Colour-Consistent Structure-from-Motion Models using Underwater Imagery

Bryson, Mitch; Johnson-Roberson, Matthew; Pizarro, Oscar; Williams, Stefan B.

doi:10.15607/rss.2012.viii.005

Cited by 41 publications

(42 citation statements)

References 15 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the data pre‐processing phase (B), a series of operations were carried out to achieve two major objectives: preparing the exact sequence of stereoscopic image pairs, and limiting the typical effects of degradation on image quality from the underwater environment (Bryson, Johnson‐Roberson, Pizarro, & Williams, ). These operations are divided into three steps: video synchronization image export colour correction …”

Section: Methodsmentioning

confidence: 99%

Virtual simulation of a late antique shipwreck at Marzamemi, Sicily: Integrated processes for 3D documentation, analysis and representation of underwater archaeological data

Repola

Carlo

Signoretti

et al. 2018

Archaeological Prospection

View full text Add to dashboard Cite

Three‐dimensional (3D) models derived from digital survey techniques have increasingly become a mainstay of archaeological research and cultural heritage management. The high accuracy of such modelling makes it an attractive solution for a wide range of challenges from site recording and interpretation to object analysis and reconstruction. The present paper focuses on a new 3D digitization method using stereoscopic video for the documentation, analysis, and representation of archaeological contexts as part of shipwreck investigations off southeast Sicily at Marzamemi. This sixth‐century ce vessel sank in shallow water (7–8 m) while carrying a massive cargo of largely prefabricated architectural elements intended for the construction and decoration of a church somewhere in the late antique west. This dynamic site presents significant challenges to the interpretation of depositional and post‐depositional events as well the reconstruction of the original cargo and individual architectural elements. Therefore, 3D documentation underwater at Marzamemi has centred on new methods for stereoscopic scanning of the site, topography, and large architectural finds, allowing not only more rapid and precise mapping but insights into site formation processes and the organizational mechanisms behind the cargo assemblage. The adoption of this new system based on a precise workflow and simple, inexpensive hardware combined with readily available software allows more accurate and rapid digital recording underwater to a high standard across scales, from the site level down to the individual artefact. This process, named ISU3D (Integrated System for Underwater 3D Digitization), offers innovative solutions not only for archaeological field research but for heritage management and public outreach.

show abstract

Section: Methodsmentioning

confidence: 99%

Virtual simulation of a late antique shipwreck at Marzamemi, Sicily: Integrated processes for 3D documentation, analysis and representation of underwater archaeological data

Repola

Carlo

Signoretti

et al. 2018

Archaeological Prospection

View full text Add to dashboard Cite

show abstract

“…In this case, the map creation is oversimplified because one can benefit from the large set of tools in the robotics community to retrieve smooth elevation maps even if the data contain some level of corruption. It is also easy to then combine both acoustic and image‐based maps to reach further detail …”

Section: Related Workmentioning

confidence: 99%

Surface meshing of underwater maps from highly defective point sets

Campos

García

2017

Journal of Field Robotics

View full text Add to dashboard Cite

Owing to the many possible errors that may occur during real‐world mapping, point set maps often present a huge amount of outliers and large levels of noise. We present two robust surface reconstruction techniques dealing with corrupted point sets without resorting to any prefiltering step. They are based on building an unsigned distance function, discretely evaluated on an adaptive tetrahedral grid, and defined from an outlier‐robust splat representation. To extract the surface from this volumetric view, the space is partitioned into two subsets, the surface of interest being at the boundary separating them. While both methods are based on a similar graph definition derived from the above‐mentioned grid, they differ in the partitioning procedure. First, we propose a method using S‐T cuts to separate the inside and outside of the mapped area. Second, we use a normalized cut approach to partition the volume using only the values of the unsigned distance function. We prove the validity of our methods by applying them to challenging underwater data sets (sonar and image based), and we benchmark their results against the approaches in the state of the art.

show abstract

“…For restoring color, methods range from simple white balancing [23,113] to Markov Random Fields [167], fusion-based techniques [5], and even colored strobes [172]. In the case of many robotic imaging platforms, additional sensor information may be useful for correction as well [11,15,81,85,131,137].…”

Section: Underwater Imagingmentioning

confidence: 99%

“…Stereo camera pairs [15] or a sheet laser in the camera's field of view [11] can similarly provide bathymetry information for modeling attenuation path lengths.…”

Section: Beyond a Single Imagementioning

confidence: 99%

Computational strategies for understanding underwater optical image datasets

Kaeli¹

2013

View full text Add to dashboard Cite

A fundamental problem in autonomous underwater robotics is the high latency between the capture of image data and the time at which operators are able to gain a visual understanding of the survey environment. Typical missions can generate imagery at rates hundreds of times greater than highly compressed images can be transmited acoustically, delaying that understanding until after the vehicle has been recovered and the data analyzed. While automated classification algorithms can lessen the burden on human annotators after a mission, most are too computationally expensive or lack the robustness to run in situ on a vehicle. Fast algorithms designed for mission-time performance could lessen the latency of understanding by producing low-bandwidth semantic maps of the survey area that can then be telemetered back to operators during a mission.This thesis presents a lightweight framework for processing imagery in real time aboard a robotic vehicle. We begin with a review of pre-processing techniques for correcting illumination and attenuation artifacts in underwater images, presenting our own approach based on multi-sensor fusion and a strong physical model. Next, we construct a novel image pyramid structure that can reduce the complexity necessary to compute features across multiple scales by an order of magnitude and recommend features which are fast to compute and invariant to underwater artifacts. Finally, we implement our framework on real underwater datasets and demonstrate how it can be used to select summary images for the purpose of creating low-bandwidth semantic maps capable of being transmitted acoustically.

show abstract

Colour-Consistent Structure-from-Motion Models using Underwater Imagery

Cited by 41 publications

References 15 publications

Virtual simulation of a late antique shipwreck at Marzamemi, Sicily: Integrated processes for 3D documentation, analysis and representation of underwater archaeological data

Virtual simulation of a late antique shipwreck at Marzamemi, Sicily: Integrated processes for 3D documentation, analysis and representation of underwater archaeological data

Surface meshing of underwater maps from highly defective point sets

Computational strategies for understanding underwater optical image datasets

Contact Info

Product

Resources

About