Global localization with non-quantized local image features

In the field of appearance-based robot localization, the mainstream approach uses a quantized representation of local image features. An alternative strategy is the exploitation of raw feature descriptors, thus avoiding approximations due to quantization. In this work, the quantized and non-quantized representations are compared with respect to their discriminativity, in the context of the robot global localization problem. Having demonstrated the advantages of the non-quantized representation, the paper proposes mechanisms to reduce the computational burden this approach would carry, when applied in its simplest form. This reduction is achieved through a hierarchical strategy which gradually discards candidate locations and by exploring two simplifying assumptions about the training data. The potential of the non-quantized representation is exploited by resorting to the entropy-discriminativity relation. The idea behind this approach is that the non-quantized representation facilitates the assessment of the distinctiveness of features, through the entropy measure. Building on this finding, the robustness of the localization system is enhanced by modulating the importance of features according to the entropy measure. Experimental results support the effectiveness of this approach, as well as the validity of the proposed computation reduction methods.

Pentagonal parch-excited sectorized antenna for localization systems

A pentagonal patch-excited sectorized antenna (SA) suitable for 2.4-2.5 GHz localization systems was studied and developed. The integration of six patch-excited structures converges into a sectorized antenna called Hive5 that provides gain improvement compared to a patch antenna, maximum variation of 3 dB beam width over the radiation pattern and circular polarization (CP). This antenna is presented and analyzed taking into account the tap length and the flare angle. The proposed antenna in combination with a RF-Switch provides a cost effective solution for localization based on Wireless Sensor Networks (WSN) and will be used for implementing angle of arrival (AoA) techniques combined with RF fingerprinting techniques.

Detection of classic and invasive E. coli and Shigella serotypes in stools by indirect immunofluorescence

IIF in the detection of invasive and classic enteropathogenic E. coli and Shigella serotypes was compared with traditional coproculture methods. IIP results agreed with the coproculture findings in 128 out of 140 cases tested for enteropathogenic E. coli (91%) and in 108 out of 112 for Shigella (96%). All cases with positive reactions by coproculture were confirmed by IIP. In the control group it were obtained by IIF 12 cases with positive reactions for enteropathogenic E. coli and 4 cases for Shigella, including two cases of mixed infection by E. coli 026/Sh. dysenteriae and E. coli 0124/Sh. dysenteriae. It was discussed the high sensitivity and specificity of the IIF when compared with the traditional methods, being suggested that IIF is a valuable tool in epidemiological studies involving these organisms and an important aid in the stablishment of an early presumptive diagnosis of the acute infantile diarrhea.

Lectins for the detection of IgM antibodies to T. gondii in the diagnosis of acute toxoplasmosis by immunofluorescence test

Lectins were labeled with fluorescein and tried as conjugates in the immunofluorescence (IP) test for the detection of IgM antibodies to T. gondii, in the diagnosis of acute toxoplasmosis. This approach was an attempt to find alternative reagents for anti-human IgM fluorescent conjugates (AHIgMFC), which contain quite frequently anaibcdies to toxoplasma, as contaminants, due to natural T. gondii infections among animals used for imunization. Lentil (Lens culinaris) lectin fluorescence conjugates (LcFC) provided most satisfactory results. The evaluation of LcFC carried out in a total of 179 sera from patients with acute and chronic toxoplasmosis, with non-related infections or healthy subjects, gave high values of relative efficiency, co-positivity and co-negativity indices, respectively 0.989, 0.969 and 1.000, in reference to the conventional AHIgMFC. Moreover, three batches of LcFC successively prepared gave reproducible test results. The advantage of LcFC as an alternative reagent for the serodiagnosis of acute toxoplasmosis is supported by practical aspects of its preparation.

Comparison of indirect immunofluorescence test for measles antibodies with haemagglutination inhibition and plaque neutralization tests

Indirect Immunofluorescence (IFA), Plaque Reduction Neutralization (PRN) and Haemagglutination Inhibition (HI) tests for measles antibodies were carried out in 197 sera obtained from umbilical cord and vaccinated children. The IFA was also applied to blood samples collected with filter paper. IFA results demonstrated that the test is relatively simple to perform, with good reproducibility for different antigen lots. Good correlation was obtained between IFA, PRN and HI antibody titers. Better correlation was demonstrated with IFA and PRN than with HI and PRN tests. Sensitivity of IFA in detecting antibody was less effective than PRN, however more effective than HI using rhesus monkey red blood cells. PRN antibody titers over 100 were detected by IFA but not by HI (9.7% with negative results). IFA may be of considerable practical use and able to substitute HI in Seroepidemiological surveys and to evaluate vaccine efficacy. It also can be simplified by employing filter paper collected samples.

Enzyme-linked immunosorbent assay (ELISA) for measles antibody: a comparison with haemagglutination inhibition, immunofluorescence and plaque neutralization tests

An enzyme-linked immunosorbent assay (ELISA) for measles antibodies was compared with Plaque Neutralization (PRN), Haemagglutination inhibition (HI) and Fluorescent antibody (IFA) tests in 181 sera from vaccinated children and umbilical cord. Of 179 positive samples by the sensitive PRN, only two, with titers of 8, were negative by ELISA (copositivity of 98.9%). IFA and HI presented, respectively, copo-sitivities of 93.3% and 82.7%. The ELISA presented a high sensitivity as well as a good reproducibility and represents an alternative for the time consuming PRN for detection of low measles antibodies.

Comparison on the performance of Leishmania major-like and Leishmania braziliensis braziliensis as antigen for new world leishmaniasis IgG-immunofluorescence test

The performance of an antigen of L. major-like promastigotes for the serological diagnosis of mucocutaneous leishmaniasis in the IgG-immunofluorescent test was compared to that of an antigen of L. braziliensis braziliensis. Each antigen was used to test two hundred and twenty-four sera of etiologies such as mucocutaneous leishmaniasis, deep mycoses, toxoplasmosis, malaria, Chagas' disease, visceral leishmaniasis, anti-nuclear factor, schistosomaiasis, rheumatoid factor and normal controls. Agreement between responses to each antigen was high: 77.2% of leishmaniases sera agreed on a positive or a negative result to both antigens and 91.1 % of control sera. Cross reactivity was restricted to Chagas' disease sera, visceral leishmaniasis, anti-nuclear factor and paracoccidiodomycosis. The quantitative response of leishmaniasis and Chagas' disease sera to both antigens was evaluated by a linear regression; although the y-intercept and the slope were different for each antigen, neither was better than the other in the disclosure of anti-Leishmania antibodies. In the case of Chagas' disease sera the L. major-like antigen was better than L. b. braziliensis' to disclose cross-reacting antibodies.

Enhanced PCA-based localization using depth maps with missing data

In this paper a new method for self-localization of mobile robots, based on a PCA positioning sensor to operate in unstructured environments, is proposed and experimentally validated. The proposed PCA extension is able to perform the eigenvectors computation from a set of signals corrupted by missing data. The sensor package considered in this work contains a 2D depth sensor pointed upwards to the ceiling, providing depth images with missing data. The positioning sensor obtained is then integrated in a Linear Parameter Varying mobile robot model to obtain a self-localization system, based on linear Kalman filters, with globally stable position error estimates. A study consisting in adding synthetic random corrupted data to the captured depth images revealed that this extended PCA technique is able to reconstruct the signals, with improved accuracy. The self-localization system obtained is assessed in unstructured environments and the methodologies are validated even in the case of varying illumination conditions.

Comparative study on the localization of adult Schistosoma mansoni worms in albino mice anesthetized with pentobarbital sodium, ether or chlorophorm

The effect of anesthetic drugs on the localization of adult worms in albino mice was compared. The animals with 56 days of infection were anesthetized with pentobarbital sodium, ether or chlorophorm. Perfusion was carried out immediately after, recovering the worms and classifying them in relation to their localization on the liver or portal vein and the mesenteric veins. Our results showed that pentobarbital sodium produced a greater displacement of the worms to the liver (89%) than ether (76%) and chlorophorm (34%) did, when compared to the control group (22%). The difference between pentobarbital sodium and ether was significant (p < 0.05). We suggest that anesthetic drugs may not be used in studies on the distribution of adult worms in several hosts.

Robot visual localization through local feature fusion: an evaluation of multiple classifiers combination approaches

In the last decade, local image features have been widely used in robot visual localization. In order to assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image with those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, in this paper we compare several candidate combiners with respect to their performance in the visual localization task. For this evaluation, we selected the most popular methods in the class of non-trained combiners, namely the sum rule and product rule. A deeper insight into the potential of these combiners is provided through a discriminativity analysis involving the algebraic rules and two extensions of these methods: the threshold, as well as the weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. Furthermore, we address the process of constructing a model of the environment by describing how the model granularity impacts upon performance. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance, confirming the general agreement on the robustness of this rule in other classification problems. The voting method, whilst competitive with the product rule in its standard form, is shown to be outperformed by its modified versions.

Geo-localization System for People with Cognitive Disabilities

Technology is present in almost every simple aspect of the people’s daily life. As an instance, let us refer to the smartphone. This device is usually equipped with a GPS modulewhich may be used as an orientation system, if it carries the right functionalities. The problem is that these applications may be complex to operate and may not be within the bounds of everybody. Therefore, the main goal here is to develop an orientation system that may help people with cognitive disabilities in their day-to-day journeys, when the caregivers are absent. On the other hand, to keep paid helpers aware of the current location of the disable people, it will be also considered a localization system. Knowing their current locations, caregiversmay engage in others activities without neglecting their prime work, and, at the same time, turning people with cognitive disabilities more independent.

Step count algorithm adapted to indoor localization

This paper presents a step count algorithm designed to work in real-time using low computational power. This proposal is our first step for the development of an indoor navigation system, based on Pedestrian Dead Reckoning (PDR). We present two approaches to solve this problem and compare them based in their error on step counting, as well as, the capability of their use in a real time system.

Traveled Distance Estimation Algorithm for Indoor Localization

This paper presents an ankle mounted Inertial Navigation System (INS) used to estimate the distance traveled by a pedestrian. This distance is estimated by the number of steps given by the user. The proposed method is based on force sensors to enhance the results obtained from an INS. Experimental results have shown that, depending on the step frequency, the traveled distance error varies between 2.7% and 5.6%.

Person Localization Using Sensor Information Fusion

Nowadays the incredible grow of mobile devices market led to the need for location-aware applications. However, sometimes person location is difficult to obtain, since most of these devices only have a GPS (Global Positioning System) chip to retrieve location. In order to suppress this limitation and to provide location everywhere (even where a structured environment doesn’t exist) a wearable inertial navigation system is proposed, which is a convenient way to track people in situations where other localization systems fail. The system combines pedestrian dead reckoning with GPS, using widely available, low-cost and low-power hardware components. The system innovation is the information fusion and the use of probabilistic methods to learn persons gait behavior to correct, in real-time, the drift errors given by the sensors.

Localization system for pedestrians based on sensor and information fusion

Nowadays there is an increase of location-aware mobile applications. However, these applications only retrieve location with a mobile device's GPS chip. This means that in indoor or in more dense environments these applications don't work properly. To provide location information everywhere a pedestrian Inertial Navigation System (INS) is typically used, but these systems can have a large estimation error since, in order to turn the system wearable, they use low-cost and low-power sensors. In this work a pedestrian INS is proposed, where force sensors were included to combine with the accelerometer data in order to have a better detection of the stance phase of the human gait cycle, which leads to improvements in location estimation. Besides sensor fusion an information fusion architecture is proposed, based on the information from GPS and several inertial units placed on the pedestrian body, that will be used to learn the pedestrian gait behavior to correct, in real-time, the inertial sensors errors, thus improving location estimation.