This thesis explores the contactless estimation of people’s vital signs. We designed two camera-based systems and applied object detection algorithms to locate the regions of interest where vital signs are estimated. With the development of Deep Learning, Convolutional Neural Network (CNN) model has many applications in the real world nowadays. We applied the CNN based frameworks to the different types of camera based systems and improve the efficiency of the contactless vital signs estimation. In the field of medical healthcare, contactless monitoring draws a lot attention in the recent years because the wide use of different sensors. However most of the methods are still in the experimental phase and have never been used in real applications. We were interested in monitoring vital signs of patients lying in bed or sitting around the bed at a hospital. This required using sensors that have range of 2 to 5 meters. We developed a system based on the depth camera for detecting people’s chest area and the radar for estimating the respiration signal. We applied a CNN based object detection method to locate the position of the subject lying in the bed covered with blanket. And the respiratory-like signal is estimated from the radar device based on the detected subject’s location. We also create a manually annotated dataset containing 1,320 depth images. In each of the depth image the silhouette of the subject’s upper body is annotated, as well as the class. In addition, a small subset of the depth images also labeled four keypoints for the positioning of people’s chest area. This dataset is built on the data collected from the anonymous patients at the hospital which is substantial. Another problem in the field of human vital signs monitoring is that systems seldom contain the functions of monitoring multiple vital signs at the same time. Though there are few attempting to work on this problem recently, they are still all prototypes and have a lot limitations like shorter operation distance. In this application, we focused on contactless estimating subjects’ temperature, breathing rate and heart rate at different distances with or without wearing the mask. We developed a system based on thermal and RGB camera and also explore the feasibility of CNN based object detection algorithms to detect the vital signs from human faces with specifically defined RoIs based on our thermal camera system. We proposed the methods to estimate respiratory rate and heart rate from the thermal videos and RGB videos. The mean absolute difference (MAE) between the estimated HR using the proposed method and the baseline HR for all subjects at different distances is 4.24 ± 2.47 beats per minute, the MAE between the estimated RR and the reference RR for all subjects at different distances is 1.55 ± 0.78 breaths per minute.

No description available.

The diploma thesis deals with the origin and adaptation of the concept of CNN Prima NEWS on the Czech market and its possible hybridization. The expansion of global media corporations is a phenomenon of the 20th century that affects persisted till present. The television companies set up centers, branches or, through the sale of licenses, reach its audience through localized television stations. This thesis approaches the theory of globalization with a focus on the concepts of global culture, glocalization and hybridization. With standardization of successful patterns the companys strengthen the its positions in the global market, expand their influence and, last but not least, it is a profitable prosperous activity that does not require high costs. The thesis captures the arrival of the licensing concept of a global television station on Czech media market. The thesis develops connection of the global news brand CNN with Czech commercial television. These connections and deviations are elaborated and compared on the basis of three confrontable areas. At the same time, it is evaluated what creates this concept and what are its possible forms of hybridization.

Journalism as we know it today is facing massive change. Technological advances have enabled new ways of delivering news which differ from traditional means in both practical and content-related matters. This bachelors thesis intended to obtain greater understanding of how journalistic content manifested itself on the new media platform Snapchat. We chose to conduct a socialsemiotic analysis of six of CNNs “stories” on the platform and their corresponding content on CNNs website. By doing this we could distinguish a signifigant change in both magnitude and form. Compared to the corresponding content the stories contained less information and indicated a higher level of sensation and dramatics. In addition we found that information not conveyed in the stories text could appear in other modalities such as image or music. This suggests a different way of storytelling in news media when distributed on this new platform.

We consider the problem of enabling a robot to efficiently obtain a dense haptic map of its visible surroundings Using the complementary properties of vision and tactile sensing. Our approach assumes that visible surfaces that look similar to one another are likely to have similar haptic properties. In our previous work, we introduced an iterative algorithm that enabled a robot to infer dense haptic labels across visible surfaces in an RGB-D image when given a sequence of sparse haptic labels. In this work, we describe how dense conditional random fields (CRFs) can be applied to this same problem and present results from evaluating a dense CRF’s performance in simulated trials with idealized haptic labels. We evaluated our method using several publicly available RGB-D image datasets with indoor cluttered scenes pertinent to robot manipulation. In these simulated trials, the dense CRF substantially outperformed our previous algorithm by correctly assigning haptic labels to an average of 93% (versus 76% in our previous work) of all object pixels in an image given the highest number of contact points per object. Likewise, the dense CRF correctly assigned haptic labels to an average of 81% (versus 63% in our previous work) of all object pixels in an image given a low number of contact points per object. We compared the performance of dense CRF using uniform prior with a dense CRF using prior obtained from the visible scene using a Fully Convolutional Network trained for visual material recognition. The use of the convolutional network further improves the performance of the algorithm. We also performed experiments with the humanoid robot DARCI reaching in a cluttered foliage environment while using our algorithm to create a haptic map. The algorithm correctly assigned the label to 82.52% of the scenes with trunks and leaves after 10 reaches into the environment.

Is there any truth in the saying “no news is good news” or is there a reason to question whether media actually do reflect the world’s worst conflicts proportionally? The communication technologies have seen major developments in recent years, and more and more people choose to read their news on the Internet. With smartphones and other devices, one could imagine that there would be easier to cover more conflict areas than ever – but is this what has happened? In this study we aimed to investigate how three chosen Swedish newspapers reflected five of the on-going conflicts of 2012 and how this can be explained with the theories; the CNN effect and Stealth Conflicts. We started out with studies of the two theories. The definition of “conflict” used in this study is Uppsala Conflict Data Program’s “war and minor conflict”. Then a quantitative study followed, where we used the three newspapers’ websites to search for articles about our chosen conflict areas: Algeria, Israel, Democratic Republic of Congo, Rwanda and Syria. The conclusion of this study is that there is, at least among our chosen newspapers, a disproportionate covering of the world’s conflicts, with the exception of Syria. This matches largely with how the two theories explain the media’s covering of conflicts, but we found a deeper explanation in the Stealth Conflict theory, though the CNN effect stood for interesting points as well. The theories could benefit from a merger since that would create a theory with a wider range of explanation tools of why the conflict news reports looks and works the way it does and of its consequences.

Ingeniero Civil Eléctrico / En el presente trabajo de título se desarrolla un sistema de detección de objetos (localización y clasificación), basado en redes neuronales convolucionales (CNN por su sigla en inglés) y dos métodos clásicos de machine learning como Random Forest (RF) y Support Vector Machines (SVMs). La idea es mejorar, con los mencionados clasificadores, el rendimiento del sistema de detección conocido como Faster R-CNN (su significado en inglés es: Regions with CNN features). El sistema Faster R-CNN, se fundamenta en el concepto de region proposal para generar muestras candidatas a ser objetos y posteriormente producir dos salidas: una con la regresión que caracteriza la localización de los objetos y otra con los puntajes de confianza asociados a los bounding boxes predichos. Ambas salidas son generadas por capas completamente conectadas. En este trabajo se interviene la salida que genera los puntajes de confianza, tal que, en este punto se conecta un clasificador (RF o SVM), para generar con estos los puntajes de salida del sistema. De esta forma se busca mejorar el rendimiento del sistema Faster R-CNN. El entrenamiento de los clasificadores se realiza con los vectores de características extraídos, desde una de las capas completamente conectadas del sistema Faster R-CNN, específicamente se prueban las tres que contempla la arquitectura, para evaluar cuál de estas permite obtener los mejores resultados. Para definir, entre otras cosas, el número de capas convolucionales a utilizar y el tamaño de los filtros presentes en las primeras capas del sistema Faster R-CNN, se emplean los modelos de redes convolucionales ZF y VGG16, estas redes son solamente de clasificación, y son las mismas ocupados originalmente. Para desarrollar los sistemas propuestos se utilizan distintas implementaciones o librerías para las cuales se dispone de su código de forma abierta. Para el detector Faster R-CNN se utiliza una implementación desarrollado en Python, para RF se comparan dos librerías: randomForest escrita en R y scikit-learn en Python. Por su parte para SVM se utiliza la librería conocida como LIBSVM escrita en C. Las principales tareas de programación consisten en desarrollar los algoritmos de etiquetado de los vectores de características extraídos desde las capas completamente conectadas; unir los clasificadores con el sistema base, para el análisis \textit{online} de las imágenes en la etapa de prueba; programar un algoritmo para el entrenamiento eficiente en tiempo y en memoria para SVM (algoritmo conocido como hard negative mining) Al evaluar los sistemas desarrollados se concluye que los mejores resultados se obtienen con la red VGG16, específicamente para el caso en que se implementa el sistema Faster R-CNN+SVM con kernel RBF (radial basis function), logrando un mean Average Precision (mAP) de 68.9%. El segundo mejor resultado se alcanza con Faster R-CNN+RF con 180 árboles y es de 67.8%. Con el sistema original Faster R-CNN se consigue un mAP de 69.3%.

Μια σύντομη αναφορά σε κάποια γνωστά μοντέλα Νευρωνικών Δικτύων, περιγραφή της αρχιτεκτονικής τους και εφαρμογές. Παραδείγματα και εφαρμογές Δυναμικών Νευρωνικών Δικτύων. Γενικό πλαίσιο λειτουργίας των CNN, ιδιότητες και εφαρμογές. / A short reference in Neural Networks, architecture description and applications. Implementation of Dynamic Neural Networks. CNN (cellular neural networks) paradigm, attributes and examples.

The animal-vehicle collision has been a topic of concern for years, especially in North America. To mitigate the problem, this thesis focuses on animal detection based on the onboard camera for intelligent vehicles. In the domain of image classification and object detection, the methods of shape matching and local feature crafting have reached the technical plateau for decades. The development of Convolutional Neural Network (CNN) brings a new breakthrough. The evolution of CNN architectures has dramatically improved the performance of image classification. Effective frameworks on object detection through CNN structures are thus boosted. Notably, the family of Region-based Convolutional Neural Networks (R-CNN) perform well by combining region proposal with CNN. In this thesis, we propose to apply a new region proposal method|Maximally Stable Extremal Regions (MSER) in Fast R-CNN to construct the animal detection framework. MSER algorithm detects stable regions which are invariant to scale, rotation and viewpoint changes. We generate regions of interest by dealing with the result of MSER algorithm in two ways: by enclosing all the pixels from the resulted pixel-list with a minimum enclosing rectangle (the PL MSER) and by fitting the resulted elliptical region to an approximate box (the EL MSER). We then preprocess the bounding boxes of PL MSER and EL MSER to improve the recall of detection. The preprocessing steps consist of filtering out undesirable regions by aspect ratio model, clustering bounding boxes to merge the overlapping regions, modifying and then enlarging the regions to cover the entire animal. We evaluate the two region proposal methods by the measurement of recall over IOU-threshold curve. The proposed MSER method can cover the expected regions better than Edge Boxes and Region Proposal Network (RPN) in Faster R-CNN. We apply the MSER region proposal method to the framework of R-CNN and Fast R-CNN. The experiments on the animal database with moose, deer, elk, and horses show that Fast R-CNN with MSER achieves better accuracy and faster speed than R-CNN with MSER. Concerning the two ways of MSER, the experimental results show that PL MSER is faster than EL MSER and EL MSER gains higher precision than PL MSER. Also, by altering the structure of network used in Fast R-CNN, we verify that network stacking more layers achieves higher accuracy and recall. In addition, we compare the Fast R-CNN framework using MSER region proposal with the state-of-the-art Faster R-CNN by evaluating the experimental results of on our animal database. Using the same CNN structure, the proposed Fast R-CNN with MSER gains a higher average accuracy of the animal detection 0.73, compared to 0.42 of Faster R-CNN. In terms of detection quality, the proposed Fast R-CNN with MSER achieves better IoU histogram than that of Faster R-CNN.

Parsing floorplans have been a problem in automatic document analysis for long and have up until recent years been approached with algorithmic methods. With the rise of convolutional neural networks (CNN), this problem too has seen an upswing in performance. In this thesis the task is to recover, as accurately as possible, spatial and geometric information from floorplans. This project builds around instance segmentation models like Cascade Mask R-CNN to extract the bulk of information from a floorplan image. To complement the segmentation, a new style of using keypoint-CNN is presented to find precise locations of corners. These are then combined in a post-processing step to give the resulting segmentation. The resulting segmentation scores exceed the current baseline of the CubiCasa5k floorplan dataset with a mean IoU of 72.7% compared to 57.5%. Further, the mean IoU for individual classes is also improved for almost every class. It is also shown that Cascade Mask R-CNN is better suited than Mask R-CNN for this task.