Real-Time 3D Object Detection and SLAM Fusion in a Low-Cost LiDAR Test Vehicle Setup.

Recently released research about deep learning applications related to perception for autonomous driving focuses heavily on the usage of LiDAR point cloud data as input for the neural networks, highlighting the importance of LiDAR technology in the field of Autonomous Driving (AD). In this sense, a great percentage of the vehicle platforms used to create the datasets released for the development of these neural networks, as well as some AD commercial solutions available on the market, heavily invest in an array of sensors, including a large number of sensors as well as several sensor modalities. However, these costs create a barrier to entry for low-cost solutions for the performance of critical perception tasks such as Object Detection and SLAM.

Resource-Constrained Onboard Inference of 3D Object Detection and Localisation in Point Clouds Targeting Self-Driving Applications.

Research about deep learning applied in object detection tasks in LiDAR data has been massively widespread in recent years, achieving notable developments, namely in improving precision and inference speed performances. These improvements have been facilitated by powerful GPU servers, taking advantage of their capacity to train the networks in reasonable periods and their parallel architecture that allows for high performance and real-time inference. However, these features are limited in autonomous driving due to space, power capacity, and inference time constraints, and onboard devices are not as powerful as their counterparts used for training.

Monitoring Walker Assistive Devices: A Novel Approach Based on Load Cells and Optical Distance Measurements.

This paper presents a measurement system intended to monitor the usage of walker assistive devices. The goal is to guide the user in the correct use of the device in order to prevent risky situations and maximize comfort. Two risk indicators are defined: one related to force unbalance and the other related to motor incoordination.

Wearable sensor network to study laterality of brain functions.

In the last decade researches on laterality of brain functions have been reinvigorated. New models of lateralization of brain functions were proposed and new methods for understanding mechanisms of asymmetry between right and left brain functions were described. We design a system to study laterality of motor and autonomic nervous system based on wearable sensors network.

Intelligent composting assisted by a wireless sensing network.

Monitoring of the moisture and temperature of composting process is a key factor to obtain a quality product beyond the quality of raw materials. Current methodologies for monitoring these two parameters are time consuming for workers, sometimes not sufficiently reliable to help decision-making and thus are ignored in some cases. This article describes an advance on monitoring of composting process through a Wireless Sensor Network (WSN) that allows measurement of temperature and moisture in real time in multiple points of the composting material, the Compo-ball system.

Comparative analysis of two systems for unobtrusive heart signal acquisition and characterization.

In this paper we describe and compared method of heart rate estimation from cardiac signal acquired with EMFIT, FMCW Doppler radar and Finapres based technology, in the same context, and briefly investigated their similarities and differences. Study of processing of acquired cardiac signal for accurate peak detection using Wavelet Transform is also described. The results suggest good reliability of the two implemented unobtrusive systems for heart rate estimation.

New insight into arrhythmia onset using HRV and BPV analysis.

In this paper Heart Rate Variability (HRV) and Blood Pressure Variability (BPV) were analyzed before the onset of cardiac arrhythmia in order to derive markers for short-term forecasting. The (a) coherence between systolic blood pressure (SBP) and cardiac oscillations in low-frequency (LF) and high-frequency (HF) band; (b) fluctuations of phase; (c) HRV and BPV as a LF power and HF power in frequency and time-frequency domain; (d) transfer function analysis of cardiovascular signals were analyzed. Arrhythmia was preceded by: a) lower coherence; b) increase in fluctuations of phase between signals; c) higher spectral energy associated with respiratory frequency in blood pressure signal; d) raise of sympathetic outflow to the heart; e) decreased HRV.

Cardio-respiratory and daily activity monitor based on FMCW Doppler radar embedded in a wheelchair.

Unobtrusive monitoring of the cardio-respiratory and daily activity for wheelchair users became nowadays an important challenge, considering population aging phenomena and the increasing of the elderly with chronic diseases that affect their motion capabilities. This work reports the utilization of FMCW (frequency modulated continuous wave) Doppler radar sensors embedded in a manual wheelchair to measure the cardiac and respiratory activities and the physical activity of the wheelchair user. Another radar sensor is included in the system in order to quantify the motor activity through the wheelchair traveled distance, when the user performs the manual operation of the wheelchair.

Online heart rate estimation in unstable ballistocardiographic records.

When recording the pressure oscillations of a seated subject two distinct effects are assessed, ample vibrations due to the person's movement, and periodic oscillations of small amplitude due to cardiopulmonary activity, expressed by the ballistocardiogram (BCG). Embedding a pressure sensor in a chair's back or seat allows unobtrusive monitoring of the BCG. However, inconspicuously acquired signals are affected by numerous artifacts, often generated by the subject's forgetfulness, and posture changes due to lack of constrains.

Automatic wavelet detrending benefits to the analysis of cardiac signals acquired in a moving wheelchair.

Biomedical signals are customarily overlaid with interferences and noise, furthermore, baseline wandering is another significant drawback to their accurate interpretation, especially if the implementation platform is a wheelchair. The nonlinear processes which generate the physiologic signals, and the disturbances, regularly exclude, or limit, the usage of classical linear techniques, hence, among other options, wavelets have been used to decompose the signals. Unobtrusively acquired signals are prone to have important baseline fluctuations, namely contactless impedance plethysmogram, and ballistocardiogram, therefore making them apposite to detrending.

Theory and developments in an unobtrusive cardiovascular system representation: ballistocardiography.

Due to recent technological improvements, namely in the field of piezoelectric sensors, ballistocardiography - an almost forgotten physiological measurement - is now being object of a renewed scientific interest.Transcending the initial purposes of its development, ballistocardiography has revealed itself to be a useful informative signal about the cardiovascular system status, since it is a non-intrusive technique which is able to assess the body's vibrations due to its cardiac, and respiratory physiological signatures.Apart from representing the outcome of the electrical stimulus to the myocardium - which may be obtained by electrocardiography - the ballistocardiograph has additional advantages, as it can be embedded in objects of common use, such as a bed or a chair.