 publications

References 39 publications

DepthLearn: Learning to Correct the Refraction on Point Clouds Derived from Aerial Imagery for Accurate Dense Shallow Water Bathymetry Based on SVMs-Fusion with LiDAR Point Clouds

DepthLearn: Learning to Correct the Refraction on Point Clouds Derived from Aerial Imagery for Accurate Dense Shallow Water Bathymetry Based on SVMs-Fusion with LiDAR Point Clouds

Occluded-Object 3D Reconstruction Using Camera Array Synthetic Aperture Imaging

Unified Underwater Structure-from-Motion

Contact Info

Product

Resources

About