Imaging Techniques

Smith, Christopher J.; Rumohr, Heye

doi:10.1002/9781118542392.ch3

Cited by 8 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MBES systems also enable recording of acoustic images of the seabed by recording the strength of the backscattering signal. However, the images are of lower resolution and poorer quality than acoustic backscattering images provided by side scan sonars [35].…”

Section: Acoustic Systems For Imaging Of Seabed and Underwater Objectsmentioning

confidence: 98%

Results from Developments in the Use of a Scanning Sonar to Support Diving Operations from a Rescue Ship

Grządziel

2020

Remote Sensing

View full text Add to dashboard Cite

In recent years, widespread use of scanning sonars for acoustic imaging of the seabed surface can be observed. These types of sonars are mainly used with tripods or special booms, or are mounted onboard remotely operated or unmanned vehicles. Typical scanning sonar applications include search and recovery operations, imaging of underwater infrastructure, and scour monitoring. The use of these sonars is often limited to shallow waters. Diver teams or underwater remotely operated vehicles (ROV) are commonly used to inspect shipwrecks, port wharfs, and ship hulls. However, reduced underwater visibility, submerged debris, and extreme water depths can limit divers’ capabilities. In this paper, a novel, nonstandard technique for use of a scanning sonar is proposed. The new application for scanning sonar technology is a practical solution developed on the Polish Navy’s search and rescue ship “Lech.” To verify the effectiveness of the proposed technique, the author took part in four different studies carried out in the southeastern Baltic Sea. The tests were performed using the MS 1000 scanning sonar. The results demonstrate that the proposed technique has the potential to provide detailed sonar images of the seabed and underwater objects before the descent of divers. The divers get acquainted with the underwater situation, which undoubtedly increases the safety of the entire operation. Scanning sonars are unlikely to completely replace the work of divers but may reduce the number and duration of dives. The sonar use technique turned out to be useful when rescuing a crew of a submarine that crashed and settled on the sea bottom as part of a naval exercise. The sonar data obtained during four experimental tests performed in the Baltic Sea prove the validity, usefulness, and significance of the proposed technique, especially from the standpoint of safety of underwater work.

show abstract

Section: Acoustic Systems For Imaging Of Seabed and Underwater Objectsmentioning

confidence: 98%

Results from Developments in the Use of a Scanning Sonar to Support Diving Operations from a Rescue Ship

Grządziel

2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Imaging systems are increasingly being used to study aquatic organisms and their interactions with the environment at different spatial and temporal scales (Solan et al 2003; Wiebe and Benfield 2003; Smith and Rumohr 2013; Durden et al 2016; Shortis et al 2016; Irisson et al 2022). In light of the rapid developments and diverse applications of various imaging systems, automated image processing encounters several challenges.…”

Section: Figmentioning

confidence: 99%

Taming the data deluge: A novel end‐to‐end deep learning system for classifying marine biological and environmental images

Bi,

Cheng,

Cheng

et al. 2023

Limnology & Ocean Methods

View full text Add to dashboard Cite

Underwater imaging enables nondestructive plankton sampling at frequencies, durations, and resolutions unattainable by traditional methods. These systems necessitate automated processes to identify organisms efficiently. Early underwater image processing used a standard approach: binarizing images to segment targets, then integrating deep learning models for classification. While intuitive, this infrastructure has limitations in handling high concentrations of biotic and abiotic particles, rapid changes in dominant taxa, and highly variable target sizes. To address these challenges, we introduce a new framework that starts with a scene classifier to capture large within‐image variation, such as disparities in the layout of particles and dominant taxa. After scene classification, scene‐specific Mask regional convolutional neural network (Mask R‐CNN) models are trained to separate target objects into different groups. The procedure allows information to be extracted from different image types, while minimizing potential bias for commonly occurring features. Using in situ coastal plankton images, we compared the scene‐specific models to the Mask R‐CNN model encompassing all scene categories as a single full model. Results showed that the scene‐specific approach outperformed the full model by achieving a 20% accuracy improvement in complex noisy images. The full model yielded counts that were up to 78% lower than those enumerated by the scene‐specific model for some small‐sized plankton groups. We further tested the framework on images from a benthic video camera and an imaging sonar system with good results. The integration of scene classification, which groups similar images together, can improve the accuracy of detection and classification for complex marine biological images.

show abstract

“…Imaging systems are increasingly being used to study aquatic organisms and their interactions with the environment at different spatial and temporal scales [1][2][3][4][5][6]. Despite the rapid developments and applications of various imaging systems, automated image processing faces several challenges: The root of the problem lies in in the field's lack of an adopted unified processing framework.…”

Section: Introductionmentioning

confidence: 99%

Taming the data deluge: a novel end-to-end deep learning system for classifying marine biological and environmental images

Cheng

et al. 2022

Preprint

View full text Add to dashboard Cite

Marine underwater imaging facilitates non-destructive sampling of species at frequencies, durations, and accuracies that are unattainable by conventional sampling methods. These systems necessitate complex automated processes to identify organisms efficiently, however, current frameworks struggle to disentangle ecological foreground components from their dispensable background content. Underwater image processing relies on common architecture: namely image binarization for segmenting potential targets, prior to information extraction and classification by deep learning models. While intuitive, this infrastructure underperforms as it has difficulty in handling: high concentrations of biotic and abiotic particles, rapid changes in dominant taxa, and target sizes that vary by several orders of magnitude. To overcome these issues, a new framework is presented that begins with a scene classifier to capture large within-image variation, such as disparities in particle concentration and dominant taxa. Following scene classification, scene-specific regional convolutional neural network (Mask R-CNN) models were trained to separate target objects into different taxonomic groups. The procedure allows information to be extracted from different image types, while minimizing potential bias for commonly occurring features. Usingin situcoastal PlanktonScope images, we compared the scene-specific models to the Mask R-CNN model including all scene categories without scene classification, defined as the full model, and found that the scene-specific approach outperformed the full model with >20% accuracy in noisy images. The full model missed up to 78% of the dominant taxonomic groups, such asLyngbya, Noctiluca, andPhaeocystiscolonies. This performance improvement is due to the scene classifier, which reduces the variation among images and allows an improved match between the observed taxonomic groups and the taxonomic groups in pre-trained models. We further tested the framework on images from a benthic video camera and an imaging sonar system. Results demonstrate that the procedure is applicable to different types of underwater images and achieves significantly more accurate results than the full model. Given that the unified framework is neither instrument nor ecosystem-specific, the proposed model facilitates deployment throughout the marine biome.

show abstract

Imaging Techniques

Cited by 8 publications

References 17 publications

Results from Developments in the Use of a Scanning Sonar to Support Diving Operations from a Rescue Ship

Results from Developments in the Use of a Scanning Sonar to Support Diving Operations from a Rescue Ship

Taming the data deluge: A novel end‐to‐end deep learning system for classifying marine biological and environmental images

Taming the data deluge: a novel end-to-end deep learning system for classifying marine biological and environmental images

Contact Info

Product

Resources

About