A Framework for Underwater Vehicle Localization based on Cross-view and Cross-domain Acoustic and Aerial Images

2021 ◽  
Author(s):  
Matheus M. Dos Santos ◽  
Giovanni G. De Giacomo ◽  
Paulo L. J. Drews-Jr ◽  
Silvia S. C. Botelho ◽  
Claudio D. Mello
Keyword(s):  
Underwater Vehicle ◽  
Aerial Images ◽  
Vehicle Localization ◽  
Cross Domain

Predictive and sliding mode cascade control for cross-domain locomotion of a coaxial aerial underwater vehicle with disturbances

2020 ◽  
Vol 100 ◽  
pp. 102183 ◽  
Author(s):  
Hanwen Zhang ◽  
Zheng Zeng ◽  
Caoyang Yu ◽  
Zhining Jiang ◽  
Bo Han ◽  
...  
Keyword(s):  
Sliding Mode ◽  
Underwater Vehicle ◽  
Cascade Control ◽  
Cross Domain

scholarly journals An Observability Metric for Underwater Vehicle Localization Using Range Measurements

Sensors ◽  
2013 ◽  
Vol 13 (12) ◽  
pp. 16191-16215 ◽  
Author(s):  
Filippo Arrichiello ◽  
Gianluca Antonelli ◽  
Antonio Aguiar ◽  
Antonio Pascoal
Keyword(s):  
Underwater Vehicle ◽  
Vehicle Localization ◽  
Range Measurements

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

2021 ◽  
Vol 7 (12) ◽  
pp. 270
Author(s):  
Daniel Tøttrup ◽  
Stinus Lykke Skovgaard ◽  
Jonas le Fevre Sejersen ◽  
Rui Pimentel de Figueiredo
Keyword(s):  
Object Segmentation ◽  
Aerial Images ◽  
Simulation Environment ◽  
Tracking Accuracy ◽  
Video Streams ◽  
Simulation Data ◽  
Vehicle Localization ◽  
Top View ◽  
Tracking Objects ◽  
Localization And Tracking

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.

Sign in / Sign up

Export Citation Format

Share Document