Publications
Underwater Visual SLAM using a Bottom-Looking Camera
Vision-based Mobile Robot Motion Control Combining T2 and ND Approaches
RANSAC based data association for underwater visual SLAM
A description of the FTT-SE protocol
The Flexible Time-Triggered (FTT) paradigm, proposed at the university of Aveiro in Portugal, makes it possible for distributed embedded systems(DES) to exchange real-time data in a flexible fashion, that is, it ensures that changes in the communication requirements...
SOAcom: Designing Service communication in adaptive automotive networks
This paper describes SOAcom, a communication model as well as a development process to characterize and adapt automotive network protocols to Service-based Driver Assistance Systems (DAS). Future DAS for articulated vehicles like a car with a caravan are characterized...
Developments in Flexible Time-Triggered Switched Ethernet
Towards Preventing Error Propagation in a Real-Time Ethernet Switch
Flexible Time-Triggered communication (FTT) allows a distributed embedded system (DES) to adapt to changing real-time requirements at runtime. This facilitates the continuous operation of the DES under dynamic environments that change over time. However, for...
Implementing a Clock Synchronization Protocol on a Multi-Master Switched Ethernet Network
The interest to use Switched Ethernet technologies in real-time communication is increasing due to its absence of collisions when transmitting messages. Nevertheless, using COTS switches affect the timeliness guarantee inherent in potentially overflowing internal FIFO...
sfiCAN: a Star-based Physical Fault-Injection Infrastructure for CAN networks
The dependability requirements of distributed embedded control systems demand appropriate evaluation techniques. Requirements of embedded systems are often tested by means of fault injection. However, for the Controller Area Network (CAN) the potential of this...
Visual Odometry Parameters Optimization for Autonomous Underwater Vehicles
Evaluation of a laser based structured light system for 3D reconstruction of underwater environments
Structure from motion or stereoscopy are used to obtain 3D from a sequence of still images. However if there is no texture or features in the images, no 3D can be obtained. Featureless environments are difficult to reconstruct in 3D only using cameras. Projected light...
Vision-Based Topological Mapping and Localization by means of Local Invariant Features and Map Refinement
An appearance-based approach for topological visual mapping and localization using local invariant features is proposed in this paper. To optimize running times, matchings between the current image and previous visited places are determined using an index based on a...
Visual Odometry for Autonomous Underwater Vehicles
Vision based motion estimation algorithms are widely used in ground-based and aerial robotics. Combined with inertial measurement units, they have proven to be a precise and low-cost sensor for velocity and pose estimation. In this paper we show that stereo vision...
Texture Analysis of Seabed Images to Quantify the Presence of Posidonia Oceanica Using Logistic Model Trees
An automatic classifier algorithm has been designed to assess the population of Posidonia Oceanica over a set of underwater images taken at Palma Bay. Laws' energy filters and statistical descriptors of the Gray Level Co-occurrence Matrix have been used to correctly...
Design and verification of a media redundancy management driver for a CAN star topology
Towards a Flexible Time-Triggered Replicated Star for Ethernet
https://www.youtube.com/watch?v=SqNCAETKYoU
Towards Dynamic Fault Tolerance on FTT-based Distributed Embedded Systems
A proposal for Flexible, Real-Time and Consistent Multicast in FTT/HaRTES Switched Ethernet
Texture Analysis of Seabed Images: Quantifying the Presence of Posidonia Oceanica at Palma Bay
An automatic classifier algorithm has been designed to assess the population of Posidonia oceanica over a set of underwater images at Palma Bay. Laws' energy filters and statistical descriptors of the Gray Level Co-occurrence Matrix have been use to correctly classify...