Hand tracking in high-speed camera videos

Visual object tracking has been one of the most popular research topics in the field of computer vision recently. Specifically, hand tracking has attracted significant attention since it would enable many useful practical applications. However, hand tracking is still a very challenging problem which cannot be considered solved. The fact that almost every aspect of hand appearance can change is the fundamental reason for this difficulty. This thesis focused on 2D-based hand tracking in high-speed camera videos. During the project, a toolbox for this purpose was collected which contains nine different tracking methods. In the experiments, these methods were tested and compared against each other with both high-speed videos recorded during the project and publicly available normal speed videos. The results revealed that tracking accuracies varied considerably depending on the video and the method. Therefore, no single method was clearly the best in all videos, but three methods, CT, HT, and TLD, performed better than the others overall. Moreover, the results provide insights about the suitability of each method to different types and situations of hand tracking.

Automatic traffic sign inventory- and condition analysis

This thesis researches automatic traffic sign inventory and condition analysis using machine vision and pattern recognition methods. Automatic traffic sign inventory and condition analysis can be used to more efficient road maintenance, improving the maintenance processes, and to enable intelligent driving systems. Automatic traffic sign detection and classification has been researched before from the viewpoint of self-driving vehicles, driver assistance systems, and the use of signs in mapping services. Machine vision based inventory of traffic signs consists of detection, classification, localization, and condition analysis of traffic signs. The produced machine vision system performance is estimated with three datasets, from which two of have been been collected for this thesis. Based on the experiments almost all traffic signs can be detected, classified, and located and their condition analysed. In future, the inventory system performance has to be verified in challenging conditions and the system has to be pilot tested.

A micromethod for quantitation of debrisoquine and 4-hydroxydebrisoquine in urine by liquid chromatography

We describe a new simple, selective and sensitive micromethod based on HPLC and fluorescence detection to measure debrisoquine (D) and 4-hydroxydebrisoquine (4-OHD) in urine for the investigation of xenobiotic metabolism by debrisoquine hydroxylase (CYP2D6). Four hundred µl of urine was required for the analysis of D and 4-OHD. Peaks were eluted at 8.3 min (4-OHD), 14.0 min (D) and 16.6 min for the internal standard, metoprolol (20 µg/ml). The 5-µm CN-reverse-phase column (Shimpack, 250 x 4.6 mm) was eluted with a mobile phase consisting of 0.25 M acetate buffer, pH 5.0, and acetonitrile (9:1, v/v) at 0.7 ml/min with detection at lexcitation = 210 nm and lemission = 290 nm. The method, validated on the basis of measurements of spiked urine, presented 3 ng/ml (D) and 6 ng/ml (4-OHD) sensitivity, 390-6240 ng/ml (D) and 750-12000 ng/ml (4-OHD) linearity, and 5.7/8.2% (D) and 5.3/8.2% (4-OHD) intra/interassay precision. The method was validated using urine of a healthy Caucasian volunteer who received one 10-mg tablet of Declinax®, po, in the morning after an overnight fast. Urine samples (diuresis of 4 or 6 h) were collected from zero to 24 h. The urinary excretion of D and 4-OHD, Fel (0-24 h), i.e., fraction of dose administered and excreted into urine, was 6.4% and 31.9%, respectively. The hydroxylation capacity index reported as metabolic ratio was 0.18 (D/4-OHD) for the person investigated and can be compared to reference limits of >12.5 for poor metabolizers (PM) and <12.5 for extensive metabolizers (EM). In parallel, the recovery ratio (RR), another hydroxylation capacity index, was 0.85 (4-OHD: SD + 4-OHD) versus reference limits of RR <0.12 for PM and RR >0.12 for EM. The healthy volunteer was considered to be an extensive metabolizer on the basis of the debrisoquine test.

Press forming of paperboard – advancement of converting tools and process control

Press forming is nowadays one of the most common industrial methods in use for producing deeper trays from paperboard. Demands for material properties like recyclability and sustainability have increased also in the packaging industry, but there are still limitations related to the formability of paperboard. A majority of recent studies have focused on material development, but the potential of the package manufacturing process can also be improved by the development of tooling and process control. In this study, advanced converting tools (die cutting tools and the press forming mould) are created for production scale paperboard tray manufacturing. Also monitoring methods that enable the production of paperboard trays with enhanced quality, and can be utilized in process control are developed. The principles for tray blank preparation, including creasing pattern and die cutting tool design are introduced. The mould heating arrangement and determination of mould clearance are investigated to improve the quality of the press formed trays. The effect of the spring back of the tray walls on the tray dimensions can be managed by adjusting the heat-related process parameters and estimating it at the mould design stage. This enables production speed optimization as the process parameters can be adjusted more freely. Real-time monitoring of pressing force by using multiple force sensors embedded in the mould structure can be utilized in the evaluation of material characteristics on a modified production machinery. Comprehensive process control can be achieved with a combination of measurement of the outer dimensions of the trays and pressing force monitoring. The control method enables detection of defects and tracking changes in the material properties. The optimized converting tools provide a basis for effective operation of the control system.

Urban Detection From Hyperspectral Images Using Dimension-Reduction Model and Fusion of Multiple Segmentations Based on Stuctural and Textural Features

Ce mémoire de maîtrise présente une nouvelle approche non supervisée pour détecter et segmenter les régions urbaines dans les images hyperspectrales. La méthode proposée n ́ecessite trois étapes. Tout d’abord, afin de réduire le coût calculatoire de notre algorithme, une image couleur du contenu spectral est estimée. A cette fin, une étape de réduction de dimensionalité non-linéaire, basée sur deux critères complémentaires mais contradictoires de bonne visualisation; à savoir la précision et le contraste, est réalisée pour l’affichage couleur de chaque image hyperspectrale. Ensuite, pour discriminer les régions urbaines des régions non urbaines, la seconde étape consiste à extraire quelques caractéristiques discriminantes (et complémentaires) sur cette image hyperspectrale couleur. A cette fin, nous avons extrait une série de paramètres discriminants pour décrire les caractéristiques d’une zone urbaine, principalement composée d’objets manufacturés de formes simples g ́eométriques et régulières. Nous avons utilisé des caractéristiques texturales basées sur les niveaux de gris, la magnitude du gradient ou des paramètres issus de la matrice de co-occurrence combinés avec des caractéristiques structurelles basées sur l’orientation locale du gradient de l’image et la détection locale de segments de droites. Afin de réduire encore la complexité de calcul de notre approche et éviter le problème de la ”malédiction de la dimensionnalité” quand on décide de regrouper des données de dimensions élevées, nous avons décidé de classifier individuellement, dans la dernière étape, chaque caractéristique texturale ou structurelle avec une simple procédure de K-moyennes et ensuite de combiner ces segmentations grossières, obtenues à faible coût, avec un modèle efficace de fusion de cartes de segmentations. Les expérimentations données dans ce rapport montrent que cette stratégie est efficace visuellement et se compare favorablement aux autres méthodes de détection et segmentation de zones urbaines à partir d’images hyperspectrales.

Underwater Target Localization, Tracking and Classification

Underwater target localization and tracking attracts tremendous research interest due to various impediments to the estimation task caused by the noisy ocean environment. This thesis envisages the implementation of a prototype automated system for underwater target localization, tracking and classification using passive listening buoy systems and target identification techniques. An autonomous three buoy system has been developed and field trials have been conducted successfully. Inaccuracies in the localization results, due to changes in the environmental parameters, measurement errors and theoretical approximations are refined using the Kalman filter approach. Simulation studies have been conducted for the tracking of targets with different scenarios even under maneuvering situations. This system can as well be used for classifying the unknown targets by extracting the features of the noise emanations from the targets.

Object Detection in Images by Components

In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is described here for people is easily applied to other objects as well. The motivation for developing a component based approach is two fold: first, to enhance the performance of person detection systems on frontal and rear views of people and second, to develop a framework that directly addresses the problem of detecting people who are partially occluded or whose body parts blend in with the background. The data classification is handled by several support vector machine classifiers arranged in two layers. This architecture is known as Adaptive Combination of Classifiers (ACC). The system performs very well and is capable of detecting people even when all components of a person are not found. The performance of the system is significantly better than a full body person detector designed along similar lines. This suggests that the improved performance is due to the components based approach and the ACC data classification structure.

Feature tracking on the unit-sphere

Techniques used in a previous study of the objective identification and tracking of meteorological features in model data are extended to the unit sphere. An alternative feature detection scheme is described based on cubic interpolation for the sphere and local maximization. The extension of the tracking technique, used in the previous study, to the unit sphere is described. An example of the application of these techniques to a global relative vorticity field from a model integration are presented and discussed.

Improved fluorescent proteins for single-molecule research in molecular tracking and co-localization

Three promising variants of autofluorescent proteins have been analyzed photophysically for their proposed use in single-molecule microscopy studies in living cells to compare their superiority to other fluorescent proteins previously reported regarding the number of photons emitted. The first variant under investigation the F46L mutant of eYFP has a 10% greater photon emission rate and > 50% slower photobleaching rate on average than the standard eYFP fluorophore. The monomeric red fluorescent protein (mRFP) has a fivefold lower photon emission rate, likely due to the monomeric content, and also a tenfold faster photobleaching rate than the DsRed fluorescent protein. In contrast, the previously reported eqfp611 has a 50% lower emission rate yet photobleaches more than a factor 2 slowly. We conclude that the F46L YFP and the eqfp611 are superior new options for single molecule imaging and tracking studies in living cells. Studies were also performed on the effects of forced quenching of multiple fluorescent proteins in sub-micrometer regions that would show the effects of dimerization at low concentration levels of fluorescent proteins and also indicate corrections to stoichiometry patterns with fluorescent proteins previously in print. We also introduce properties at the single molecule level of new FRET pairs with combinations of fluorescent proteins and artificial fluorophores.

Evaluation of probabilistic occupancy map people detection for surveillance systems

In this paper, we evaluate the Probabilistic Occupancy Map (POM) pedestrian detection algorithm on the PETS 2009 benchmark dataset. POM is a multi-camera generative detection method, which estimates ground plane occupancy from multiple background subtraction views. Occupancy probabilities are iteratively estimated by fitting a synthetic model of the background subtraction to the binary foreground motion. Furthermore, we test the integration of this algorithm into a larger framework designed for understanding human activities in real environments. We demonstrate accurate detection and localization on the PETS dataset, despite suboptimal calibration and foreground motion segmentation input.

Towards pain-free diagnosis of skin diseases through multiplexed microneedles: biomarker extraction and detection using a highly sensitive blotting method

Immunodiagnostic microneedles provide a novel way to extract protein biomarkers from the skin in a minimally invasive manner for analysis in vitro. The technology could overcome challenges in biomarker analysis specifically in solid tissue, which currently often involves invasive biopsies. This study describes the development of a multiplex immunodiagnostic device incorporating mechanisms to detect multiple antigens simultaneously, as well as internal assay controls for result validation. A novel detection method is also proposed. It enables signal detection specifically at microneedle tips and therefore may aid the construction of depth profiles of skin biomarkers. The detection method can be coupled with computerised densitometry for signal quantitation. The antigen specificity, sensitivity and functional stability of the device were assessed against a number of model biomarkers. Detection and analysis of endogenous antigens (interleukins 1α and 6) from the skin using the device was demonstrated. The results were verified using conventional enzyme-linked immunosorbent assays. The detection limit of the microneedle device, at ≤10 pg/mL, was at least comparable to conventional plate-based solid-phase enzyme immunoassays.

Detection of urease in the cell wall and membranes from leaf tissues of bromeliad species

Urea is an important nitrogen source for some bromeliad species, and in nature it is derived from the excretion of amphibians, which visit or live inside the tank water. Its assimilation is dependent on the hydrolysis by urease (EC: 3.5.1.5), and although this enzyme has been extensively studied to date, little information is available about its cellular location. In higher plants, this enzyme is considered to be present in the cytoplasm. However, there is evidence that urease is secreted by the bromeliad Vriesea gigantea, implying that this enzyme is at least temporarily located in the plasmatic membrane and cell wall. In this article, urease activity was measured in different cell fractions using leaf tissues of two bromeliad species: the tank bromeliad V. gigantea and the terrestrial bromeliad Ananas comosus (L.) Merr. In both species, urease was present in the cell wall and membrane fractions, besides the cytoplasm. Moreover, a considerable difference was observed between the species: while V. gigantea had 40% of the urease activity detected in the membranes and cell wall fractions, less than 20% were found in the same fractions in A. comosus. The high proportion of urease found in cell wall and membranes in V. gigantea was also investigated by cytochemical detection and immunoreaction assay. Both approaches confirmed the enzymatic assay. We suggest this physiological characteristic allows tank bromeliads to survive in a nitrogen-limited environment, utilizing urea rapidly and efficiently and competing successfully for this nitrogen source against microorganisms that live in the tank water.

Motion Detection for Video Surveillance

This thesis is related to the broad subject of automatic motion detection and analysis in videosurveillance image sequence. Besides, proposing the new unique solution, some of the previousalgorithms are evaluated, where some of the approaches are noticeably complementary sometimes.In real time surveillance, detecting and tracking multiple objects and monitoring their activities inboth outdoor and indoor environment are challenging task for the video surveillance system. Inpresence of a good number of real time problems limits scope for this work since the beginning. Theproblems are namely, illumination changes, moving background and shadow detection.An improved background subtraction method has been followed by foreground segmentation, dataevaluation, shadow detection in the scene and finally the motion detection method. The algorithm isapplied on to a number of practical problems to observe whether it leads us to the expected solution.Several experiments are done under different challenging problem environment. Test result showsthat under most of the problematic environment, the proposed algorithm shows the better qualityresult.

A low cost one-camera optical tracking system for indoor wide-area augmented and virtual reality environments

In the last years the number of industrial applications for Augmented Reality (AR) and Virtual Reality (VR) environments has significantly increased. Optical tracking systems are an important component of AR/VR environments. In this work, a low cost optical tracking system with adequate attributes for professional use is proposed. The system works in infrared spectral region to reduce optical noise. A highspeed camera, equipped with daylight blocking filter and infrared flash strobes, transfers uncompressed grayscale images to a regular PC, where image pre-processing software and the PTrack tracking algorithm recognize a set of retro-reflective markers and extract its 3D position and orientation. Included in this work is a comprehensive research on image pre-processing and tracking algorithms. A testbed was built to perform accuracy and precision tests. Results show that the system reaches accuracy and precision levels slightly worse than but still comparable to professional systems. Due to its modularity, the system can be expanded by using several one-camera tracking modules linked by a sensor fusion algorithm, in order to obtain a larger working range. A setup with two modules was built and tested, resulting in performance similar to the stand-alone configuration.

Detection of SPM and IMP metallo-beta-lactamases in clinical specimens of Pseudomonas aeruginosa from a Brazilian public tertiary hospital

Phenotypic and genotypic SPM and IMP metallo-beta-lactamases (MBL) detection and also the determination of minimal inhibitory concentrations (MIC) to imipenem, meropenem and ceftazidime were evaluated in 47 multidrug-resistant Pseudomonas aeruginosa isolates from clinical specimens. Polymerase chain reaction detected 14 positive samples to either bla(SPM) or bla(IMP) genes, while the best phenotypic assay (ceftazidime substrate and mercaptopropionic acid inhibitor) detected 13 of these samples. Imipenem, meropenem and ceftazidime MICs were higher for MBL positive compared to MBL negative isolates. We describe here the SPM and IMP MBL findings in clinical specimens of P. aeruginosa from the University Hospital of Botucatu Medical School, São Paulo, Brazil, that reinforce local studies showing the high spreading of bla(SPM) and bla(IMP) genes among Brazilian clinical isolates.