>Magister Scientiae - MSc / The SASL project is in the process of developing a machine translation system that can translate fully-fledged phrases between SASL and English in real-time. To-date, several systems have been developed by the project focusing on facial expression, hand shape, hand motion, hand orientation and hand location recognition and estimation. Achmed developed a highly accurate upper body pose recognition and estimation system. The system is capable of recognizing and estimating the location of the arms from a twodimensional video captured from a monocular view at an accuracy of 88%. The system operates at well below real-time speeds. This research aims to investigate the use of optimizations and parallel processing techniques using the CUDA framework on Achmed’s algorithm to achieve real-time upper body pose recognition and estimation. A detailed analysis of Achmed’s algorithm identified potential improvements to the algorithm. Are- implementation of Achmed’s algorithm on the CUDA framework, coupled with these improvements culminated in an enhanced upper body pose recognition and estimation system that operates in real-time with an increased accuracy.

Contexte : Les patients recevant une pose d’implants dentaires ressentent une douleur procédurale faible à modérée pendant la chirurgie malgré une anesthésie locale et un analgésique préopératoire. Des affects négatifs sont également associés à cette douleur. Durant les jours suivants, la douleur se poursuit et est soulagée par des analgésiques. Il est donc important de réduire cette douleur périopératoire persistante, l’expérience émotionnelle négative qui l’accompagne et la consommation d’analgésiques, par une approche non pharmacologique. En ce sens, la musique peut les réduire chez diverses populations cliniques, mais à notre connaissance, son efficacité n’a pas été étudiée dans le contexte d’implantologie dentaire. Objectif : Ce projet de recherche visait à comparer les effets de l’écoute de musique à celle d’un livre audio (groupe contrôle) dans le cadre d’une pose d’implants dentaires, sur la douleur pendant la chirurgie et les affects associés, ainsi que la douleur et la consommation d’analgésiques au cours des jours suivants la chirurgie. Méthodologie : Vingt-huit patients ont été recrutés et répartis de manière aléatoire dans le groupe musique ou contrôle (livre audio). En fonction du groupe qui leur avait été assigné, chaque participant a choisi parmi sept options de musique ou de livre audio. Des mesures autorapportées ont été utilisées pour la douleur, les affects associés et la consommation d’analgésiques, avant et après la chirurgie, et au cours des sept jours postopératoires. Résultats : La douleur ressentie pendant la chirurgie était significativement moindre pour les participants qui écoutaient de la musique pendant la chirurgie que pour ceux qui écoutaient un livre audio. Cependant, il n’y avait pas de différences significatives entre les groupes pour la douleur et pour la consommation d’analgésiques durant les jours postopératoires. En ce qui concerne les affects négatifs, les participants ayant écouté de la musique en ressentaient significativement moins que ceux ayant écouté un livre audio. Conclusion : L’écoute de musique permet de réduire la douleur procédurale et ses affects négatifs lors d’une chirurgie de pose d’implants dentaires. Ainsi, elle pourrait être utilisée dans d’autres contextes cliniques comme approche analgésique non pharmacologique simple, abordable et adjuvante aux traitements pharmacologiques existant. / Background: Patients receiving dental implants placement experience mild to moderate procedural pain during surgery, despite local anesthesia and intake of a preoperative analgesic. There are also negative affects associated with this pain. During the following days, the pain continues and is treated with analgesics. Therefore, it is important to reduce this persisting perioperative pain, the negative emotional experience that accompanies it as well as consumption of analgesics with a non-pharmacological approach. In this sense, music can reduce them in various clinical populations, but to our knowledge, its effectiveness has not been studied in the context of dental implantology. Objective: The purpose of this research project was to compare the effects of listening to music and listening to an audiobook (control group) in the context of dental implant surgery on pain during surgery and associated affects, as well as pain and analgesics consumption in the days following surgery. Methodology: Twenty-eight patients were recruited and randomly assigned to the music or control (audiobook) group. Based on their assigned group, each participant chose from seven music or audiobook options. Self-reported measures were used for pain and associated affects, before and after surgery, and during the seven postoperative days. Results: Pain experienced during surgery was significantly lower for participants who listened to music during surgery than for those who listened to an audiobook. However, there was no significant difference between the groups in either pain or analgesics use during the postoperative days. Participants who listened to music felt signicantly fewer negative affects than those who listened to audiobooks. Conclusion: Listening to music reduces procedural pain and its negative affects during dental implant placement surgery. As such, it could be used in other clinical settings as a simple, affordable, non-pharmacological analgesic approach and adjuvant to pharmacological treatments already in place.

Joint detection is vital for characterizing human pose and serves as a foundation for a wide range of computer vision applications such as physical training, health care, entertainment. This dissertation proposed two methods to detect joints in the human body for pose analysis. The first method detects joints by combining body model and automatic feature points detection together. The human body model maps the detected extreme points to the corresponding body parts of the model and detects the position of implicit joints. The dominant joints are detected after implicit joints and extreme points are located by a shortest path based methods. The main contribution of this work is a hybrid framework to detect joints on the human body to achieve robustness to different body shapes or proportions, pose variations and occlusions. Another contribution of this work is the idea of using geodesic features of the human body to build a model for guiding the human pose detection and estimation. The second proposed method detects joints by segmenting human body into parts first and then detect joints by making the detection algorithm focusing on each limb. The advantage of applying body part segmentation first is that the body segmentation method narrows down the searching area for each joint so that the joint detection method can provide more stable and accurate results.

The goal of this diploma thesis is design and implementation of an application for automated measurement of objects in augmented reality. It focuses on automating the entire process, so that the user carries out the fewest number of manual actions. The proposed interface divides the measurement into several steps in which it gives the user instructions to progress to the next stage. The result is an Android application with ARCore technology. Is capable of determining the minimal bounding box of an object of a general shape lying on a horizontal surface. Measure error depends on ambient conditions and is in units of percent.

K nahrazení člověka při úloze testování dotykových embedded zařízení je zapotřebí vyvinout komplexní automatizovaný robotický systém. Jedním ze zásadních úkolů je tento systém automaticky zkalibrovat. V této práci jsem se zabýval možnými způsoby automatické kalibrace robotického ramene v prostoru ve vztahu k dotykovému zařízení pomocí jedné či více kamer. Následně jsem představil řešení založené na estimaci polohy jedné kamery pomocí iterativních metod jako např. Gauss-Newton nebo Levenberg-Marquardt. Na konci jsem zhodnotil dosaženou přesnost a navrhnul postup pro její zvýšení.

The aim of this work is to design a method for the object localization in the point could and as accurately as possible estimates the 6D pose of known objects in the industrial scene for bin picking. The design of the solution is inspired by the PoseCNN network. The solution also includes a scene simulator that generates artificial data. The simulator is used to generate a training data set containing 2 objects for training a convolutional neural network. The network is tested on annotated real scenes and achieves low success, only 23.8 % and 31.6 % success for estimating translation and rotation for one type of obejct and for another 12.4 % and 21.6 %, while the tolerance for correct estimation is 5 mm and 15°. However, by using the ICP algorithm on the estimated results, the success of the translation estimate is 81.5 % and the rotation is 51.8 % and for the second object 51.9 % and 48.7 %. The benefit of this work is the creation of a generator and testing the functionality of the network on small objects

Sectors of security, safety, and defence require methods for identifying people on the individual level. Automation of these tasks has the potential of outperforming manual labor, as well as relieving workloads. The ever-extending surveillance camera networks, advances in human pose estimation from monocular cameras, together with the progress of deep learning techniques, pave the way for automated walking gait analysis as an identification method. This thesis investigates the use of 2D kinematic pose sequences to represent gait, monocularly extracted from a limited dataset containing walking individuals captured from five camera views. The sequential information of the gait is captured using recurrent neural networks. Techniques in deep metric learning are applied to evaluate two network models, with contrasting output dimensionalities, against deep-metric-, and non-deep-metric-based embedding spaces. The results indicate that the gait representation, network designs, and network learning structure show promise when identifying individuals, scaling particularly well to unseen individuals. However, with the limited dataset, the network models performed best when the dataset included the labels from both the individuals and the camera views simultaneously, contrary to when the data only contained the labels from the individuals without the information of the camera views. For further investigations, an extension of the data would be required to evaluate the accuracy and effectiveness of these methods, for the re-identification task of each individual. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>

Recent advances in technology have increased awareness of the necessity for automated systems in people’s everyday lives. Artificial systems are more frequently being introduced into environments previously thought to be too perilous for humans to operate in. Some robots can be used to extract potentially hazardous materials from sites inaccessible to humans, while others are being developed to aid humans with laborious tasks. A crucial aspect of all artificial systems is the manner in which they interact with their immediate surroundings. Developing such a deceivingly simply aspect has proven to be significantly challenging, as it not only entails the methods through which the system perceives its environment, but also its ability to perform critical tasks. These undertakings often involve the coordination of numerous subsystems, each performing its own complex duty. To complicate matters further, it is nowadays becoming increasingly important for these artificial systems to be able to perform their tasks in real-time. The task of object recognition is typically described as the process of retrieving the object in a database that is most similar to an unknown, or query, object. Pose estimation, on the other hand, involves estimating the position and orientation of an object in three-dimensional space, as seen from an observer’s viewpoint. These two tasks are regarded as vital to many computer vision techniques and regularly serve as input to more complex perception algorithms. An approach is presented which regards the object recognition and pose estimation procedures as mutually dependent. The core idea is that dissimilar objects might appear similar when observed from certain viewpoints. A feature-based conceptualisation, which makes use of a database, is implemented and used to perform simultaneous object recognition and pose estimation. The design incorporates data compression techniques, originally suggested by the image-processing community, to facilitate fast processing of large databases. System performance is quantified primarily on object recognition, pose estimation and execution time characteristics. These aspects are investigated under ideal conditions by exploiting three-dimensional models of relevant objects. The performance of the system is also analysed for practical scenarios by acquiring input data from a structured light implementation, which resembles that obtained from many commercial range scanners. Practical experiments indicate that the system was capable of performing simultaneous object recognition and pose estimation in approximately 230 ms once a novel object has been sensed. An average object recognition accuracy of approximately 73% was achieved. The pose estimation results were reasonable but prompted further research. The results are comparable to what has been achieved using other suggested approaches such as Viewpoint Feature Histograms and Spin Images. / Dissertation (MEng)--University of Pretoria, 2013. / gm2014 / Electrical, Electronic and Computer Engineering / unrestricted

Pose estimation and tracking is essential for applications involving human controls. Specifically, as the primary operating tool for human activities, hand pose estimation plays a significant role in applications such as hand tracking, gesture recognition, human-computer interaction and VR/AR. As the field develops, there has been a trend to utilize deep learning to estimate the 2D/3D hand poses using color-based information without depth data. Within the depth-based as well as color-based approaches, the research community has primarily focused on single-hand scenarios in a localized/normalized coordinate system. Due to the fact that both hands are utilized in most applications, we propose to push the frontier by addressing two-hand pose estimation in the global coordinate system using only color information. Our first chapter introduces the first system capable of estimating global 3D joint locations for both hands via only monocular RGB input images. To enable training and evaluation of the learning-based models, we propose to introduce a large-scale synthetic 3D hand pose dataset Ego3DHands. As knowledge in synthetic data cannot be directly applied to the real-world domain, a natural two-hand pose dataset is necessary for real-world applications. To this end, we present a large-scale RGB-based egocentric hand dataset Ego2Hands in two chapters. In chapter 2, we address the task of two-hand segmentation/detection using images in the wild. In chapter 3, we focus on the task of two-hand 2D/3D pose estimation using real-world data. In addition to research in hand pose estimation, chapter 4 includes our work on interactive refinement that generalizes the backpropagating refinement technique for dense prediction models.

This project explores the understudied, yet important, case of human pose estimation in low-resolution images. This is done in the use-case of images with football players of known scale in the image. Human pose estimation can mainly be done in two different ways, the bottom-up method and the top-down method. This project explores the bottom-up method, which first finds body keypoints and then groups them to get the person, or persons, within the image. This method is generally faster and has been shown to have an advantage when there is occlusion or crowded scenes, but suffers from false positive errors. Low-resolution makes human pose estimation harder, due to the decreased information that can be extracted. Furthermore, the output heatmap risks becoming too small to correctly locate the keypoints. However, low-resolution human pose estimation is needed in many cases, if the camera has a low-resolution sensor or the person occupies a small portion of the image. Several neural networks are evaluated and, in conclusion, there are multiple ways to improve the current state of the art network HigherHRNet for lower resolution human pose estimation. Maintaining large feature maps through the network turns out to be crucial for low-resolution images and can be achieved by modifying the feature extractor in HigherHRNet. Furthermore, as the resolution decreases, the need for sub-pixel accuracy grows. To improve this, various heatmap encoding-decoding methods are investigated, and by using unbiased data processing, both heatmap encoding-decoding and coordinate system transformation can be improved. / Detta projekt utforskar det understuderade, men ändå viktiga, fallet med uppskattning av mänskliga poser i lågupplösta bilder. Detta görs i användningsområdet av bilder med fotbollsspelare av en förutbestämd storlek i bilden. Mänskliga poseuppskattningar kan huvudsakligen göras på två olika sätt, nedifrån-och-upp- metoden och uppifrån-och-ned-metoden. Detta projekt utforskar nedifrån-och- upp-metoden, som först hittar kroppsdelar och sedan grupperar dem för att få fram personen, eller personerna, i bilden. Denna metod är generellt sett snabbare och har visat sig vara fördelaktig i scenarion med ocklusion eller mycket folk, men lider av falska positiva felaktigheter. Låg upplösning gör uppskattning av mänskliga poser svårare, på grund av den minskade informationen som kan extraheras. Dessutom riskerar färgdiagramet att bli för liten för att korrekt lokalisera kroppsdelarna. Ändå behövs uppskattning av lågupplöst mänskliga poser i många fall, exempelvis om kameran har en lågupplöst sensor eller om personen upptar en liten del av bilden. Flera neurala nätverk utvärderas och sammanfattningsvis finns flera sätt att förbättra det nuvarande toppklassade nätverket HigherHRNet för uppskattning av mänskliga poser med lägre upplösning. Att bibehålla stora särdragskartor genom nätverket visar sig vara avgörande för lågupplösta bilder och kan uppnås genom att modifiera särdragsextraktorn i HigherHRNet. Dessutom, när upplösningen minskar, ökar behovet av subpixel-noggrannhet. För att förbättra detta undersöktes olika färgdiagram-kodning-avkodningsmetoder, och genom att använda opartisk databehandling kan både färgdiagram-kodning-avkodning och koordinatsystemtransformationen förbättras.