Seafloor Classification With Neural Networks

Αλεξάνδρου, Δ.; Pantzartzis, D.

doi:10.1109/oceans.1990.584692

Cited by 10 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the two other classes, it is a discriminating parameter since rock (label w 4 ) shadows are larger than the ones created by pebbles (label w 3 ). We define for the parameter N max µ 1,4 (N max ) = µ 2,4 (N max ) = 1…”

Section: Fuzzy Classificationmentioning

confidence: 99%

“…High-resolution sidescan sonar plays an important role in underwater sensing, for it provides acoustic "images" of the seabed whose quality is much higher than that of images 1 The authors thank GESMA ("Groupe d'Étude Sous-Marine de l'Atlantique," Brest, France), for having provided numerous real sonar pictures, and DGA ("Direction Générale de l'Armement," French Ministry of Defense) for financial support of this work via student grant.…”

Section: Introductionmentioning

confidence: 99%

“…Neural classifiers have also been considered [1,2,5,14,21,25,26,28]. In that case, one does not make use of much parametric prior knowledge.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Markov Random Field and Fuzzy Logic Modeling in Sonar Imagery: Application to the Classification of Underwater Floor

Mignotte¹,

Collet²,

Pérez

et al. 2000

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Section: Fuzzy Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Markov Random Field and Fuzzy Logic Modeling in Sonar Imagery: Application to the Classification of Underwater Floor

Mignotte¹,

Collet²,

Pérez

et al. 2000

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…Combined with BS data and some traditional sediment sampling data, it brings a fast and effective method for acoustic seabed sediment classification. In the previous studies, there are so many methods applied including spectral analysis (Reut et al 1985;Pace and Gao 1998), texture analysis (Subramaniam et al 1993;Pican et al 1998;Blondel and Sichi 2009;Zieger et al 2009), statistical classification (Huseby 1993;Michalopoulou et al 1995;Simons and Snellen 2009), and neural network (Alexandrou and Pantzartzis 1990;Kavli et al 1993;Stewart et al 1994;Chakraborty et al 2001Chakraborty et al , 2003Yang and Liu 2003;Zhou et al 2006;Satyanarayana 2007). The neural network methods (Chakraborty et al 2001(Chakraborty et al , 2003Zhou et al 2006), especially, are applied in the seabed sediment classification with multi-beam echo sounder BS data to achieve better classification results than the traditional classification methods.…”

Section: Introductionmentioning

confidence: 99%

Seabed Mixed Sediment Classification with Multi-beam Echo Sounder Backscatter Data in Jiaozhou Bay

Tang

Lei

et al. 2014

Marine Georesources & Geotechnology

View full text Add to dashboard Cite

The multi-beam echo sounder system can not only obtain high-precision seabed bathymetry data, but also obtain high-resolution seabed backscatter strength data. A number of studies have applied acoustic remote sensing method to classify seabed sediment type with multi-beam backscatter strength data, and obtained better classification results than the traditional sediment sampling method. However, these studies mainly focus on the single type sediment classification or seabed mixed sediment classification using single beam data, not multi-beam echo sounder data. Based on backscatter strength data by a high-frequency (300 kHz) Simrad EM3000 multi-beam echo sounder and seabed sediment sampling data of Jiaozhou Bay in Qingdao, China, we establish the relation model between seabed backscatter strength and sediment type characteristics after data processing and corrections. The purpose of data processing is to diminish or weaken the influence of local bottom slope and near nadir reflection on backscatter strength data. Processed backscatter strength data through corrections and compensations can better characterize the features of the seabed sediments. Applying the back propagation neural network method based on genetic algorithm, we present a fast and accurate seabed classification method in this paper which could identify not just a single type of sediment-like rock, sand but also mixed types of sediment like sand gravel, clayey silt and sand-silt-clay.

show abstract

“…Similar models have been used by other workers [2] to investigate the ability of a neural network to learn to classify different ocean-bottom types by means of simulation studies. Their work, however, focused on modeling of the reverberation from distributions of point reflectors but did not consider the modeling of target echoes.…”

Section: Introductionmentioning

confidence: 97%

Neural networks for active echo classification

Maksym¹

1995 International Conference on Acoustics, Speech, and Signal Processing

View full text Add to dashboard Cite

Target and Clutter ModelsThis paper explores the use of an artificial neural network to distinguish between echoes from a constellation of acoustic reflectors representing a target and similar echoes produced by other reflectors, e.g. reverberation. The network was both trained and tested with simulated data. A wide band linear frequency modulated pulse was used in order to resolve the highlights of the target.

show abstract

Seafloor Classification With Neural Networks

Cited by 10 publications

References 7 publications

Markov Random Field and Fuzzy Logic Modeling in Sonar Imagery: Application to the Classification of Underwater Floor

Markov Random Field and Fuzzy Logic Modeling in Sonar Imagery: Application to the Classification of Underwater Floor

Seabed Mixed Sediment Classification with Multi-beam Echo Sounder Backscatter Data in Jiaozhou Bay

Neural networks for active echo classification

Contact Info

Product

Resources

About