Safe Vessel Navigation Visually Aided by Autonomous Unmanned Aerial Vehicles in Congested Harbors and Waterways

Sejersen, Jonas le Fevre; Figueiredo, Rui J. P. de; Kayacan, Erdal

doi:10.1109/case49439.2021.9551637

Cited by 12 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where c i,j is the weighted sum metric of i-th track and j-th bounding box, λ is a hyperparameter, d (1) (i, j) and d (2) (i, j) is the motion metric and appearance metric. This metric is used to solve the association problem with the Hungarian method.…”

Section: Multiple-object Tracking From Top-viewmentioning

confidence: 99%

See 1 more Smart Citation

A Real-Time Method for Time-to-Collision Estimation from Aerial Images

et al. 2022

Self Cite

View full text Add to dashboard Cite

When large vessels such as container ships are approaching their destination port, they are required by law to have a maritime pilot on board responsible for safely navigating the vessel to its desired location. The maritime pilot has extensive knowledge of the local area and how currents and tides affect the vessel’s navigation. In this work, we present a novel end-to-end solution for estimating time-to-collision time-to-collision (TTC) between moving objects (i.e., vessels), using real-time image streams from aerial drones in dynamic maritime environments. Our method relies on deep features, which are learned using realistic simulation data, for reliable and robust object detection, segmentation, and tracking. Furthermore, our method uses rotated bounding box representations, which are computed by taking advantage of pixel-level object segmentation for enhanced TTC estimation accuracy. We present collision estimates in an intuitive manner, as collision arrows that gradually change its color to red to indicate an imminent collision. A set of experiments in a realistic shipyard simulation environment demonstrate that our method can accurately, robustly, and quickly predict TTC between dynamic objects seen from a top-view, with a mean error and a standard deviation of 0.358 and 0.114 s, respectively, in a worst case scenario.

show abstract

Section: Multiple-object Tracking From Top-viewmentioning

confidence: 99%

“…However, ensuring safe navigation inside dock environments is demanding as mistakes can be extremely costly, time-consuming to correct, and even fatal. An assisting tool working autonomously to support the maritime pilot by predicting possible collisions would lower the risk involved with navigating the vessel [ 2 , 3 ].…”

Section: Introductionmentioning

confidence: 99%

A Real-Time Method for Time-to-Collision Estimation from Aerial Images

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore we have chosen BiSeNetv2, instead of other better performing ones such as Mask RCNN. However, other similar architectures such as HarDNet Hong et al (2021) and Chao et al (2019) , would be suitable alternatives, as demonstrated in le Fevre Sejersen et al (2021) . We emphasize that the main focus of this work was on using probabilistic semantic information for NBV planning.…”

Section: Methodsmentioning

confidence: 99%

Integrated design-sense-plan architecture for autonomous geometric-semantic mapping with UAVs

et al. 2022

Self Cite

View full text Add to dashboard Cite

This article presents a complete solution for autonomous mapping and inspection tasks, namely a lightweight multi-camera drone design coupled with computationally efficient planning algorithms and environment representations for enhanced autonomous navigation in exploration and mapping tasks. The proposed system utilizes state-of-the-art Next-Best-View (NBV) planning techniques, with geometric and semantic segmentation information computed with Deep Convolutional Neural Networks (DCNNs) to improve the environment map representation. The main contributions of this article are the following. First, we propose a novel efficient sensor observation model and a utility function that encodes the expected information gains from observations taken from specific viewpoints. Second, we propose a reward function that incorporates both geometric and semantic probabilistic information provided by a DCNN for semantic segmentation that operates in close to real-time. The incorporation of semantics in the environment representation enables biasing exploration towards specific object categories while disregarding task-irrelevant ones during path planning. Experiments in both a virtual and a real scenario demonstrate the benefits on reconstruction accuracy of using semantics for biasing exploration towards task-relevant objects, when compared with purely geometric state-of-the-art methods. Finally, we present a unified approach for the selection of the number of cameras on a UAV, to optimize the balance between power consumption, flight-time duration, and exploration and mapping performance trade-offs. Unlike previous design optimization approaches, our method is couples with the sense and plan algorithms. The proposed system and general formulations can be be applied in the mapping, exploration, and inspection of any type of environment, as long as environment dependent semantic training data are available, with demonstrated successful applicability in the inspection of dry dock shipyard environments.

show abstract

“…Considering the realistic rendering engine used in our experiments, the simulationreality gap should be easily overcome with a few real-life samples, as demonstrated in [18,19].…”

Section: Data Collection Methods and Toolsmentioning

confidence: 99%

A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this work we present a novel end-to-end solution for tracking objects (i.e., vessels), using video streams from aerial drones, in dynamic maritime environments. Our method relies on deep features, which are learned using realistic simulation data, for robust object detection, segmentation and tracking. Furthermore, we propose the use of rotated bounding-box representations, which are computed by taking advantage of pixel-level object segmentation, for improved tracking accuracy, by reducing erroneous data associations during tracking, when combined with the appearance-based features. A thorough set of experiments and results obtained in a realistic shipyard simulation environment, demonstrate that our method can accurately, and fast detect and track dynamic objects seen from a top-view.

show abstract

Safe Vessel Navigation Visually Aided by Autonomous Unmanned Aerial Vehicles in Congested Harbors and Waterways

Cited by 12 publications

References 18 publications

A Real-Time Method for Time-to-Collision Estimation from Aerial Images

A Real-Time Method for Time-to-Collision Estimation from Aerial Images

Integrated design-sense-plan architecture for autonomous geometric-semantic mapping with UAVs

A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images

Contact Info

Product

Resources

About