Salviano Soares

Automatic detection of bunches of grapes in natural environment from color images

Abstract Despite the benefits of precision agriculture and precision viticulture production systems, its rate of adoption in the Portuguese Douro Demarcated Region remains low. We believe that one way to raise it is to address challenging real-world problems whose solution offers a clear benefit to the viticulturist. For example, one of the most demanding tasks in wine making is harvesting. Even for humans, the environment makes grape detection difficult, especially when the grapes and leaves have a similar color, which is generally the case for white grapes. In this paper, we propose a system for the detection and location, in the natural environment, of bunches of grapes in color images. This system is able to distinguish between white and red grapes, and at the same time, it calculates the location of the bunch stem. The system achieved 97% and 91% correct classifications for red and white grapes, respectively.

Induction motor response to periodical voltage fluctuations

The main aim of this paper is to analyze the behavior of the three-phase squirrel cage induction motor under different voltage fluctuation levels. To achieve this goal several simulations were performed using the EMTP/ATP tool. Here we present how mechanical torque, speed and efficiency parameters varied with different levels of voltage fluctuation and modeling frequencies. As it was expected, the induction motor is sensitive to voltage fluctuations within certain amplitude levels and frequencies. Also, the speed is more affected by low frequencies and high amplitudes of voltage fluctuations, while the torque and efficiency are more affected by middle and high frequencies and amplitudes.

Coexistence and interference tests on a Bluetooth Low Energy front-end

Over the last decade, impelled by the industry demand to achieve a technology capable of sending low amount of data payloads, but at the same time with a very low latency and ultra-low power consumption, several efforts in wireless network transmission standardization emerged, supporting new applications in health, sports and fitness, medical, sensor networking, and even the automotive industry field. Despite the competition from ANT+, ZigBee, Nike+, NFC and RF4CE, in 2010 the Bluetooth SIG (special interest groups) adopted a new wireless technology named Bluetooth Low Energy (BLE). BLE coexist with Bluetooth in the same chip (called dual mode) therefore assuring this technology a rapid growth among smartphones, iOS, tablets, laptops and PCs. In fact, Bluetooth SIG also announced that it shall be hard to find a smartphone or tablet-PC that does not integrate BLE in the near future. Despite this accelerated growth, BLE shares the same band with Wi-Fi and all other low power technologies, so in order to achieve QoS, a mandatory requirement in many systems, tests for interference and coexistence must be performed. This study analysis the impact of a BLE sensor network on a crowded 2.4GHz room, with multiple Wi-Fi routers, ZigBee sensors and Bluetooth technology. We also compare the results with the ones obtained inside an anechoic chamber on similar experiences.

A Bluetooth Approach to Diabetes Sensing on Ambient Assisted Living systems

Abstract The metabolic disorder which entails the absent or reduced control of blood glucose in the body by means of insulin dependence (Type1) or intolerance (Type 2) affects more than 366 million people in 2011. This represents an increase of 28% new cases in one year. Diabetes Mellitus has become the most common chronic diseases in nearly all countries, and continues to increase in numbers and significance, as economic development and urbanization lead to changing lifestyles characterized by reduced physical activity, and increased obesity. Ambient Assisted Living (AAL), is based on a set of technologies which aims to provide an enhanced support to peoples daily life, namely the offer of new solutions for healthcare to improve the quality of life of the population and reduce costs associated with healthcare. This paper presents a Bluetooth prototype low power battery-less wireless sensor communication system capable transmitting the information to a mobile phone or wrist wireless phone. The purpose of the system is to gather routine information from the glucose monitoring system proposed by Leal, et al and interact with systems like Ambient Assisted Living from Martins, et al.

Button Heat-Pulse Sensor for Soil Water Content Measurements

Recent developed button heat pulse probes (BHPP) demonstrated a great potential for soil water content measurements. This new probe compared to conventional heat pulse probes (HPP), does not use needles, and measurement accuracy is significantly improved. This new design, with the possibility to assembly the probe and electronics in the same package, with low-cost, and with less power consumption compared to conventional HPP, make it suitable to be connected to wireless data acquisition systems in precision agriculture. The probe was tested in agar to demonstrate the potential advantages of the button heat pulse sensor for soil water content measurements. It was possible to have an 0.5 ºC temperature rise with only 156 mW of power consumption, a ten times power reduction in heat-pulse soil water content measurements. These tests showed the potential use of the button heat pulse sensor for the determination of soil water content.

Lost block reconstruction in depth maps using color image contours

This paper presents a method to recover lost blocks in depth maps affected by data loss in 3D image/video communications over error prone networks. The proposed method relies on the color image for accurate reconstruction of the lost contour segments in the corresponding depth map areas. Such reconstructed depth map contours are then used as boundaries at different depth planes to recover the missing depth values through weighted interpolation. The method performance is evaluated by the objective quality (PSNR) of the synthesised views. Images decoded with the reconstructed depth maps are compared with those of the reference method. The proposed method exhibits PSNR gains up to 1.49dB higher than the reference one, and a better performance is consistently achieved for different 3D image content.

Error recovery of image-based depth maps using Bézier curve fitting

This paper proposes a method to recover lost regions in image-based depth maps used in video plus depth 3D format. This method performs depth maps reconstruction taking into account depth contours within the lost regions. This is achieved by extracting the contours and recovering their lost segments based on Bézier curve fitting, followed by spatial interpolation. The proposed method maintains contour smoothness and uses them as the boundary limits of homogeneous depth regions, which are then filled through weighted pixel interpolation. The experimental results show that the proposed method yields better synthesized images than classic spatial concealment methods, uniquely based on pixel interpolation techniques. The method presented in this paper is able to outperform the reference method, in terms of PSNR by up to 1.91dB. The subjective quality is also shown as being significantly better.

Quality model for monitoring QoE in VoIP services

This paper presents a no-reference model for monitoring the voice quality experienced by users in VoIP services. The proposed model is based on the E-Model, which is adapted from Recommendation ITU-T G.107 for this purpose. A calibration function was determined for relevant codecs under different packet loss conditions. Extensive field testing was carried out to validate the proposed model at PT Inovação Labs (Portugal). The results show that the mean opinion score (MOS) obtained from the proposed model match class C2 of conformance tests defined in ITU-T Recommendation P.564. The QoE model described in this paper was implemented in a VoIP QoE probe and is currently fully operational at Portugal Telecom.

Spatial error concealment for intra-coded depth maps in multiview video-plus-depth

Transmission errors or packet loss in depth maps have great impact on the decoding quality and view synthesis of 3D and multiview video. Thus efficient methods to recover corrupted depth data are critical functions for accurate view rendering. This paper proposes an error concealment method for intra-coded depth maps, based on spatial intra and inter-view methods, which exploit neighbouring data of depth and colour images received error-free. A novel three-stage processing algorithm is devised to reconstruct sharp depth transitions (i.e. lost depth contours), using a disparity map and geometric interpolation based on parametric Bézier curves. The simulation results obtained from different views of various MVD sequences, for different packetisation modes and a wide range of packet loss rates (PLR), show that the proposed method consistently leads to quality improvement of synthesised images in comparison with reference methods.

Signal processing interpolation educational workbench

This article presents an educational tool to be used in signal processing interpolation‐related subjects. The aim is to contribute to the better consolidation of acquired theoretical knowledge, allowing students to test signal reconstruction algorithms and visualize the results obtained by the usage of such algorithms, and how several parameters affect their convergence and performance.