Textural Segmentation of Sidescan Sonar Images Based on Gabor Filters Bank and Active Contours without Edges

Samiee, Kaveh; Rad, Gholam Ali Rezai

doi:10.1109/avss.2008.11

Cited by 8 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[24] uses the coefficient of multi-scale orthogonal wavelet decomposition to extract the features where each sliding window of SAS images is treated as a unique data point. [25], [26] use the superposition of Gabor filter banks response to represent seabed textures.…”

Section: Related Workmentioning

confidence: 99%

Iterative, Deep Synthetic Aperture Sonar Image Segmentation

Sun,

Gerg,

Monga

2022

Preprint

View full text Add to dashboard Cite

Synthetic aperture sonar (SAS) systems produce high-resolution images of the seabed environment. Moreover, deep learning has demonstrated superior ability in finding robust features for automating imagery analysis. However, the success of deep learning is conditioned on having lots of labeled training data, but obtaining generous pixel-level annotations of SAS imagery is often practically infeasible. This challenge has thus far limited the adoption of deep learning methods for SAS segmentation. Algorithms exist to segment SAS imagery in an unsupervised manner, but they lack the benefit of state-of-theart learning methods and the results present significant room for improvement. In view of the above, we propose a new iterative algorithm for unsupervised SAS image segmentation combining superpixel formation, deep learning, and traditional clustering methods. We call our method Iterative Deep Unsupervised Segmentation (IDUS). IDUS is an unsupervised learning framework that can be divided into four main steps: 1) A deep network estimates class assignments. 2) Low-level image features from the deep network are clustered into superpixels. 3) Superpixels are clustered into class assignments (which we call pseudo-labels) using k-means. 4) Resulting pseudo-labels are used for loss backpropagation of the deep network prediction. These four steps are performed iteratively until convergence. A comparison of IDUS to current state-of-the-art methods on a realistic benchmark dataset for SAS image segmentation demonstrates the benefits of our proposal even as the IDUS incurs a much lower computational burden during inference (actual labeling of a test image). Because our design combines merits of classical superpixel methods with deep learning, practically we demonstrate a very significant benefit in terms of reduced selection bias, i.e. IDUS shows markedly improved robustness against the choice of training images. Finally, we also develop a semi-supervised (SS) extension of IDUS called IDSS and demonstrate experimentally that it can further enhance performance while outperforming supervised alternatives that exploit the same labeled training imagery.

show abstract

Section: Related Workmentioning

confidence: 99%

Iterative, Deep Synthetic Aperture Sonar Image Segmentation

Sun,

Gerg,

Monga

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…9,14,17,45 Much seabed classification research has focused on using sonar image texture as a discriminative subspace, with feature creation methods including; Gabor filter banks, 46 Wavelets, 15,47 the prevalent Grey Level Co-occurrence Matrices (GLCM) 11,17,48 and a fusion of different feature types. 18 For an evaluation of several state-of-the-art statistical, signal processing-based and morphologybased features applied to a related problem on sonar waterfall imagery, refer to our recent paper.…”

Section: Application Contextmentioning

confidence: 99%

Novel Consensus Approaches to the Reliable Ranking of Features for Seabed Imagery Classification

Harrison

Birchall²,

Mann³

et al. 2012

Int. J. Neur. Syst.

View full text Add to dashboard Cite

Feature saliency estimation and feature selection are important tasks in machine learning applications. Filters, such as distance measures are commonly used as an efficient means of estimating the saliency of individual features. However, feature rankings derived from different distance measures are frequently inconsistent. This can present reliability issues when the rankings are used for feature selection. Two novel consensus approaches to creating a more robust ranking are presented in this paper. Our experimental results show that the consensus approaches can improve reliability over a range of feature parameterizations and various seabed texture classification tasks in sidescan sonar mosaic imagery.

show abstract

“…Different methods for the generic textural analysis of sonar images have been studied widely and include; Gabor filters [10]; Wavelets [11,12] and Co-occurrence matrices [13,14,15]. Yet there is no published research on features which could be used for our specific task -the automated identification of Sabellaria in sidescan imagery.…”

Section: Introductionmentioning

confidence: 99%

A Texture Analysis Approach to Identifying Sabellaria Spinulosa Colonies in Sidescan Sonar Imagery

Harrison¹,

Bianconi

Harvey

et al. 2011

2011 Irish Machine Vision and Image Processing Conference

View full text Add to dashboard Cite

Offshore wind farms are undergoing unprecedented development as EU member states focus on complying with 2020 renewable energy mandates. However, wind farm site placement requires great care, to avoid compromising protected habitats, such as Sabellaria spinulosa reefs. This paper presents an investigation into the potential of different feature generation methods for identifying sidescan sonar image textures characteristic of Sabellaria spinulosa colonies. We propose an extensible test methodology and carry out a detailed comparison of several textural features. Our results show that Gabor filter bank features yield good (up to 89.4% overall) classification accuracies and often outperform other methods in identifying the Sabellaria spinulosa textural class. A DualTree Complex Wavelet Transform, Ring filters and some statistical methods also produce encouraging results.

show abstract

Textural Segmentation of Sidescan Sonar Images Based on Gabor Filters Bank and Active Contours without Edges

Cited by 8 publications

References 12 publications

Iterative, Deep Synthetic Aperture Sonar Image Segmentation

Iterative, Deep Synthetic Aperture Sonar Image Segmentation

Novel Consensus Approaches to the Reliable Ranking of Features for Seabed Imagery Classification

A Texture Analysis Approach to Identifying Sabellaria Spinulosa Colonies in Sidescan Sonar Imagery

Contact Info

Product

Resources

About