Cookies
Usamos cookies para melhorar nosso site e a sua experiência. Ao continuar a navegar no site, você aceita a nossa política de cookies. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por Carlos Almeida

2016

Air and underwater survey of water enclosed spaces for VAMOS! Project

Autores
Almeida, J; Ferreira, A; Matias, B; Dias, A; Martins, A; Silva, F; Oliveira, J; Sousa, P; Moreira, M; Miranda, T; Almeida, C; Silva, E;

Publicação
OCEANS 2016 MTS/IEEE Monterey, OCE 2016

Abstract
This paper addresses a three-dimensional (3D) reconstruction of a flooded open pit mine with an autonomous surface vehicle (ASV) and unmanned aerial vehicle (UAV). The ROAZ USV and the Otus UAV were used to provide the underwater bathymetric map and aerial 3D reconstruction based from image data. This work was performed within the context of the European research project VAMOS with the objective of developing robotic tools for efficient underwater mining © 2016 IEEE.

2016

UAV trials for multi-spectral imaging target detection and recognition in maritime environment

Autores
Silva, H; Almeida, JM; Lopes, F; Ribeiro, JP; Freitas, S; Amaral, G; Almeida, C; Martins, A; Silva, E;

Publicação
OCEANS 2016 MTS/IEEE Monterey, OCE 2016

Abstract
This paper addresses the use of heterogeneous sensors for target detection and recognition in maritime environment. An Unmanned Aerial Vehicle payload was assembled using hyperspectral, infrared, electro-optical, AIS and INS information to collect synchronized sensor data with vessel ground-truth position for conducting air and sea trials. The data collected is used to develop automated robust methods for detect and recognize vessels based on their exogenous physical characteristics and their behaviour across time. Data Processing preliminary results are also presented. © 2016 IEEE.

2017

Simulation environment for underground flooded mines robotic exploration

Autores
Pereira, R; Rodrigues, J; Martins, A; Dias, A; Almeida, J; Almeida, C; Silva, E;

Publicação
2017 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2017

Abstract
This paper presents the work performed in the implementation of an underwater simulation environment for the development of an autonomous underwater vehicle for the exploration of flooded underground tunnels. In particular, the implementation of a laser based structured light system, multibeam sonar and other robot details were addressed. The simulation was used as a relevant tool in order to study and specify the robot multiple sensors characteristics and placement in order to adequately survey a realistic environment. A detailed description of the research and development work is presented along with the analysis of obtained results and the benefits this work brings to the project. © 2017 IEEE.

2017

STRONGMAR Summer School 2016 — Joining theory with a practical application in Underwater Archeology

Autores
Marques, MM; Salgado, A; Lobo, V; Carapau, RS; Rodrigues, AV; Carreras, M; Roca, J; Palomeras, N; Hurtos, N; Candela, C; Martins, A; Matos, A; Ferreira, B; Almeida, C; de Sa, FA; Almeida, JM; Silva, E;

Publicação
OCEANS 2017 - Aberdeen

Abstract

2017

UAV cooperative perception for target detection and tracking in maritime environment

Autores
Amaral, G; Silva, H; Lopes, F; Ribeiro, JP; Freitas, S; Almeida, C; Martins, A; Almeida, J; Silva, E;

Publicação
OCEANS 2017 - Aberdeen

Abstract

2018

Supervised classification for hyperspectral imaging in UAV maritime target detection

Autores
Freitas, S; Almeida, C; Silva, H; Almeida, J; Silva, E;

Publicação
18th IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2018

Abstract
This paper addresses the use of a hyperspectral image system to detect vessels in maritime operational scenarios. The developed hyperspectral imaging classification methods are based on supervised approaches and allow to detect the presence of vessels using real hyperspectral data. We implemented two different methods for comparison purposes: SVM and SAM. The SVM method, which can be considered one of most utilized methods for image classification, was implemented using linear, RBF, sigmoid and polynomial kernels with PCA for dimensionality reduction, and compared with SAM using a two classes definition, namely vessel and water. The obtained results using real data collected from a UAV allow to conclude that the SVM approach is suitable for detecting the vessel presence in the water with a precision and recall rates favorable when compared to SAM. © 2018 IEEE.

  • 1
  • 2