944 resultados para 3D object detection
Resumo:
Target tracking with bearing-only sensors is a challenging problem when the target moves dynamically in complex scenarios. Besides the partial observability of such sensors, they have limited field of views, occlusions can occur, etc. In those cases, cooperative approaches with multiple tracking robots are interesting, but the different sources of uncertain information need to be considered appropriately in order to achieve better estimates. Even though there exist probabilistic filters that can estimate the position of a target dealing with incertainties, bearing-only measurements bring usually additional problems with initialization and data association. In this paper, we propose a multi-robot triangulation method with a dynamic baseline that can triangulate bearing-only measurements in a probabilistic manner to produce 3D observations. This method is combined with a decentralized stochastic filter and used to tackle those initialization and data association issues. The approach is validated with simulations and field experiments where a team of aerial and ground robots with cameras track a dynamic target.
Resumo:
The underground scenarios are one of the most challenging environments for accurate and precise 3d mapping where hostile conditions like absence of Global Positioning Systems, extreme lighting variations and geometrically smooth surfaces may be expected. So far, the state-of-the-art methods in underground modelling remain restricted to environments in which pronounced geometric features are abundant. This limitation is a consequence of the scan matching algorithms used to solve the localization and registration problems. This paper contributes to the expansion of the modelling capabilities to structures characterized by uniform geometry and smooth surfaces, as is the case of road and train tunnels. To achieve that, we combine some state of the art techniques from mobile robotics, and propose a method for 6DOF platform positioning in such scenarios, that is latter used for the environment modelling. A visual monocular Simultaneous Localization and Mapping (MonoSLAM) approach based on the Extended Kalman Filter (EKF), complemented by the introduction of inertial measurements in the prediction step, allows our system to localize himself over long distances, using exclusively sensors carried on board a mobile platform. By feeding the Extended Kalman Filter with inertial data we were able to overcome the major problem related with MonoSLAM implementations, known as scale factor ambiguity. Despite extreme lighting variations, reliable visual features were extracted through the SIFT algorithm, and inserted directly in the EKF mechanism according to the Inverse Depth Parametrization. Through the 1-Point RANSAC (Random Sample Consensus) wrong frame-to-frame feature matches were rejected. The developed method was tested based on a dataset acquired inside a road tunnel and the navigation results compared with a ground truth obtained by post-processing a high grade Inertial Navigation System and L1/L2 RTK-GPS measurements acquired outside the tunnel. Results from the localization strategy are presented and analyzed.
Resumo:
The protozoan Cryptosporidium sp. has been frequently detected in faeces from children with persistent diarrhoea. This work achieved to investigate an outbreak of cryptosporidiosis, in a day care center, attending children of high socio-economic level, between 0 and six years old. The outbreak was detected through the network of public health, when stool samples, not diarrhoeic, were examined at the Parasitology Service of the Adolfo Lutz Institute. Among the 64 examined children, 13 (20.3%) showed oocysts of Cryptosporidium sp. in the faeces examined by Kinyoun technique: seven children one year old, three, two years old and three, three years old. Among the 23 examined adults, only a 22 years old woman, possibly having an immunocomprometiment, was positive. Clinical and epidemiological aspects were investigated by questionnaires, highlighting the occurrence of the outbreak in a very dry period.
Resumo:
In this paper we present a set of field tests for detection of human in the water with an unmanned surface vehicle using infrared and color cameras. These experiments aimed to contribute in the development of victim target tracking and obstacle avoidance for unmanned surface vehicles operating in marine search and rescue missions. This research is integrated in the work conducted in the European FP7 research project Icarus aiming to develop robotic tools for large scale rescue operations. The tests consisted in the use of the ROAZ unmanned surface vehicle equipped with a precision GPS system for localization and both visible spectrum and IR cameras to detect the target. In the experimental setup, the test human target was deployed in the water wearing a life vest and a diver suit (thus having lower temperature signature in the body except hands and head) and was equipped with a GPS logger. Multiple target approaches were performed in order to test the system with different sun incidence relative angles. The experimental setup, detection method and preliminary results from the field trials performed in the summer of 2013 in Sesimbra, Portugal and in La Spezia, Italy are also presented in this work.
Resumo:
13th International Conference on Autonomous Robot Systems (Robotica), 2013
Resumo:
This work presents an automatic calibration method for a vision based external underwater ground-truth positioning system. These systems are a relevant tool in benchmarking and assessing the quality of research in underwater robotics applications. A stereo vision system can in suitable environments such as test tanks or in clear water conditions provide accurate position with low cost and flexible operation. In this work we present a two step extrinsic camera parameter calibration procedure in order to reduce the setup time and provide accurate results. The proposed method uses a planar homography decomposition in order to determine the relative camera poses and the determination of vanishing points of detected lines in the image to obtain the global pose of the stereo rig in the reference frame. This method was applied to our external vision based ground-truth at the INESC TEC/Robotics test tank. Results are presented in comparison with an precise calibration performed using points obtained from an accurate 3D LIDAR modelling of the environment.
Resumo:
In this work we propose the development of a stereo SLS system for underwater inspection operations. We demonstrate how to perform a SLS calibration both in dry and underwater environments using two different methods. The proposed methodology is able to achieve quite accurate results, lower than 1 mm in dry environments. We also display a 3D underwater scan of a known object size, a sea scallop, where the system is able to perform a scan with a global error lower than 2% of the object size.
Resumo:
In this paper we introduce a formation control loop that maximizes the performance of the cooperative perception of a tracked target by a team of mobile robots, while maintaining the team in formation, with a dynamically adjustable geometry which is a function of the quality of the target perception by the team. In the formation control loop, the controller module is a distributed non-linear model predictive controller and the estimator module fuses local estimates of the target state, obtained by a particle filter at each robot. The two modules and their integration are described in detail, including a real-time database associated to a wireless communication protocol that facilitates the exchange of state data while reducing collisions among team members. Simulation and real robot results for indoor and outdoor teams of different robots are presented. The results highlight how our method successfully enables a team of homogeneous robots to minimize the total uncertainty of the tracked target cooperative estimate while complying with performance criteria such as keeping a pre-set distance between the teammates and the target, avoiding collisions with teammates and/or surrounding obstacles.
Resumo:
4th International Conference, SIMPAR 2014, Bergamo, Italy, October 20-23, 2014
Resumo:
INTRODUCTION: Prolonged survival of patients under HAART has resulted in new demands for assisted reproductive technologies. HIV serodiscordant couples wish to make use of assisted reproduction techniques in order to avoid viral transmission to the partner or to the newborn. It is therefore essential to test the effectiveness of techniques aimed at reducing HIV and HCV loads in infected semen using molecular biology tests. METHODS: After seminal analysis, semen samples from 20 coinfected patients were submitted to cell fractioning and isolation of motile spermatozoa by density gradient centrifugation and swim-up. HIV and HCV RNA detection tests were performed with RNA obtained from sperm, seminal plasma and total semen. RESULTS: In pre-washing semen, HIV RNA was detected in 100% of total semen samples, whereas HCV RNA was concomitantly amplified in only one specimen. Neither HIV nor HCV were detected either in the swim-up or in the post-washing semen fractions. CONCLUSIONS: Reduction of HIV and/or HCV shedding in semen by density gradient centrifugation followed by swim-up is an efficient method. These findings lead us to believe that, although semen is rarely found to contain HCV, semen processing is highly beneficial for HIV/HCV coinfected individuals.
Resumo:
The diagnosis of American cutaneous leishmaniasis (ACL) is frequently based on clinical and epidemiological data associated with the results of laboratory tests. Some laboratory methods are currently being applied for the diagnosis of ACL, among them the indirect immunofluorescence reaction (IIFR), the Montenegro skin test (MST), histopathological examination, and the polymerase chain reaction (PCR). The performance of these methods varies in a considerable proportion of patients. After the standardization of an immunoenzymatic test (ELISA) for the detection of IgG in the serum of patients with ACL using a crude Leishmania braziliensis antigen, the results obtained were compared to those of other tests routinely used for the diagnosis. The tests revealed the following sensitivity, when analyzed separately: 85% for ELISA IgG, 81% for PCR, 64.4% for MST, 58.1% for IIFR, and 34% for the presence of parasites in the biopsy. ELISA was positive in 75% of patients with ACL presenting a negative MST, in 84.8% of ACL patients with negative skin or mucous biopsies for the presence of the parasite, and in 100% of cases with a negative PCR. Thus, ELISA presented a higher sensitivity than the other tests and was useful as a complementary method for the diagnosis of ACL.
Resumo:
Trypanosoma rangeli is non pathogenic for humans but of important medical and epidemiological interest because it shares vertebrate hosts, insect vectors, reservoirs and geographic areas with T. cruzi, the etiological agent of Chagas disease. Therefore, in this work, we set up two PCR reactions, TcH2AF/R and TrFR2, to distinguish T. cruzi from T. rangeli in mixed infections of vectors based on amplification of the histone H2A/SIRE and the small nucleolar RNA Cl1 genes, respectively. Both PCRs were able to appropriately detect all T. cruzi or T. rangeli experimentally infected-triatomines, as well as the S35/S36 PCR which amplifies the variable region of minicircle kDNA of T. cruzi. In mixed infections, whereas T. cruzi DNA was amplified in 100% of samples with TcH2AF/R and S35/S36 PCRs, T. rangeli was detected in 71% with TrF/R2 and in 6% with S35/S36. In a group of Rhodnius colombiensis collected from Coyaima (Colombia), T. cruzi was identified in 100% with both PCRs and T. rangeli in 14% with TrF/R2 and 10% with S35/S36 PCR. These results show that TcH2AF/R and TrF/R2 PCRs which are capable of recognizing all T. cruzi and T. rangeli strains and lineages could be useful for diagnosis as well as for epidemiological field studies of T. cruzi and T. rangeli vector infections.
Resumo:
Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para obtenção do grau de Mestre em Engenharia Electrotécnica e Computadores
Resumo:
Parvovirus B19 infection was first discovered in 1975 and it is implicated in fetal death from hydrops fetalis the world over. Diagnosis is usually made through histological identification of the intranuclear inclusion in placenta and fetal organs. However, these cells may be scarce or uncharacteristic, making definitive diagnosis difficult. We analyzed histologically placentas and fetal organs from 34 cases of non-immune hydrops fetalis, stained with Hematoxylin and Eosin (HE) and submitted to immunohistochemistry and polymerase chain reaction (PCR). Of 34 tissue samples, two (5.9%) presented typical intranuclear inclusion in circulating normoblasts seen in Hematoxylin and Eosin stained sections, confirmed by immunohistochemistry and PCR. However, PCR of fetal organs was negative in one case in which the placenta PCR was positive. We concluded that parvovirus B19 infection frequency is similar to the literature and that immunohistochemistry was the best detection method. It is highly specific and sensitive, preserves the morphology and reveals a larger number of positive cells than does HE with the advantage of showing cytoplasmic and nuclear positivity, making it more reliable. Although PCR is more specific and sensitive in fresh or ideally fixed material it is not so in formalin-fixed paraffin-embedded tissues, frequently the only one available in such cases.
Resumo:
Progressive disseminated histoplasmosis (PDH) is an increasingly common cause of infection in patients with acquired immune deficiency syndrome (AIDS). We report 21 cases of PDH associated with AIDS diagnosed by lysis-centrifugation blood culture method. The most prevalent clinical findings were fever, weight loss, respiratory symptoms, and mucocutaneous lesions. Chest roentgenogram showed diffuse pulmonary infiltrates in 13 of 21 patients (62%). Brochoalveolar fluid has yelded positive culture in four patients only in medium with cycloheximide.