Objective: The heart rate is an essential vital sign that can be measured remotely with camera-based photoplethysmography (cbPPG). Systems for cbPPG typically use cameras that deliver red, green, and blue (RGB) channels. The combination of these channels has been proven to increase signal-to-noise ratio (SNR) and heart rate measurement accuracy (ACC). However, many combinations remain untested, the comparison of proposed combinations on large datasets is insufficiently investigated, and the interplay with skin tone is rarely addressed. Methods: Eight regions of interest and eight color spaces with a total of 25 color channels were compared in terms of ACC and SNR based on the Binghamton-Pittsburgh-RPI Multimodal Spontaneous Emotion Database (BP4D+). Additionally, two systematic grid searches were performed to evaluate ACC in the space of linear combinations of the RGB channels. Results: Glabella and forehead regions of interest provided highest ACC (up to 74.1 %) and SNR (> -3 dB) with the hue channel H from HSV color space and the chrominance channel Q from NTSC color space. The grid searches revealed a global optimum of linear RGB combinations (ACC: 79.2 %). This optimum occurred for all skin tones, although ACC dropped for darker skin tones. Conclusion: Through systematic grid searches we were able to identify the skin tone independent optimal linear RGB color combination for measuring heart rate with cbPPG. Our results proved on a large dataset that the identified optimum outperformed conventionally used color channels. Significance: The presented findings provide useful evidence for future considerations of algorithmic approaches for cbPPG.

An image is a set of quantized intensity values that are sampled at a finite set of sample points on a two-dimensional plane. Images are crucial to many application areas, such as computer graphics and pattern recognition, because they discretely represent the information that the human eyes interpret. This thesis considers the use of triangular meshes for approximating intensity images. With the help of the wavelet-based analysis, triangular meshes can be efficiently constructed to approximate the image data. In this thesis, this study will focus on local image enhancement and mesh simplification operations, which try to minimize the total error of the reconstructed image as well as the number of triangles used to represent the image. The study will also present an optimal procedure for selecting triangle types used to represent the intensity image. Besides its applications to image and video compression, this triangular representation is potentially very useful for data storage and retrieval, and for processing such as image segmentation and object recognition. / Master of Science

HINTERGRUND/ ZIELSETZUNG: Vom idiopathischen Parkinsonsyndrom (IPS) können so genannte „atypische“ Parkinsonsyndrome (APS) mit einem Anteil von ca. 20% bezogen auf die Gesamtinzidenz unterschieden werden. Neben zusätzlichen Krankheitssymptomen und einem progredienteren Verlauf zeichnen sie sich durch eine schlechtere Prognose aus, die häufig auf einem Nichtansprechen auf eine dopaminerge Therapie beruht. Eine frühzeitige, korrekte Diagnose ist daher sehr entscheidend, aber im Einzelfall auch für Spezialisten äußerst schwierig. Trotz anerkannter klinischer Diagnosekriterien gibt es besonders im Frühstadium eine hohe Rate an Fehldiagnosen. Das zur Zeit vorherrschende Verfahren in der bildgebenden Diagnostik ist die Magnetresonanztomographie, wobei die konventionelle, qualitative MRT bislang keine zufriedenstellenden Ergebnisse bezüglich ihrer Spezifität und Sensitivität gezeigt hat. Die vorliegende Arbeit untersucht in einer direkten Vergleichsstudie das differenzialdiagnostische Potential der sogenannten „erweiterten“ quantitativen MRT-Verfahren. MATERIAL UND METHODEN: Ein Gesamtkollektiv von insgesamt 44 Probanden (IPS/ APS/ gesunde Kontrollen) durchlief ein umfassendes quantitatives MRT- Protokoll (R1/R2(*)-, DTI-, MTR- Mapping) um in manuell bilateral markierten, definierten Regionen (ROIs) in den Basalganglienkernen quantitative Parameter zu erheben. ERGEBNISSE: Die beste hochsignifikante Trennung der MSA-P- Patienten sowohl von IPS- Patienten (p = 0,001) als auch von Kontrollen (p = 0,004) konnte anhand des R2 * - Mappings im Putamen erreicht werden. Es zeigte sich eine Vorhersagekraft AUC von > / = 0,96 mit einer Sensitivität von 77,8 % (bei einer Spezifität von 100 %). Dies bestätigt die große Bedeutung der Eisensensitivität des R2*-Mappings bei der Identifizierung von MSA-P- Patienten. Auch anhand des MTR-Mappings konnte eine MSA-P anhand der putaminalen (p = 0,005) und nigralen (p = 0,003) Signalveränderungen signifikant vorhergesagt werden. Die beste signifikante Abgrenzung der PSP- Patienten von den Kontrollen gelang anhand der DTI- Messungen in der Substantia nigra (p = 0,001) sowie im Globus pallidus (p = 0,004). Für die diagnostische Vorhersage eines IPS konnten keine nutzbaren Signalunterschiede festgestellt werden. Insbesondere in der Substantia nigra zeigten sich gegenüber Kontrollen keine signifikanten Gruppenunterschiede. FAZIT: Unter den angewandten MRT- Verfahren zeigt das R2*-Mapping die beste Vorhersagekraft zur Differenzierung der MSA von IPS- Patienten und das DTI- Mapping zur Identifizierung der PSP- Patienten. Das Besondere unseres Arbeitsansatzes war, im Gegensatz zu vorherigen Studien, die Durchführung der Untersuchung an nur einer Kohorte. Dadurch konnte die Güte der verschiedenen MRT-Verfahren direkt und quantitativ miteinander verglichen werden. Insgesamt unterstreichen die Erkenntnisse dieser Arbeit den Stellenwert und die mögliche klinische Relevanz der quantitativen MRT, insbesondere bei der Identifizierung atypischer Parkinsonsyndrome.

This thesis is concerned with maximizing the coding efficiency, random accessibility and visual performance of scalable compressed video. The unifying theme behind this work is the use of finely embedded localized coding structures, which govern the extent to which these goals may be jointly achieved. The first part focuses on scalable volumetric image compression. We investigate 3D transform and coding techniques which exploit inter-slice statistical redundancies without compromising slice accessibility. Our study shows that the motion-compensated temporal discrete wavelet transform (MC-TDWT) practically achieves an upper bound to the compression efficiency of slice transforms. From a video coding perspective, we find that most of the coding gain is attributed to offsetting the learning penalty in adaptive arithmetic coding through 3D code-block extension, rather than inter-frame context modelling. The second aspect of this thesis examines random accessibility. Accessibility refers to the ease with which a region of interest is accessed (subband samples needed for reconstruction are retrieved) from a compressed video bitstream, subject to spatiotemporal code-block constraints. We investigate the fundamental implications of motion compensation for random access efficiency and the compression performance of scalable interactive video. We demonstrate that inclusion of motion compensation operators within the lifting steps of a temporal subband transform incurs a random access penalty which depends on the characteristics of the motion field. The final aspect of this thesis aims to minimize the perceptual impact of visible distortion in scalable reconstructed video. We present a visual optimization strategy based on distortion scaling which raises the distortion-length slope of perceptually significant samples. This alters the codestream embedding order during post-compression rate-distortion optimization, thus allowing visually sensitive sites to be encoded with higher fidelity at a given bit-rate. For visual sensitivity analysis, we propose a contrast perception model that incorporates an adaptive masking slope. This versatile feature provides a context which models perceptual significance. It enables scene structures that otherwise suffer significant degradation to be preserved at lower bit-rates. The novelty in our approach derives from a set of "perceptual mappings" which account for quantization noise shaping effects induced by motion-compensated temporal synthesis. The proposed technique reduces wavelet compression artefacts and improves the perceptual quality of video.

In the field of craniomaxillofacial (CMF) surgery, surgical planning is an important and necessary procedure due to the complex nature of the craniofacial skeleton. Computed tomography (CT) has brought about a revolution in virtual diagnosis, surgical planning and simulation, and evaluation of treatment outcomes. It provides high-quality 3D image and model of skull for Computer-aided surgical planning system (CSPS). During the planning process, one of the essential steps is to reestablish the dental occlusion. In the first project, a new approach is presented to automatically and efficiently reestablish dental occlusion. It includes two steps. The first step is to initially position the models based on dental curves and a point matching technique. The second step is to reposition the models to the final desired occlusion based on iterative surface-based minimum distance mapping with collision constraints. With linearization of rotation matrix, the alignment is modeled by solving quadratic programming. The simulation was completed on 12 sets of digital dental models. Two sets of dental models were partially edentulous, and another two sets have first premolar extractions for orthodontic treatment. Two validation methods were applied to the articulated models. The results show that using the proposed method, the dental models can be successfully articulated with a small degree of deviations from the occlusion achieved with the gold-standard method. Low contrast resolution in CBCT image has become its major limitation in building skull model. Intensive hand-segmentation is required to reconstruct the skull model. Thin bone images are particularly affected by this limitation. In the second project, a novel segmentation approach is presented based on wavelet active shape model (WASM) for a particular interest in the outer surface of the anterior wall of maxilla. 19 CBCT datasets are used to conduct two experiments. This model-based segmentation approach is validated and compared with three different segmentation approaches. The results show that the performance of this model-based segmentation approach is better than those of the other approaches. It can achieve 0.25 +/- 0.2mm of surface error distance from the ground truth of the bone surface. Field of view (FOV) can be reduced in order to reduce unnecessary radiation dose in CBCT. This ROI imaging is common in most of the dentomaxillofacial imaging and orthodontic practices. However, a truncation effect is created due to the truncation of projection images and becomes one of the limitation in CBCT. In the third project, a method for small region of interest (ROI) imaging and reconstruction of the image of ROI in CBCT and two experiments for measurement of dosage are presented. The first experiment shows at least 60% and 70% of radiation dose can be reduced. It also demonstrates that the image quality was still acceptable with little variation of gray by using the traditional truncation correction approach for ROI imaging. The second experiment demonstrates that the images reconstructed by CBCT reconstruction algorithms without truncation correction can be degraded to unacceptable image quality.

L'increment de bases de dades que cada vegada contenen imatges més difícils i amb un nombre més elevat de categories, està forçant el desenvolupament de tècniques de representació d'imatges que siguin discriminatives quan es vol treballar amb múltiples classes i d'algorismes que siguin eficients en l'aprenentatge i classificació. Aquesta tesi explora el problema de classificar les imatges segons l'objecte que contenen quan es disposa d'un gran nombre de categories. Primerament s'investiga com un sistema híbrid format per un model generatiu i un model discriminatiu pot beneficiar la tasca de classificació d'imatges on el nivell d'anotació humà sigui mínim. Per aquesta tasca introduïm un nou vocabulari utilitzant una representació densa de descriptors color-SIFT, i desprès s'investiga com els diferents paràmetres afecten la classificació final. Tot seguit es proposa un mètode par tal d'incorporar informació espacial amb el sistema híbrid, mostrant que la informació de context es de gran ajuda per la classificació d'imatges. Desprès introduïm un nou descriptor de forma que representa la imatge segons la seva forma local i la seva forma espacial, tot junt amb un kernel que incorpora aquesta informació espacial en forma piramidal. La forma es representada per un vector compacte obtenint un descriptor molt adequat per ésser utilitzat amb algorismes d'aprenentatge amb kernels. Els experiments realitzats postren que aquesta informació de forma te uns resultats semblants (i a vegades millors) als descriptors basats en aparença. També s'investiga com diferents característiques es poden combinar per ésser utilitzades en la classificació d'imatges i es mostra com el descriptor de forma proposat juntament amb un descriptor d'aparença millora substancialment la classificació. Finalment es descriu un algoritme que detecta les regions d'interès automàticament durant l'entrenament i la classificació. Això proporciona un mètode per inhibir el fons de la imatge i afegeix invariança a la posició dels objectes dins les imatges. S'ensenya que la forma i l'aparença sobre aquesta regió d'interès i utilitzant els classificadors random forests millora la classificació i el temps computacional. Es comparen els postres resultats amb resultats de la literatura utilitzant les mateixes bases de dades que els autors Aixa com els mateixos protocols d'aprenentatge i classificació. Es veu com totes les innovacions introduïdes incrementen la classificació final de les imatges. / The release of challenging data sets with ever increasing numbers of object categories isforcing the development of image representations that can cope with multiple classes andof algorithms that are efficient in training and testing. This thesis explores the problem ofclassifying images by the object they contain in the case of a large number of categories. We first investigate weather the hybrid combination of a latent generative model with a discriminative classifier is beneficial for the task of weakly supervised image classification.We introduce a novel vocabulary using dense color SIFT descriptors, and then investigate classification performances by optimizing different parameters. A new way to incorporate spatial information within the hybrid system is also proposed showing that contextual information provides a strong support for image classification. We then introduce a new shape descriptor that represents local image shape and its spatial layout, together with a spatial pyramid kernel. Shape is represented as a compactvector descriptor suitable for use in standard learning algorithms with kernels. Experimentalresults show that shape information has similar classification performances and sometimes outperforms those methods using only appearance information. We also investigate how different cues of image information can be used together. Wewill see that shape and appearance kernels may be combined and that additional informationcues increase classification performance. Finally we provide an algorithm to automatically select the regions of interest in training. This provides a method of inhibiting background clutter and adding invariance to the object instance's position. We show that shape and appearance representation over the regions of interest together with a random forest classifier which automatically selects the best cues increases on performance and speed. We compare our classification performance to that of previous methods using the authors'own datasets and testing protocols. We will see that the set of innovations introduced here lead for an impressive increase on performance.

No description available.

High resolution surveillance video cameras are invaluable resources for effective crime prevention and forensic investigations. However, increasing communication bandwidth requirements of high definition surveillance videos are severely limiting the number of cameras that can be deployed. Higher bitrate also increases operating expenses due to higher data communication and storage costs. Hence, it is essential to develop low complexity algorithms which reduce data rate of the compressed video stream without affecting the image fidelity. In this thesis, a computer vision aided H.264 surveillance video encoder and four associated algorithms are proposed to reduce the bitrate. The proposed techniques are (I) Speeded up foreground segmentation, (II) Skip decision, (III) Reference frame selection and (IV) Face Region-of-Interest (ROI) coding. In the first part of the thesis, a modification to the adaptive Gaussian Mixture Model (GMM) based foreground segmentation algorithm is proposed to reduce computational complexity. This is achieved by replacing expensive floating point computations with low cost integer operations. To maintain accuracy, we compute periodic floating point updates for the GMM weight parameter using the value of an integer counter. Experiments show speedups in the range of 1.33 - 1.44 on standard video datasets where a large fraction of pixels are multimodal. In the second part, we propose a skip decision technique that uses a spatial sampler to sample pixels. The sampled pixels are segmented using the speeded up GMM algorithm. The storage pattern of the GMM parameters in memory is also modified to improve cache performance. Skip selection is performed using the segmentation results of the sampled pixels. In the third part, a reference frame selection algorithm is proposed to maximize the number of background Macroblocks (MB’s) (i.e. MB’s that contain background image content) in the Decoded Picture Buffer. This reduces the cost of coding uncovered background regions. Distortion over foreground pixels is measured to quantify the performance of skip decision and reference frame selection techniques. Experimental results show bit rate savings of up to 94.5% over methods proposed in literature on video surveillance data sets. The proposed techniques also provide up to 74.5% reduction in compression complexity without increasing the distortion over the foreground regions in the video sequence. In the final part of the thesis, face and shadow region detection is combined with the skip decision algorithm to perform ROI coding for pedestrian surveillance videos. Since person identification requires high quality face images, MB’s containing face image content are encoded with a low Quantization Parameter setting (i.e. high quality). Other regions of the body in the image are considered as RORI (Regions of reduced interest) and are encoded at low quality. The shadow regions are marked as Skip. Techniques that use only facial features to detect faces (e.g. Viola Jones face detector) are not robust in real world scenarios. Hence, we propose to initially detect pedestrians using deformable part models. The face region is determined using the deformed part locations. Detected pedestrians are tracked using an optical flow based tracker combined with a Kalman filter. The tracker improves the accuracy and also avoids the need to run the object detector on already detected pedestrians. Shadow and skin detector scores are computed over super pixels. Bilattice based logic inference is used to combine multiple likelihood scores and classify the super pixels as ROI, RORI or RONI. The coding mode and QP values of the MB’s are determined using the super pixel labels. The proposed techniques provide a further reduction in bitrate of up to 50.2%.

Humanitarian clearance of minefields is most often carried out by hand, conventionally using a a metal detector and a probe. Detection is a very slow process, as every piece of detected metal must treated as if it were a landmine and carefully probed and excavated, while many of them are not. The process can be safely sped up by use of Ground-Penetrating Radar (GPR) to image the subsurface, to verify metal detection results and safely ignore any objects which could not possibly be a landmine. In this thesis, we explore the possibility of using Full Wave Inversion (FWI) to improve GPR imaging for landmine detection. Posing the imaging task as FWI means solving the large-scale, non-linear and ill-posed optimisation problem of determining the physical parameters of the subsurface (such as electrical permittivity) which would best reproduce the data. This thesis begins by giving an overview of all the mathematical and implementational aspects of FWI, so as to provide an informative text for both mathematicians (perhaps already familiar with other inverse problems) wanting to contribute to the mine detection problem, as well as a wider engineering audience (perhaps already working on GPR or mine detection) interested in the mathematical study of inverse problems and FWI.We present the first numerical 3D FWI results for GPR, and consider only surface measurements from small-scale arrays as these are suitable for our application. The FWI problem requires an accurate forward model to simulate GPR data, for which we use a hybrid finite-element boundary-integral solver utilising first order curl-conforming N\'d\'{e}lec (edge) elements. We present a novel `line search' type algorithm which prioritises inversion of some target parameters in a region of interest (ROI), with the update outside of the area defined implicitly as a function of the target parameters. This is particularly applicable to the mine detection problem, in which we wish to know more about some detected metallic objects, but are not interested in the surrounding medium. We may need to resolve the surrounding area though, in order to account for the target being obscured and multiple scattering in a highly cluttered subsurface. We focus particularly on spatial sensitivity of the inverse problem, using both a singular value decomposition to analyse the Jacobian matrix, as well as an asymptotic expansion involving polarization tensors describing the perturbation of electric field due to small objects. The latter allows us to extend the current theory of sensitivity in for acoustic FWI, based on the Born approximation, to better understand how polarization plays a role in the 3D electromagnetic inverse problem. Based on this asymptotic approximation, we derive a novel approximation to the diagonals of the Hessian matrix which can be used to pre-condition the GPR FWI problem.