Despite the continual advances in Advanced Driver Assistance Systems (ADAS) and the development of high-level autonomous vehicles (AV), there is a consensus that for the short to medium term, there is a requirement for a human supervisor to handle the edge cases that inevitably arise. Given this requirement, the state of the autonomous vehicle operator (referred to as the safety driver) must be monitored to ensure their contribution to the vehicle's safe operation. This paper introduces a dual-source approach integrating data from an infrared camera facing the safety driver and vehicle perception systems to produce a metric for safety driver alertness to promote and ensure safe operator behaviour. The infrared camera detects the safety driver’s head, enabling the calculation of head orientation, which is relevant as the head typically moves according to the individual's focus of attention. By incorporating environmental data from the perception system, it becomes possible to determine whether the safety driver observes objects in the surroundings. Experiments were conducted using data collected in Sydney, Australia, simulating AV operations in an urban environment. Our results demonstrate that the proposed system effectively determines a metric for the attention levels of the safety driver, enabling interventions such as warnings or reducing autonomous functionality as appropriate. The results indicate reduced awareness on subsequent laps during the study, demonstrating the "automation complacency" phenomenon. This comprehensive solution shows promise in contributing to ADAS and AVs’ overall safety and efficiency in a real-world setting.

Despite the continual advances in Advanced Driver Assistance Systems (ADAS) and the development of high-level autonomous vehicles (AV), there is a general consensus that for the short to medium term, there is a requirement for a human supervisor to handle the edge cases that inevitably arise. Given this requirement, it is essential that the state of the vehicle operator is monitored to ensure they are contributing to the vehicle's safe operation. This paper introduces a dual-source approach integrating data from an infrared camera facing the vehicle operator and vehicle perception systems to produce a metric for driver alertness in order to promote and ensure safe operator behaviour. The infrared camera detects the driver's head, enabling the calculation of head orientation, which is relevant as the head typically moves according to the individual's focus of attention. By incorporating environmental data from the perception system, it becomes possible to determine whether the vehicle operator observes objects in the surroundings. Experiments were conducted using data collected in Sydney, Australia, simulating AV operations in an urban environment. Our results demonstrate that the proposed system effectively determines a metric for the attention levels of the vehicle operator, enabling interventions such as warnings or reducing autonomous functionality as appropriate. This comprehensive solution shows promise in contributing to ADAS and AVs' overall safety and efficiency in a real-world setting.

An essential task to prevent pedestrian injuries by an autonomous vehicle is the ability to correctly detect and predict its movement. A deep learning-based 2D human poses detector, as OpenPose, provides a skeleton of people present in an image captured by cameras mounted in the car. Nevertheless, these kinds of algorithms give a frame solution but do not capture the movement between them. Then, parts of the body are missed or the skeleton leaped to another part of the image where the infrastructure resembles a person. In this context, an algorithm based in the Kalman Filter algorithm to estimate the real skeleton including correlations in time and between parts of the body is presented. The algorithm was tested on videos using data provided by a vehicle moving in real scenarios. Results are presented that shown the capability of the algorithm to correct the mentioned loss of tracking.

A circularly polarised RFID tag antenna with wide axial ratio bandwidth, wide impedance bandwidth and simple tuning network is presented. The antenna, based on the widely used crossed-dipole design, incorporates a novel matching network based on two large L-shaped strips joining the arms of the dipoles to match the impedance. The L-shaped strips create large area loops enabling the antenna to be adapted to the high inductances required for good matching without the currents flowing through them degrading the axial ratio of the antenna. The gain pattern, input impedance and axial ratio (AR) are computed with numerical simulation and measurements, resulting in a 30 MHz bandwidth based on the -3 dB Axial Ratio criterion, which can provide a maximum reading distance of 12.8 m.

No English translation of this document was provided by the author or conference organizers.

This work presents a comprehensive comparison of the influence of the substrate material on the efficiency of an RF harvesting dipole antenna. A simple dipole antenna was designed as a starting model with capacitive loads on each end, in order to achieve a compact design, tuned at two high RF energy frequency bands of interest according to previous measurements. Two equivalent monopole prototypes were fabricated, one with an FR4 substrate and other with air substrate. With them, the efficiency measurements of these prototypes were carried out through the extendedWCap method for ultrawideband antennas. As it is shown, the loss in efficiency in dipole antennas having the dielectric substrate is not as important as it would be expected. On the other hand, they have assembly facilities that make them preferable.

The estimation and prediction of pedestrian motion is of fundamental importance in ITS applications. Most existing solutions have utilized a particular type of sensor for perception such as cameras (stereo, monocular, infrared) or other modalities such as a laser range finder or radar. The advent of wearable devices with inertial sensors have led to the development of systems capable of the robust inference of pedestrian intention. Unfortunately, these devices do not have communications capabilities to broadcast this information to all vehicles in proximity, and also this strategy requires functioning devices on all pedestrians to work. This paper presents a robust perception method that is able to extract dynamic pedestrian information with accuracy comparable to that of typical gyroscopes and accelerometers installed in wearable devices. Experimental results are presented to demonstrate the potential for obtaining very comprehensive dynamic information from limbs representing the skeleton of a pedestrian. This work also demonstrates the accuracy of vision based systems by comparing these results to the rotation and acceleration measured directly on the pedestrian using a wearable device. The contributions of this paper demonstrate that it is possible to significantly improve both the detection and estimation of pedestrian intention by incorporating dynamic information obtained from vision sensors.

A compact ultra-wideband (UWB) Printed Inverted-F Antenna (PIFA) is presented, compatible with Decawave's DW1000 transceiver, for usage in Real-Time Location Systems (RTLS). This fully integrated, single-chip transceiver implements ultra-wideband communications covering the frequencies from 3.244 GHz to 6.999 GHz and is compliant to the IEEE802.15.4-2011 standard. The proposed antenna consists of a multi-resonant PIFA design made of five sections with different resonance frequencies, each one with its own short-circuited stub, to provide impedance matching on the entire operating bandwidth. The presented design achieves values of S 1, 1 less than -8 dB between 3 GHz and 8 GHz; with a simple design, low cost and easy to manufacture and integrate into the application. A prototype was manufactured on FR4 with an area of 29 × 15.4 mm 2 and 1.5 mm thick, that include ground planes, required for correct operation.

Wearable devices have inertial sensors that provide useful information to estimate and predict pedestrian motion and intention, which is of fundamental importance in ITS applications. These devices are usually placed in the limbs, such as wrist, ankles and feet and they provide rotation rate and acceleration information. This information is essential for the successful development of systems capable of inferencing pedestrian intentions. Unfortunately these devices do not have the capabilities to broadcast information to all vehicles in proximity and require all pedestrian to be retrofitted with such capability. This is the fundamental reason why all existing approaches are based on sensing installed directly in the vehicles. Intelligent vehicles have different types of sensors to perceive the environment in proximity, the most common being cameras. This work demonstrates that vision from cameras is capable of obtaining pedestrian dynamics with similar accuracy of wearables devices. It compares rotation ratios and acceleration obtained with wearables installed in pedestrian wrists with similar information obtained by vision. The vision dynamic information is obtained using robust methods that combine skeleton representation with semantic information. The experimental results presented demonstrate the strong correlation between the wearable measured and vision observed rates and acceleration information. The outcomes of this work will enable the solution of one of the fundamental issues in pedestrian safety that is inference of intent.

A balun designed on laminated epoxy PCB to measure inductive ultra-high-frequency-balanced antennas is presented. Its objective is to minimise the reflection coefficient at its unbalanced input when the antenna is connected to its balanced output. This improves the accuracy in the posterior extraction of the antenna parameters from the measurement of its reflection coefficient. Theoretical considerations, design parameters and experimental results with an evaluation antenna are shown.

This work present an circularly polarized L Band antenna for terrestrial satellite observation services. The design is based on two crossed dipoles fed by a coaxial cable, and a flat reflector to improve the characteristics of the radiation pattern. The dipoles are implemented on PCB and the assembly is designed considering the weight and size constraints imposed by aerospace technology. Simulation results of the main characteristics of the antenna are shown as well as impedance and axial ratio measurements performed on a prototype built in FR4.

The agricultural industry faces the challenge of increase yield and improve the food quality. This paper presents a study on the prediction of fruit production and also intends to detect other information that can be obtained based on the scans of fruit trees using a LIDAR sensor. We worked on a Williams pear orchard using a semi-automatic procedure in order to estimates tree volume. We compute the canopy area with a simple method based on the Gauss's formula at harvest and during tree dormancy. We correlates volume vs. weight of harvested fruits from each plant. Regression coefficients were obtained for individual and grouped data. At harvest time, we obtain a good relationship between the volume of the canopy and the production (r = 67). The information obtained is very valuable in terms of the general state of the crop, the evolution and distribution of production within the orchard, and to make adequate decisions about its management.

The prediction of pedestrian movements, here referred as intention, is important to improve the autonomous vehicles' safety systems. Recognize it correctly helps to avoid traffic accidents, specially on low visibility areas, non-line-of-sight or hiding. This paper analyzes the use of movement information provided by an accelerometer carried by pedestrians. With real data extracted from a real experiment, It is proved that the use of simple classifiers can detect the crossing -or not-crossing intention over a street, before the pedestrian does action.

Innovation in intelligent transportation systems relies on analysis of high-quality data. In this paper, we describe the design principles behind our data management infrastructure. The principles we adopt place an emphasis on flexibility and maintainability. This is achieved by breaking up code into a modular design that can be run on many independent processes. Message passing over a publish-subscribe network enables interprocess communication and promotes data-driven execution. By following these principles, rapid prototyping and experimentation with new sensing modalities and algorithms are possible. The communication library underpinning our proposed architecture is compared against several popular communication libraries. Features designed into the system make it decentralized, robust to failure, and amenable to scaling across multiple machines with minimal configuration. Code written using the proposed architecture is compact, transparent, and easy to maintain. Experimentation shows that our proposed architecture offers a high performance when compared against alternative communication libraries.

The use of simulators on Intelligent Transportation Systems allows to recreate transit situations from real data; evaluation of algorithms without put at risk the people and assets; and analyze driver behavior on controlled experimental situations. This work shows the development of a simulator from a virtualized environment, using strategies of image processing, and a game engine which offer support and functionalities needed to the simulation. Results with experimental data in normal traffic situations that shows the operation on real time, are also presented.

In this paper we present a vanishing point algorithm variation oriented to a VLSI ASIC. We proposed a simplified voting process and analyze the minimum resolution that can be used for the input image and the filter kernels in order to obtain a good performance.

A key aspect to improve the operating range in the manufacture of tags for UHF RFID systems is to achieve an effective adaptation between the impedance of antenna and chip. Due to the characteristics of the communication between reader and tag, UHF RFID integrated circuits present two operational states which have different impedances. Integrated circuits manufacturers only publish data about one of the states, namely the absorbing state. This paper introduces a procedure to characterize chip impedance thoroughly in both operational states and describes experimental results of Alien Higgs 4 commercial chip.

Advanced Driver Assistance Systems (ADAS) are a result of many years of research with the main motivation of reducing the amount and the severity of traffic accidents. The use of cameras is now crucial for many of these systems, such as Lane Departure Warning Systems (LDWS). This paper proposes a method to estimate in advance the change of curvature of a road through vanishing points computed from the orientation of the texture in different regions of the image. This information can be used to aid drivers and control the vehicle speed in curves. The validity of the results is demonstrated experimentally using real public data in adverse lighting conditions.

Particle Filter is an algorithm that provides system state estimation even for non-linear and non-gaussian systems. For applications that require a large number of particles, real time constraint is hard to accomplish since the algorithm is computationally expensive and the resampling step becomes a bottleneck. In this work, a VLSI architecture for particle filtering in real time is presented. The proposed design implements a fraction of the processing using piecewise linear functions and allocates them as global resources. In this way, a large number of processing elements (PE) working in parallel can be instantiated in the design. An example based on a range-only localization using Radio-Frequency identification (RFID) tags is developed to illustrate the approach. The received signal strength indicator (RSSI) is used to estimate the distance between transmitter and receiver. A VHDL RTL model of the processing data flow is implemented and compared to Matlab simulations showing similar results.