Matching Color Aerial Images and Underwater Sonar Images Using Deep Learning for Underwater Localization

Santos, Matheus Machado dos; Giacomo, Giovanni G. De; Drews, Paul; Botelho, Silvia Silva da Costa

doi:10.1109/lra.2020.3013852

Cited by 27 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A few work study the underwater acoustic and aerial image match. Santos et al [5] proposed a Deep Neural Network (DNN) based on a Siamese architecture [7] that handles the cross-domain problem by training two independent networks. Giacomo et al [6] proposed a cooperative approach for training multiple networks to reduce the image dimensionality belonging to the same domain of the present work.…”

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The problem of matching of underwater acoustic and optical aerial images was previously addressed on [4], [5], [6]. Santos et al [4], [5] proposed a Deep Neural Network (DNN) based on a Siamese architecture [7] that handles the Fig. 1: An underwater vehicle doted on multi-beam forwardlooking sonar travels in a semi-structured marina environment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cross-view and Cross-domain Underwater Localization based on Optical Aerial and Acoustic Underwater Images

Santos¹,

Giacomo²,

Drews-Jr³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Cross-view image matches have been widely explored on terrestrial image localization using aerial images from drones or satellites. This study expands the cross-view image match idea and proposes a cross-domain and cross-view localization framework. The method identifies the correlation between color aerial images and underwater acoustic images to improve the localization of underwater vehicles that travel in partially structured environments such as harbors and marinas. The approach is validated on a real dataset acquired by an underwater vehicle in a marina. The results show an improvement in the localization when compared to the dead reckoning of the vehicle.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cross-view and Cross-domain Underwater Localization based on Optical Aerial and Acoustic Underwater Images

Santos¹,

Giacomo²,

Drews-Jr³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In 2020, Matheus Machado Dos Santos et al [1], developed a cross-view as well as cross-domain image identical which was exploited by the underwater acoustic image as well as a color aerial image to recognize the given images are captured or not in a similar place. In partially structured environments, the technique was modeled to match the images obtained with share features namely marinas as well as harbors.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In addition, the light scattering creates the contrast relatively minimum. Therefore, the UI contrast is frequently unacceptable [1].…”

Section: Introductionmentioning

confidence: 99%

Underwater Image Enhancement using Improved Bat Algorithm

Deshmukh¹

2021

View full text Add to dashboard Cite

From the past decades, improving the superiority of an Underwater Image (UI) has received well recognition in terms of the deprived image visibility that is occurred due to the water medium physical property. The light absorption of wavelength-reliant, as well as scattering in an underwater view, degrades the image visibility which causes lesser contrast as well as distorted color casts. To overcome the issues, a highly developed technique is adopted for the advancement and it improves the UI classification. Specifically, by exploiting the Improved Bat Algorithm (IBA), the underwater input image RGB is enhanced. The next stage is feature extraction. To the enhanced Principle Component Analysis (PCA) technique, the extracted attributes are given as input; here the dimensions of the features are minimized. Subsequently, the classification operation is carried out by exploiting the ANFIS classifier. Finally, the classified improved deeper water images besides the improved shallow water images which are seen are available in the testing stage. Finally, the simulation outcomes for the proposed and conventional methods are analyzed. The developed UIE system shows superior accuracy while compared with the conventional techniques.

show abstract

Self-learning Methodology Based on Degradation Estimation for Underwater Image Enhancement

Mello

Moreira

Evald

et al. 2022

Intelligent Systems

View full text Add to dashboard Cite

Matching Color Aerial Images and Underwater Sonar Images Using Deep Learning for Underwater Localization

Cited by 27 publications

References 22 publications

Cross-view and Cross-domain Underwater Localization based on Optical Aerial and Acoustic Underwater Images

Cross-view and Cross-domain Underwater Localization based on Optical Aerial and Acoustic Underwater Images

Underwater Image Enhancement using Improved Bat Algorithm

Self-learning Methodology Based on Degradation Estimation for Underwater Image Enhancement

Contact Info

Product

Resources

About