Keypoint-Based Analysis of Sonar Images: Application to Seabed Recognition

Nguyen, Huu-Giao; Fablet, Ronan; Ehrhold, Axel; Boucher, Jean‐Marc

doi:10.1109/tgrs.2011.2165848

Cited by 10 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work will further explore this methodology in two directions. On the one hand, BoF could be complemented by an actual characterization of the spatial patterns formed by fish schools based on point process statistics and models (Nguyen et al 2012). On the other hand, local signatures (Nguyen et al 2012) widely used for image processing and computer vision might also provide relevant alternatives, especially when fish schools are poorly defined (e.g., for night data).…”

Section: Echogram-level Analysis and Characterization Of Fisheries Acmentioning

confidence: 99%

Bags-of-Features for fish school cluster characterization in pelagic ecosystems: application to the discrimination of juvenile and adult anchovy (Engraulis ringens) clusters off Peru

Fablet

Peraltilla

Peña

et al. 2012

Can. J. Fish. Aquat. Sci.

Self Cite

View full text Add to dashboard Cite

Whereas fisheries acoustics data processing mainly focused on the detection, characterization, and recognition of individual fish schools, here we addressed the characterization and discrimination of fish school clusters. The proposed scheme relied on the application of the Bags-of-Features (BoF) approach to acoustic echograms. This approach is widely exploited for pattern recognition issues and naturally applies here, considering fish schools as the relevant elementary objects. It relies on the extraction and categorization of fish schools in fisheries acoustic data. Echogram descriptors were computed per unit echogram length as the numbers of schools in different school categories. We applied this approach to the discrimination of juvenile and adult anchovy (Engraulis ringens) off Peru. Whereas the discrimination of individual schools is low (below 70%), the proposed BoF scheme achieved between 89% and 92% of correct classification of juvenile and adult echograms for different survey data sets and significantly outperformed classical school-based echogram characteristics (about 10% of improvement of the correct classification rate). We further illustrate the potential of the proposed scheme for the estimation of the spatial distribution of juvenile and adult anchovy populations.Résumé : Alors que le traitement de données acoustiques sur les ressources halieutiques est principalement axé sur la détec-tion, la caractérisation et la reconnaissance de bancs individuels de poissons, nous nous penchons sur la caractérisation et la discrimination de groupes de bancs de poissons. Le schéma proposé repose sur l'application de l'approche des sacs de mots visuels (« Bags-of-Features » ou BoF) au traitement d'échogrammes acoustiques. Cette approche est fréquemment appliquée aux problèmes de reconnaissance de formes et s'applique donc tout naturellement à l'étude de bancs de poissons en tant qu'objets élémentaires. Elle repose sur l'extraction et la catégorisation de bancs de poissons à partir de données acoustiques sur les ressources halieutiques. Des descripteurs d'échogramme ont été calculés par unité de longueur d'échogramme, correspondant aux nombres de bancs, dans différentes catégories de bancs. Nous avons appliqué cette approche à la discrimination d'anchois (Engraulis ringens) juvéniles et adultes au large des côtes du Pérou. Si la discrimination de bancs individuels est faible (inférieure à 70 %), la classification des échogrammes de juvéniles et d'adultes reposant sur l'approche des BoF s'est avérée exacte dans de 89 % à 92 % des cas pour différents ensembles de données de levés, ce qui correspond à une augmentation significative de l'exactitude par rapport aux approches classiques reposant sur les caractéristiques d'échogram-mes basées sur le banc (augmentation d'environ 10 % du taux de classification exacte). Nous poussons plus loin la démons-tration du potentiel du schéma proposé pour l'estimation de la distribution spatiale des populations d'anchois juvéniles et adultes.[Traduit par la Rédaction]

show abstract

Section: Echogram-level Analysis and Characterization Of Fisheries Acmentioning

confidence: 99%

Bags-of-Features for fish school cluster characterization in pelagic ecosystems: application to the discrimination of juvenile and adult anchovy (Engraulis ringens) clusters off Peru

Fablet

Peraltilla

Peña

et al. 2012

Can. J. Fish. Aquat. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sonar image has the advantages of representing long distance of action as it has strong penetrating ability, and is especially suitable for mixed waters. Therefore, it has been widely used in underwater address geomorphology survey, underwater-lost object searching, mine detection, dam foundation detection and other fields [2].…”

Section: Introductionmentioning

confidence: 99%

Underwater acoustic signal analysis: preprocessing and classification by deep learning

Wu¹,

Song²,

Jin³

2020

NNW

View full text Add to dashboard Cite

The identification and classification is important parts of the research in the field like underwater acoustic signal processing. Recently, deep learning technology has been utilized to achieve good performance in the underwater acoustic signal case. On the other side, there are still some problems should be solved. The first one is that it cannot achieve high accuracy by the dataset that is transformed into audio spectrum. The second one is that the accuracy of classification on the dataset is still low, so that, it cannot satisfy the real demand. To solve those problems, we firstly evaluated four popular spectrums (Audio Spectrum, Image Histogram, Demon and LOFAR) for data preprocessing and selected the best one that is suitable for the neural networks (LeNet, ALEXNET, VGG16). Then, among these methods, we modified a neural network(LeNet) to fit the dataset that is transformed by the spectrum to improve the classification accuracy. The experimental result shows that the accuracy of our method can achieve 97.22 %, which is higher than existing methods and it met the expected target of practical application.

show abstract

“…SURF has been demonstrated to outperform SIFT on speed, repeatability, distinctiveness, and robustness [8]. It has been used for multispectral satellite image registration [24], seabed recognition based on sonar images [25], and SAR image registration [26][27][28][29].…”

Section: Introductionmentioning

confidence: 99%

On Feature-Based SAR Image Registration: Appropriate Feature and Retrieval Algorithm

Dong¹,

Zhang²,

Shi³

2019

Advanced Remote Sensing Technology for Synthetic Aperture Radar Applications, Tsunami Disasters, and Infrastructure

View full text Add to dashboard Cite

An investigation on the appropriate feature and parameter retrieval algorithm is conducted for feature-based registration of synthetic aperture radar (SAR) images. The commonly used features such as tie points, Harris corner, SIFT, and SURF are comprehensively evaluated. SURF is shown to outperform others on criteria such as the geometrical invariance of feature and descriptor, the extraction and matching speed, the localization accuracy, as well as the robustness to decorrelation and speckling. The processing result reveals that SURF has nice flexibility to SAR speckles for the potential relationship between Fast-Hessian detector and refined Lee filter. Moreover, the use of Fast-Hessian to oversampled images with unaltered sampling step helps to improve the registration accuracy to subpixel (i.e., <1 pixel). As for parameter retrieval, the widely used random sample consensus (RANSAC) is inappropriate because it may trap into local occlusion and result in uncertain estimation. An extended fast least trimmed squares (EF-LTS) is proposed, which behaves stable and averagely better than RANSAC. Fitting SURF features with EF-LTS is hence suggested for SAR image registration. The nice performance of this scheme is validated on both InSAR and MiniSAR image pairs.

show abstract

Keypoint-Based Analysis of Sonar Images: Application to Seabed Recognition

Cited by 10 publications

References 53 publications

Bags-of-Features for fish school cluster characterization in pelagic ecosystems: application to the discrimination of juvenile and adult anchovy (Engraulis ringens) clusters off Peru

Bags-of-Features for fish school cluster characterization in pelagic ecosystems: application to the discrimination of juvenile and adult anchovy (Engraulis ringens) clusters off Peru

Underwater acoustic signal analysis: preprocessing and classification by deep learning

On Feature-Based SAR Image Registration: Appropriate Feature and Retrieval Algorithm

Contact Info

Product

Resources

About