96 research outputs found
Underwater laser-based structured light system for one-shot 3D reconstruction
No full textA Laser-based Structured Light System (LbSLS) has been designed to perform underwater close-range 3D reconstructions even with high turbidity conditions and outperform conventional systems. The system uses a camera and a 532 nm green laser projector. The optical technique used is based on the projection of a pattern obtained placing a Diffractive Optical Element (DOE) in front of the laser beam. In the experiments described in this manuscript, the DOE used diffracts the laser beam in 25 parallel lines providing enough information in a single camera frame to perform a 3D reconstruction
Optical Sensors and Methods for Underwater 3D Reconstruction
No full textThis paper presents a survey on optical sensors and methods for 3D reconstruction in underwater environments. The techniques to obtain range data have been listed and explained, together with the different sensor hardware that makes them possible. The literature has been reviewed, and a classification has been proposed for the existing solutions. New developments, commercial solutions and previous reviews in this topic have also been gathered and considered
One-shot underwater 3D reconstruction
No full textA one-shot sensor for underwater 3D reconstruction is presented and tested underwater in a water tank. The system is composed of a RGB CCD camera and a 532 nm green laser with a Diffractive Optical Element attached to it. The laser projects a pattern of parallel lines into the scene. The deformed pattern obtained in the camera frame is then processed to obtain a non-dense 3D point cloud that can be later used for autonomous manipulation and grasping, or for detailed mapping of textureless objects or scenarios
Evaluation of a laser based structured light system for 3D reconstruction of underwater environments
No full textPeer Reviewe
Diseño y construcción de una plataforma móvil para aplicaciones de robótica de campo
No full text[spa] El presente proyecto consiste en el diseño, construcción y control de una plataforma
robot para aplicaciones de robótica de campo. Ha sido realizado en colaboración con
los profesores Gabriel Oliver Codina y José Guerrero Sastre de la Escuela Politécnica
Superior de la Universidad de las Islas Baleares como Trabajo de Fin de Grado de la
titulación Grado en Ingeniería Electrónica Industrial y Automática. Este es un proyecto
de plataforma robot eficiente, robusta, y útil.
A lo largo de esta memoria se explicarán las diferentes fases del proyecto: desde el
dimensionado de los motores y la elección de los componentes del proyecto,pasando
por la construcción de la parte mecánica del robot,así como la programación del
algoritmo de control de ésta.También se ha diseñado un protocolo de comunicación
bluetooth para para el control de la plataforma robot con una app para dispositivos
Android. Una de las características principales es que se trata de un proyecto flexible ya
que su diseño está abierto a muchas posibilidades de evolución para trabajos futuros
dada su implementación (plataformaOpen-Hardware Arduino) : como la incorporación
de sensores de reconocimiento de terreno como un sensor ultrasónico o un sensor
laser, la instalación de un brazo robot encima de la plataforma o la incorporación de
varias cámaras
Texture analysis of seabed images: Quantifying the presence of Posidonia oceanica at Palma Bay
No full textAn automatic classifier algorithm has been designed to assess the population of Posidonia oceanica over a set of underwater images at Palma Bay. Law's energy filters and statistical descriptors of the Gray Level Co-occurrence Matrix have been use to correctly classify the input image patches in two classes: Posidonia oceanica or not Posidonia oceanica. The input images have been first preprocessed and splitted in three different patch sizes in order to find the best patch size to better classify this seagrass. From all the attributes obtained in these patches, a best subset algorithm has been run to choose the best ones and a decision tree classifier has been trained. The classifier was made by training a Logistic Model Tree from 125 pre-classified images. This classifier was finally tested on 100 new images. The classifier outputs gray level images where black color indicates Posidonia oceanica presence and white no presence. Intermediate values are obtained by overlapping the processed patches, resulting in a smoother final result. This images can be merged in an offline process to obtain density maps of this algae in the sea
Stereo-vision graph-SLAM for robust navigation of the AUV SPARUS II
No full textThis paper presents the integration of a stereo-vision Graph-SLAM system in the navigation and control architecture of the Autonomous Underwater Vehicle (AUV) SPARUS II. The navigation architecture of SPARUS II is endowed with an Extended Kalman Filter (EKF) that fuses the data provided by a Doppler Velocity Log (DVL), a pressure sensor, a GPS (when the vehicle is in the surface) and an Inertial Measurement Unit (IMU). But due to the nature of the aforementioned sensors, this localization data is prone to drift. Instead, the stereo-vision Graph-SLAM clearly improves the localization data thanks to the additional pose constraints computed from visual (stereo) loop closings. SLAM estimates are thereafter inserted in the control architecture to increase the precision in the navigation and mission tasks. Experiments with SPARUS II in simulated environments show the improvement and benefits in the application of this SLAM approach for localization, navigation and control, with respect to the use of the EKF odometry
Xiroi ASV: a modular Autonomous Surface Vehicle to link communications
No full textThis paper presents the design of Xiroi: a modular Autonomous Surface Vehicle (ASV) built to guarantee a stable and continuous Acoustic Communication Link (ACL) between an underwater vehicle and a remote computer, either located on the shore or on a support vessel. The ASV is commanded to automatically ensure a close distance for the ACL by following the submarine platform when underwater, and keeping a safety distance when it surfaces. The platform can be operated in the following ways: (i) Autonomous Underwater Vehicle (AUV) tracking, where the vehicle is required to track a moving frame (e.g. the AUV) without the need to know the actual position of the platform, (ii) path following, where the objective of the vehicle is to achieve a number of waypoints in a time window and (iii) station keeping, where the vehicle holds its GPS position regardless of the wind or water currents
Visual sensing for autonomous underwater exploration and intervention tasks
No full textUnderwater activities, such as surveying or interventions, carried out by autonomous robots, can benefit greatly from using a vision system. Optics based systems provide information at a spatial and temporal resolution higher than their acoustic counterparts. At present, they are the best option when high precision maneuvering and manipulation is needed, if there is good visibility. This paper presents a new system designed to provide visual information in submarine tasks such as navigation, surveying, mapping and intervention. The main advantages of our system, called Fugu-f (Fugu flexible), are its robustness in both the mechanical structure and the software components, its flexibility, since it is installed as an external module and is adaptable to different vehicles and missions, and its capacity to operate in real-time. Experiments of surveying and object manipulation carried out in real conditions in the context of the TRIDENT project show the suitability of the system and its scientific and industrial potential applications.</p
- …
