João Marcos

Robust segmentation for outdoor traffic surveillance

In this paper it is presented a robust segmentation process for detecting incidents on highways. This segmentation process is based on background subtraction and uses an efficient background model initialization and update to work 24/7. A cross- correlation based shadow detection is also used for minimizing ghosts. It is also proposed a stopped vehicle detection system based on the pixel history cache. This method has proved to be quite robust in terms of different weather conditions, lighting and image quality. Some experiments carried out on some highway scenarios demonstrate the robustness of the proposed solution.

Wrongway Drivers Detection Based on Optical Flow

In this paper it is described a solution to detect wrong way drivers on highways. The proposed solution is based on three main stages: learning, detection and validation. In the first stage, the orientation pattern of vehicles motion flow is learned and modelled by a mixture of Gaussians. The second stage (detection and temporal validation) makes use of the learned orientation model to detect objects moving on lanes opposite direction. The third and final stage uses an appearance based approach to ensure the detection of a vehicle before triggering an alarm. This methodology has proven to be quite robust in terms of different weather conditions, illumination and image quality. Some experiments carried out with several movies from traffic surveillance cameras on highways show the robustness of the proposed solution.

Negative refraction and partial focusing with a crossed wire mesh: Physical insights and experimental verification

We experimentally verify that a flat metamaterial lens formed by nonconnected crossed metallic wires enables the partial focusing of electromagnetic waves, as a consequence of the phenomenon of all-angle broadband negative refraction in such media. We prove that the strength of the negative refraction effect can be controlled by adjusting the angle between the crossed wires.

Spatially Confined UHF RFID Detection With a Metamaterial Grid

The confinement of the detection region is one of the most challenging issues in Ultra-High Frequency (UHF) Radio Frequency Identification (RFID) systems. Here, we propose a new paradigm to confine the interrogation zone of standard UHF RFID systems. Our approach relies on the use of an all-planar metamaterial wire grid to block the radiation field (i.e., the far-field) of the reader antenna, and thereby obtain a spatially well-confined detection region in the near-field. This solution is analytically and numerically investigated, and then experimentally verified through near-field and tag-reading measurements, demonstrating its effectiveness and robustness under external perturbations.

Reversed rainbow with a nonlocal metamaterial

One of the intriguing potentials of metamaterials is the possibility to realize a nonlocal electromagnetic reaction, such that the effective medium response at a given point is fundamentally entangled with the macroscopic field distribution at long distances. Here, it is experimentally and numerically verified that a microwave nonlocal metamaterial formed by crossed metallic wires enables a low-loss broadband anomalous material response such that the refractive index decreases with frequency. Notably, it is shown that an electromagnetic beam refracted by our metamaterial prism creates a reversed microwave rainbow.

Robust Segmentation Process to Detect Incidents on Highways

In this paper a robust segmentation process for detecting incidents on highways is presented. This segmentation process is based on background subtraction and uses an efficient background model initialisation and update to work 24/7. A cross-correlation based shadow detection is also used for minimising ghosts. It is also proposed a stopped vehicle detection system based on the pixel history cache. This methodology has proved to be quite robust in terms of different weather conditions, lighting and image quality. Some experiments carried out on some highway scenarios demonstrate the robustness of the proposed solution.

A framework for wrong way driver detection using optical flow

In this paper a solution to detect wrong way drivers on highways is presented. The proposed solution is based on three main stages: Learning, Detection and Validation. Firstly, the orientation pattern of vehicles motion flow is learned and modelled by a mixture of gaussians. The second stage (Detection and Temporal Validation) applies the learned orientation model in order to detect objects moving in the lanes opposite direction. The third and final stage uses an Appearance-based approach to ensure the detection of a vehicle before triggering an alarm. This methodology has proven to be quite robust in terms of different weather conditions, illumination and image quality. Some experiments carried out with several movies from traffic surveillance cameras on highways show the robustness of the proposed solution.

Measurement of the Specific Absorption Rate using a single electric field sensor

The Specific Absorption Rate (SAR) is usually measured using electric field probes based on dipole antennas, loaded with radio frequency (RF) detector diodes and connected to differential amplifiers through high-impedance transmission lines. The most common configuration consists of three mutually orthogonal electric short dipole antennas, loaded with a fast switching detector, providing broadband characteristics. In this work, we describe the measurement of the SAR with a sensor based on a single dipole antenna. It is shown that this reduces the complexity of the system without compromising the accuracy and frequency response. The probe is tested by measuring the SAR for a dual-band Planar Inverted-F antenna.