Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

Publications by Alfredo Martins

2016

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

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

Publication
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.

2015

Calibration Method for Underwater Visual Ground-Truth System

Authors
Faria, A; Almeida, J; Dias, A; Martins, A; Silva, E;

Publication
OCEANS 2015 - GENOVA

Abstract
This work presents an automatic calibration method for a vision based external underwater ground-truth positioning system. These systems are a relevant tool in benchmarking and assessing the quality of research in underwater robotics applications. A stereo vision system can in suitable environments such as test tanks or in clear water conditions provide accurate position with low cost and flexible operation. In this work we present a two step extrinsic camera parameter calibration procedure in order to reduce the setup time and provide accurate results. The proposed method uses a planar homography decomposition in order to determine the relative camera poses and the determination of vanishing points of detected lines in the image to obtain the global pose of the stereo rig in the reference frame. This method was applied to our external vision based ground-truth at the INESC TEC/Robotics test tank. Results are presented in comparison with an precise calibration performed using points obtained from an accurate 3D LIDAR modelling of the environment.

2015

High-Accuracy Low-Cost RTK-GPS for an Unmannned Surface Vehicle

Authors
Matias, B; Oliveira, H; Almeida, J; Dias, A; Ferreira, H; Martins, A; Silva, E;

Publication
OCEANS 2015 - GENOVA

Abstract
This work presents a low cost RTK-GPS system for localization of unmanned surface vehicles. The system is based on the use of standard low cost L1 band receivers and in the RTKlib open source software library. Mission scenarios with multiple robotic vehicles are addressed as the ones envisioned in the ICARUS search and rescue case where the possibility of having a moving RTK base on a large USV and multiple smaller vehicles acting as rovers in a local communication network allows for local relative localization with high quality. The approach is validated in operational conditions with results presented for moving base scenario. The system was implemented in the SWIFT USV with the ROAZ autonomous surface vehicle acting as a moving base. This setup allows for the performing of a missions in a wider range of environments and applications such as precise 3D environment modeling in contained areas and multiple robot operations.

2016

ISEP/INESC TEC Aerial Robotics Team for Search and Rescue Operations at the EuRathlon Challenge 2015

Authors
Sousa, P; Ferreira, A; Moreira, M; Santos, T; Martins, A; Dias, A; Almeida, J; Silva, E;

Publication
2016 IEEE INTERNATIONAL CONFERENCE ON AUTONOMOUS ROBOT SYSTEMS AND COMPETITIONS (ICARSC 2016)

Abstract
This paper presents the autononomous aerial vehicle OTUS and its application to search and rescue scenarios, namely the participation on the EuRathlon 2015 competition. The OTUS robot was developed at INESC TEC/ ISEP for research in cooperative aerial robotics and applications in complex and dynamic environments. The system was validated in this challenging scenario and was able to win the Grand Challenge scenario in cooperation with a land and marine robotics partner teams.

2016

MarinEye - A tool for marine monitoring

Authors
Martins, A; Dias, A; Silva, E; Ferreira, H; Dias, I; Almeida, JM; Torgo, L; Goncalves, M; Guedes, M; Dias, N; Jorge, P; Mucha, AP; Magalhaes, C; Carvalho, MDF; Ribeiro, H; Almeida, CMR; Azevedo, I; Ramos, S; Borges, T; Leandro, SM; Maranhao, P; Mouga, T; Gamboa, R; Lemos, M; dos Santos, A; Silva, A; Frazao e Teixeira, BFE; Bartilotti, C; Marques, R; Cotrim, S;

Publication
OCEANS 2016 - SHANGHAI

Abstract
This work presents an autonomous system for marine integrated physical-chemical and biological monitoring - the MarinEye system. It comprises a set of sensors providing diverse and relevant information for oceanic environment characterization and marine biology studies. It is constituted by a physical-chemical water properties sensor suite, a water filtration and sampling system for DNA collection, a plankton imaging system and biomass assessment acoustic system. The MarinEye system has onboard computational and logging capabilities allowing it either for autonomous operation or for integration in other marine observing systems (such as Observatories or robotic vehicles. It was designed in order to collect integrated multi-trophic monitoring data. The validation in operational environment on 3 marine observatories: RAIA, BerlengasWatch and Cascais on the coast of Portugal is also discussed.

2016

Motion Descriptor for Human Gesture Recognition in Low Resolution Images

Authors
Ferreira, A; Silva, G; Dias, A; Martins, A; Campilho, A;

Publication
ROBOT 2015: SECOND IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 1

Abstract
A great variety of human gesture recognition methods exist in the literature, yet there is still a lack of solutions to encompass some of the challenges imposed by real life scenarios. In this document, a gesture recognition for robotic search and rescue missions in the high seas is presented. Themethod aims to identify shipwrecked people by recognizing the hand waving gesture sign. We introduce a novelmotion descriptor, through which high recognition accuracy can be achieved even for low resolution images. The method can be simultaneously applied to rigid object characterization, hence object and gesture recognition can be performed simultaneously. The descriptor has a simple implementation and is invariant to scale and gesture speed. Tests, preformed on a maritime dataset of thermal images, proved the descriptor ability to reach a meaningful representation for very low resolution objects. Recognition rates with 96.3% of accuracy were achieved.

  • 1
  • 10