Development and experimental evaluation of visual-acoustic navigation for safe maneuvering of unmanned surface vehicles in harbor and waterway areas

Volden, Øystein; Cabecinhas, David; Pascoal, António; Fossen, Thor I.

doi:10.1016/j.oceaneng.2023.114675

Cited by 5 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To cover the many weaknesses of standalone sensors, multisensor fusion is becoming ever more prevalent. [12] propose using cameras and automatic identification systems in junction to improve the situational awareness of Autonomous Surface Vehicles (ASVs), whilst [13] fuse visual, acoustic and inertial data using an error-state Kalman filter for navigation of maritime vessels in narrow waterways. [3], [4] are further examples of how multi-sensor fusion is being investigated in improving Simultaneous Localization And Mapping (SLAM) solutions, allowing for even greater autonomy of unmanned vehicles.…”

Section: A Motivationmentioning

confidence: 99%

GNSS-Independent Maritime Navigation Using Monocular Camera Images with Digital Elevation Map

Roedelé,

Vasstein,

Johansen

2023

2023 IEEE Symposium Sensor Data Fusion and International Conference on Multisensor Fusion and Integration (SDF-MFI)

View full text Add to dashboard Cite

The threat of GNSS service disruption implies the need for GNSS-independent navigation solutions. We introduce a framework that estimates the position of a maritime vessel in a littoral zone through monocular camera images and existing knowledge of the vessel's environment. A set of algorithms extract and match image features from a camera aboard the vessel with synthetic images rendered from a digital elevation model (DEM). The image features, together with the knowledge of the vessel's intended position, are used to infer a 3-dimensional feature inside the DEM. A motion-only bundle adjustment optimization problem is then posed, seeking to estimate the actual position of the vessel by minimizing the reprojection error of the DEM feature. From 57 independent estimation problems with a variance of 70m, the average error results in approximately 25m, demonstrating the technique as a potential candidate for GNSS-independent position estimation.

show abstract

Section: A Motivationmentioning

confidence: 99%

GNSS-Independent Maritime Navigation Using Monocular Camera Images with Digital Elevation Map

Roedelé,

Vasstein,

Johansen

2023

2023 IEEE Symposium Sensor Data Fusion and International Conference on Multisensor Fusion and Integration (SDF-MFI)

View full text Add to dashboard Cite

show abstract

“…Therefore, the precise navigation of USV under signal blocking conditions is challenging. Furthermore, some researchers have also studied the effectiveness of other sensors in USV navigation, such as marine radar [9], visual camera [10], Doppler velocity log [11], etc.…”

Section: Introductionmentioning

confidence: 99%

A robust integrated navigation optimization method for USV in signal occlusion environment

Lou,

Liu,

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

Unmanned surface vehicles (USV) can use global navigation satellite systems (GNSS) and inertial navigation systems (INS) for combined positioning and navigation. However, buildings such as port facilities and bridges blocking GNSS signals will increase the error in the discriminator output in the GNSS vector tracking loop and reduce positioning accuracy. Meanwhile, due to the cumulative error in the inertial navigation system, the credibility of the navigation results when the signal is blocked is further reduced. In this regard, this study proposes a robust integrated navigation optimization method. Specifically, the RTS smoothing optimized Kalman filter is used to constrain the carrier phase error and code phase error output by the discriminator, which can dynamically adjust the gain of the vector tracking loop, thereby improving the signal tracking capability. Simultaneously, the prediction results of the gated recurrent unit (GRU) network optimized based on the attention mechanism are combined with the inertial navigation system to improve navigation accuracy. Furthermore, an adaptive Kalman filter is utilized as the integrated navigation filter. The actual path of the carrier refers to the navigation solution of the existing receiver. In the open environment, the proposed optimization method reduces horizontal positioning error and speed error by 44.7% and 37.1% respectively compared with existing methods. Simultaneously, it can effectively improve the robustness of positioning in signal obstruction environments. The proposed integrated navigation method provides new possibilities for optimizing USV navigation solutions.

show abstract

“…Intelligent maritime traffic monitoring systems and automated ship navigation are gradually becoming tangible realities (Liu et al, Cheng et al, Volden et al. [1][2][3]). Therefore, it is imperative to accurately detect maritime traffic entities (such as ships, buoys, etc.)…”

Section: Introductionmentioning

confidence: 99%

Ship Detection under Low-Visibility Weather Interference via an Ensemble Generative Adversarial Network

Chen,

Wei,

Xin

et al. 2023

JMSE

View full text Add to dashboard Cite

Maritime ship detection plays a crucial role in smart ships and intelligent transportation systems. However, adverse maritime weather conditions, such as rain streak and fog, can significantly impair the performance of visual systems for maritime traffic. These factors constrain the performance of traffic monitoring systems and ship-detection algorithms for autonomous ship navigation, affecting maritime safety. The paper proposes an approach to resolve the problem by visually removing rain streaks and fog from images, achieving an integrated framework for accurate ship detection. Firstly, the paper employs an attention generation network within an adversarial neural network to focus on the distorted regions of the degraded images. The paper also utilizes a contextual encoder to infer contextual information within the distorted regions, enhancing the credibility of image restoration. Secondly, a weighted bidirectional feature pyramid network (BiFPN) is introduced to achieve rapid multi-scale feature fusion, enhancing the accuracy of maritime ship detection. The proposed GYB framework was validated using the SeaShip dataset. The experimental results show that the proposed framework achieves an average accuracy of 96.3%, a recall of 95.35%, and a harmonic mean of 95.85% in detecting maritime traffic ships under rain-streak and foggy-weather conditions. Moreover, the framework outperforms state-of-the-art ship detection methods in such challenging weather scenarios.

show abstract

Development and experimental evaluation of visual-acoustic navigation for safe maneuvering of unmanned surface vehicles in harbor and waterway areas

Cited by 5 publications

References 21 publications

GNSS-Independent Maritime Navigation Using Monocular Camera Images with Digital Elevation Map

GNSS-Independent Maritime Navigation Using Monocular Camera Images with Digital Elevation Map

A robust integrated navigation optimization method for USV in signal occlusion environment

Ship Detection under Low-Visibility Weather Interference via an Ensemble Generative Adversarial Network

Contact Info

Product

Resources

About