Shipwrecks Detection Based on Deep Generation Network and Transfer Learning with Small Amount of Sonar Images

Xu, Lixue; Wang, Xiubo; Wang, Xudong

doi:10.1109/ddcls.2019.8909011

Cited by 7 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wrecks were occasionally detectable in 3 m resolution imagery, so this imagery could potentially be used in future modeling. This finding is aligned with manual shipwreck identification conducted by Plets et al [26], from which the authors conclude that the required imagery resolution for shipwreck identification is less than 2 m. Fewer than 10 shipwrecks that we detected were easily discernible (Figure 10), while most wrecks appeared simply as anomalous topography (Figure 11). In addition to the spatial resolution of bathymetric data, wreck detection was affected by water depth and clarity.…”

Section: Discussionsupporting

confidence: 90%

“…All other published related work focuses either on a very small study area that includes fewer than four shipwrecks [5,12,24] or used privately available side scan sonar [17,18,25,26]. While some of these projects produce shipwreck detection results comparable with the new work presented here, the work presented here differs in three significant ways: (1) the study area is very large, which enables rapid mapping of huge areas all at once; (2) the imagery is open source, which means this methodology could be replicated for additional study areas; (3) the imagery used includes a substantial amount of airborne lidar which means that imagery can be efficiently collected over a much larger area than with a shipborne or unmanned platform.…”

Section: Discussionmentioning

confidence: 99%

“…As is evidenced by the low precision values, the authors had problems with false positives similar to Pasquet et al [12] and Drap et al [5]. Xu et al [26] used a neural network to detect shipwrecks in sonar imagery with a very small training dataset. They tested model performance both with and without transfer learning and found that transfer learning improved the model significantly: the model produced mean average precision values of 73% and 81% without transfer learning and with transfer learning, respectively.…”

Section: Background and Related Literaturementioning

confidence: 95%

See 2 more Smart Citations

Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar

et al. 2021

View full text Add to dashboard Cite

The objective of this project is to create a new implementation of a deep learning model that uses digital elevation data to detect shipwrecks automatically and rapidly over a large geographic area. This work is intended to apply a new methodology to the field of underwater archaeology. Shipwrecks represent a major resource to understand maritime human activity over millennia, but underwater archaeology is expensive, misappropriated, and hazardous. An automated tool to rapidly detect and map shipwrecks can therefore be used to create more accurate maps of natural and archaeological features to aid management objectives, study patterns across the landscape, and find new features. Additionally, more comprehensive and accurate shipwreck maps can help to prioritize site selection and plan excavation. The model is based on open source topo-bathymetric data and shipwreck data for the United States available from NOAA. The model uses transfer learning to compensate for a relatively small sample size and addresses a recurring problem that associated work has had with false positives by training the model both on shipwrecks and background topography. Results of statistical analyses conducted—ANOVAs and box and whisker plots—indicate that there are substantial differences between the morphologic characteristics that define shipwrecks vs. background topography, supporting this approach to addressing false positives. The model uses a YOLOv3 architecture and produced an F1 score of 0.92 and a precision score of 0.90, indicating that the approach taken herein to address false positives was successful.

show abstract

Section: Discussionsupporting

confidence: 90%

Section: Discussionmentioning

confidence: 99%

Section: Background and Related Literaturementioning

confidence: 95%

See 1 more Smart Citation

Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar

et al. 2021

View full text Add to dashboard Cite

show abstract

“…BerganZo-BeSga et al, 2021;chen et al, 2021;caSpari y creSpo, 2019). También se emplea en estudios espaciales con el objetivo de diseñar estrategias para la prevención, protección y gestión del patrimonio arqueológico (ej., friggenS et al, 2021;daviS et al, 2021;Xu et al, 2019;caStiello y tonini, 2019). En tercer lugar, los estudios de sistemas socioecológicos utilizan AA para explorar diversas temáticas como los movimientos migratorios (vahdati et al, 2019), la gestión de los recursos sociales y económicos (ej.…”

Section: Aplicación Del Aprendizaje Automático En Arqueologíaunclassified

Aplicación del aprendizaje automático en Arqueología: ¿Un cambio de paradigma?

Palacios

2023

VEG

View full text Add to dashboard Cite

Aunque las primeras aplicaciones de aprendizaje automático en arqueología datan de finales de los años 90, no ha sido hasta el año 2019 cuando su uso se ha empezado a extender. ¿Qué ventajas tiene esta metodología respecto a otros métodos con una trayectoria más larga en arqueología? ¿Se puede aplicar en todos los ámbitos de estudio? La presente contribución tiene el objetivo de dar respuesta a estas cuestiones a través de una exhaustiva revisión de los estudios arqueológicos realizados con esta metodología y desarrollando un modelo con un algoritmo concreto, las redes bayesianas, para explorar sus beneficios y limitaciones. Despite initial attempts to apply machine learning to archaeology dating back to the late 1990s, it was not until 2019 that its use began to become widespread. What advantages does this methodology have over previous methods? Can it be applied to all relevant fields of study? This article aims to answer these questions through an exhaustive review of archaeological studies that employ this methodology and by developing a model with a specific algorithm, based on Bayesian networks, to explore its benefits and limitations.

show abstract

“…Lima et al [8] proposed a deep transfer learning method for automatic ocean front recognition, extracting knowledge from deep CNN models trained on historical data. Xu et al [9] presented an approach combining deep generation networks and transfer learning for sonar shipwrecks detection. Ren et al [10] proposed an encoder-decoder framework with fully convolutional networks that can predict sea ice concentration oneweek in advance with high accuracy.…”

mentioning

confidence: 99%

Physical Knowledge-Enhanced Deep Neural Network for Sea Surface Temperature Prediction

Meng

Gao

Rigall

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Traditionally, numerical models have been deployed in oceanography studies to simulate ocean dynamics by representing physical equations. However, many factors pertaining to ocean dynamics seem to be ill-defined. We argue that transferring physical knowledge from observed data could further improve the accuracy of numerical models when predicting Sea Surface Temperature (SST). Recently, the advances in earth observation technologies have yielded a monumental growth of data. Consequently, it is imperative to explore ways in which to improve and supplement numerical models utilizing the everincreasing amounts of historical observational data. To this end, we introduce a method for SST prediction that transfers physical knowledge from historical observations to numerical models. Specifically, we use a combination of an encoder and a generative adversarial network (GAN) to capture physical knowledge from the observed data. The numerical model data is then fed into the pre-trained model to generate physics-enhanced data, which can then be used for SST prediction. Experimental results demonstrate that the proposed method considerably enhances SST prediction performance when compared to several state-ofthe-art baselines.

show abstract

Shipwrecks Detection Based on Deep Generation Network and Transfer Learning with Small Amount of Sonar Images

Cited by 7 publications

References 15 publications

Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar

Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar

Aplicación del aprendizaje automático en Arqueología: ¿Un cambio de paradigma?

Physical Knowledge-Enhanced Deep Neural Network for Sea Surface Temperature Prediction

Contact Info

Product

Resources

About