Motion capture(“MoCap”) has been used for a long time in the movie and videogame industries to animate digital characters. This technology commonly requires a studio and expensive stationary equipment. However, in recent years markerless MoCap has emerged. This is a technology that uses machine learning to estimate and reproduce the movements of humans. This technology can be used with a single video camera thus making it more accessible. This study relates to research on motion capture, machine learning and computer animation. The study examines a selection of markerless MoCap tools available on the market with amateurs and small businesses as target audiences. This to explore to which extent markerless MoCap for amateurs is suitable for use. The research questions asked in this study are: How well do these tools recreate motions from an animation? How are these results affected by aggravating circumstances? How do the results of the tools differ from each other? To explore these questions, a selection of five markerless MoCap services was made. These five services were then tested to study their performances in different aggravating circumstances. An original animation was created and used in these tests. The results from these tests were analyzed using a qualitative visual analysis and a numerical analysis of extreme values. The study found the tools could not accurately reproduce the animation they were given to process. The most prominent problem being that of depth perception, which resulted in the processed animations often deviating in depth. The services also had obvious problems with recreating arms. The study also found that some of the different aggravating circumstances affected the results more than others. The results of this study shows that markerless MoCap for amateurs still has development ahead of it before the technology can be considered an effective tool. / Motion Capture (“MoCap”) har länge använts inom film- och spelindustrin för att animera digitala karaktärer. MoCap i storskalig produktion kräver dock vanligtvis en studio och dyr utrustning. Men på senare år har Markerless MoCap vuxit fram. Det är en teknik som använder sig av maskininlärning för att estimera och avbilda en persons rörelser. Denna kan användas med enbart en videokamera vilket gör tekniken lättillgänglig. Denna studie relaterar till forskning som berör Motion Capture, 3D-datoranimation, AI och maskininlärning. Studien undersöker ett urval av Markerless MoCap-verktyg som finns tillgängliga allmänheten, med amatörer och småföretag som målgrupp. Detta i syfte att undersöka i vilken utsträckning markerless MoCap för amatörer är lämplig för bruk. Problemformuleringen i denna studie är: Hur väl återskapar programmen rörelserna från en animation? Hur påverkas detta resultat av försvårande omständigheter? Hur skiljer sig dessa programs resultat från varandra? För att undersöka dessa frågor gjordes ett urval av fem Markerless MoCap-verktyg. Dessa fem verktyg testades för att studera verktygens prestationer under olika försvårande omständigheter. En egenproducerad animation användes i dessa tester. Resultaten från dessa tester analyserades med en kvalitativ visuell analys och en numerisk analys av extremvärden. Studien fann att verktygen inte med precision kunde återge den animation de fått att avbilda. Tydligast var problemet med djupseendet, vilket resulterade i att de bearbetade animationerna ofta avvek i djupled. Verktygen hade också påtagliga problem med att avbilda armar. Studien fann även att vissa försvårande omständigheter hade större effekt än andra. Den här studiens resultat visar att Markerless MoCap för amatörer fortfarande har utveckling kvar innan tekniken kan betraktas som ett effektivt verktyg.

No description available.

No description available.

This thesis presents a framework for a hybrid model-free marker-less inertial-visual camera pose tracking with an integrated sensor fusion mechanism. The proposed solution addresses the fundamental problem of pose recovery in computer vision and robotics and provides an improved solution for wide-area pose tracking that can be used on mobile platforms and in real-time applications. In order to arrive at a suitable pose tracking algorithm, an in-depth investigation was conducted into current methods and sensors used for pose tracking. Preliminary experiments were then carried out on hybrid GPS-Visual as well as wireless micro-location tracking in order to evaluate their suitability for camera tracking in wide-area or GPS-denied environments. As a result of this investigation a combination of an inertial measurement unit and a camera was chosen as the primary sensory inputs for a hybrid camera tracking system. After following a thorough modelling and mathematical formulation process, a novel and improved hybrid tracking framework was designed, developed and evaluated. The resulting system incorporates an inertial system, a vision-based system and a recursive particle filtering-based stochastic data fusion and state estimation algorithm. The core of the algorithm is a state-space model for motion kinematics which, combined with the principles of multi-view camera geometry and the properties of optical flow and focus of expansion, form the main components of the proposed framework. The proposed solution incorporates a monitoring system, which decides on the best method of tracking at any given time based on the reliability of the fresh vision data provided by the vision-based system, and automatically switches between visual and inertial tracking as and when necessary. The system also includes a novel and effective self-adjusting mechanism, which detects when the newly captured sensory data can be reliably used to correct the past pose estimates. The corrected state is then propagated through to the current time in order to prevent sudden pose estimation errors manifesting as a permanent drift in the tracking output. Following the design stage, the complete system was fully developed and then evaluated using both synthetic and real data. The outcome shows an improved performance compared to existing techniques, such as PTAM and SLAM. The low computational cost of the algorithm enables its application on mobile devices, while the integrated self-monitoring, self-adjusting mechanisms allow for its potential use in wide-area tracking applications.

Enligt en rapport från trafikverket förekommer kollisioner vid väghållningsarbeten mellan väghållningsfordon och objekt täckta av väglag. Dessa trafikolyckor kan leda till personskador, skador på infrastruktur och skador på de inblandade väghållnings-fordonen. Som lösning på detta problem har möjligheten att visuellt markera de dolda objekten med förstärkt verklighet undersökts. Olika implementationer och metoder för användning av förstärkt verklighet studerades först för att få en bra upp-fattning om ämnet. En applikation utvecklades därefter till mobiltelefon med opera-tivsystemet Android i utvecklingsmiljön Unity. För förstärkt verklighet i applikat-ionen användes en natural feature tracking implementation av ARCore. Positioner-ingstester utfördes med Mobiltelefonens inbyggda GPS vilket visade en stor felmar-ginal. Applikationen utgår därför från en fast startpunkt inmätt med geodetisk mät-utrustning för ökad positioneringsnoggrannhet. För markering av de dolda objekten användes en lösning med cirkelbaserat skapande av tredimensionella objektmarkörer där cirklarnas radie utgick från startpositionen. Användning av applikationen gav va-rierande resultat beroende på den trafiksituation den används i och avståndet från startpositionen. Objektens position markeras tydligast i situationer där mobiltelefo-nen närmar sig det objekt som ska markeras på en väg i en riktning parallellt med cirkelns radie. Sämre tydlighet uppnåddes i situationer där mobiltelefonen närmar sig på en väg med en riktning parallell med cirkelns tangent eller på öppna ytor likt parkeringsplatser. Positioner för olika testobjekt mättes också med geodetisk mätut-rustning för hög precision för att få tillgång till en testmiljö där pålitligt data kunde hämtas upprepade gånger. Resultaten visar att den implementation av ARCore som finns i applikationen är känslig för avbrott i spårning av omgivningen och kan leda till fel i positionering. Ett fel i avståndsberäkningen finns också i programmet. Där-för är vidareutveckling och mer tester ett krav innan applikationen kan fungera i skarpt läge. / According to a report from Trafikverket collisions occur in road maintenance work with road maintenance vehicles and objects hidden by road conditions. These traffic accidents can lead to personal injury, damage to infrastructure and damage to the road maintenance vehicles involved. As a solution to this problem the possibility of visually marking the hidden objects with the use of augmented reality has been ex-amined. Different implementations and methods for use of augmented reality were first studied to get a good understanding of the subject. An application for mobile telephone was developed with the development platform Unity. The targeted oper-ating system for the mobile telephone was Android. A natural feature tracking imple-mentation of ARCore was used to bring features of augmented reality to the applica-tion. Tests were done to measure the precision of the mobile telephone’s GPS which showed a large margin for error. The application therefore uses a fixed start-ing location which has been measured with geodetic-measuring equipment for in-creased positioning accuracy. To visualize the position of the hidden objects a solu-tion with circle based creation of three-dimensional object markers was used where the radius of the circles originated from the starting position. Use of the application led to varied results which depended on the traffic situation and distance from the start position. The positions of the objects are marked more clearly in situations where the mobile phone is approaching the objects on a road and in a direction par-allel to the circle’s radius. Lower accuracy was generally achieved in situations where the mobile phone was approaching the objects on a road in a direction paral-lel to the circle’s tangent or in open areas like a parking lot. Positions for different test objects were also measured to achieve a test-environment where reliable data could be extracted repeatedly. The results of this study showed that the implemen-tation of ARCore used in this application is sensitive to disruption in the real-world registration of the mobile telephone’s position, which can lead to errors in position-ing. An error in calculating the distance to the objects also exists in the application. Therefore, before the application can be used in a real-life situations further devel-opment and tests are required.

Nous nous intéressons à l'acquisition automatique de mouvements 3D de personnes. Cette opération doit être réalisée sans un équipement spécialisé (marqueurs ou habillage spécifique), pour rendre son utilisation générale, sous la contrainte du temps réel. Pour répondre à ces questions, nous sommes amenés à traiter de la reconstruction et l'analyse de la forme 3D. Concernant le problème de reconstruction 3D en temps réel d'entités en mouvement à partir de plusieurs vues, les approches existantes font souvent appel à des calculs complexes incompatibles avec la contrainte du temps réel. Les approches du type SFS offrent un compromis intéressant entre efficacité algorithmique et précision. Ces dernières utilisent les silhouettes issues de chaque caméra pour proposer un volume englobant des objets. Cependant elles nécessitent un environnement particulièrement contraint, dont le placement minutieux des caméras. Les travaux présentés dans ce manuscrit généralisent l'utilisation des approches SFS à des environnements peu contrôlés. L'acquisition du mouvement revient à déterminer les paramètres offrant la meilleure corrélation entre le modèle et la reconstruction 3D. Notre objectif étant le suivi temps réel, nous proposons des méthodes qui offrent la précision requise et le temps réel. Couplé à un suivi temporel par filtre de Kalman, à un recalage d'objets géométriques simples (ellipsoïdes, sphères, etc.), nous proposons un système temps réel, offrant une erreur de l'ordre de 6%.De par sa robustesse, il permet le suivi simultané de plusieurs personnes, même lors de contacts. Les résultats obtenus ouvrent des perspectives à un transfert vers des applications grand public / We aim at automatically capturing 3D motion of persons without markers. To make it flexible, and to consider interactive applications, we address real-time solution, without specialized instrumentation. Real-time body estimation and shape analyze lead to home motion capture application. We begin by addressing the problem of 3D real-time reconstruction of moving objects from multiple views. Existing approaches often involve complex computation methods, making them incompatible with real-time constraints. Shape-From-Silhouette (SFS) approaches provide interesting compromise between algorithm efficiency and accuracy. They estimate 3D objects from their silhouettes in each camera. However they require constrained environments and cameras placement. The works presented in this document generalize the use of SFS approaches to uncontrolled environments. The main methods of marker-less motion capture, are based on parametric modeling of the human body. The acquisition of movement goal is to determine the parameters that provide the best correlation between the model and the 3D reconstruction.The following approaches, more robust, use natural markings of the body extremities: the skin. Coupled with a temporal Kalman filter, a registration of simple geometric objects, or an ellipsoids' decomposition, we have proposed two real-time approaches, providing a mean error of 6%. Thanks to the approach robustness, it allows the simultaneous monitoring of several people even in contacts. The results obtained open up prospects for a transfer to home applications

Although upper limb motor impairments are common, the primary tools for assessing and tracking these impairments in a clinical setting are subjective, qualitative rating scales that lack resolution and repeatability. Markerless motion capture technology has the potential to greatly improve clinical assessment by providing quick, low-cost, and accurate tools to objectively quantify motor deficits. Here we lay some of the groundwork necessary to enable markerless motion capture systems to be used in clinical settings. First, we adapted five motor tests common in clinical assessments so they can be administered via markerless motion capture. We implemented these modified tests using a particular motion capture sensor (Leap MotionTM Controller, hereafter referred to as the Leap Motion sensor) and administered the tests to 100 healthy subjects to evaluate the feasibility of administrating these tests via markerless motion capture. Second, to determine the ability of the Leap Motion sensor to accurately measure tremor, we characterized the frequency response of the Leap Motion sensor. During the administration of the five modified motor tests on 100 healthy subjects, the subjects had little trouble interfacing with the Leap Motion sensor and graphical user interface, performing the tasks with ease. The Leap Motion sensor maintained an average sampling rate above 106 Hz across all subjects during each of the five tests. The rate of adverse events caused by the Leap Motion sensor (mainly jumps in time or space) was generally below 1%. In characterizing the frequency response of the Leap Motion sensor, we found its bandwidth to vary between 1.7 and 5.5 Hz for actual tremor amplitudes above 1.5 mm, with larger bandwidth for larger amplitudes. To improve the accuracy of tremor measurements, we provide the magnitude ratios that can be used to estimate the actual amplitude of the oscillations from the measurements by the Leap Motion sensor. These results suggest that markerless motion capture systems are on the verge of becoming suitable for routine clinical use, but more work is necessary to further improve the motor tests before they can be administered via markerless motion capture with sufficient robustness for clinical settings.

The aim of this master's thesis was to develop an application, which would allow its users to program robotic actions with the help the augmented reality. The application is of demonstrative character and is made with the goal of intuitive handling and good integration of the augmented reality. This experimental application enables users to design a program for a robot using visual instructions, conditions and links and to test it by visualizing the passage through the program. The application is implemented with the use of Unity3D and the AR Foundation technology. The result was tested by a group of volunteers, whose feedback can be considered generally positive.

Tato práce se zaměřuje na technologii Cave Automatic Virtual Environment a konkrétně pak na využití principů rozšířené reality v tomto prostředí. Dává si za cíl odpovědět na otázku, zdali je možné použít v prostředí CAVE existující frameworky pro rozšířenou realitu, konkrétně ty, pracující na platformě iOS. Hlavní důraz je kladen na rozpoznávání markerů v tomto prostředí a na zvýšení přesnosti jejich rozpoznání. Práce odpovídá na množství otázek z této oblasti, jako jaké markery je vhodné použít, jaké jsou omezení a největší obtíže. Výstupem je demonstrační aplikace, pracující na platformě iOS, která v je prostředí CAVE otestovaná a plně použitelná. Tato aplikace by měla vylepšit uživatelský vjem z prostředí CAVE tím, že mu poskytne dodatečné informace a také základní možnosti interakce se zobrazenými objekty.

Augmented reality has been on the rise for some time now and begun making its way onto the mobile market for both IOS and Android. In 2017 Apple released ARKit for IOS which is a software development kit for developing augmented reality applications. To counter this, Google released their own variant called ARCore on the 1st of march 2018. ARCore is also a software development kit for developing augmented reality applications but made for the Android, Unity and Unreal platforms instead. Since ARCore is released recently it is still unknown what particular limitations may exist for it. The purpose of this paper is give an indication to companies and developers about ARCore’s potential limitations. The goal with this paper and work is to map how well ARCore works during different circumstances, and in particular, how its feature detection works and behaves. A quantitative research was done with the usage of the case study method. Various tests were performed with a modified test-application supplied by Google. The tests included testing how ARCore’s feature detection, the process that analyzes the environment presented to the application. This which enables the user of an application to place a virtual object on the physical environment. The tests were done to see how ARCore works during different light levels, different types of surfaces, different angles and the difference between having the device stationary or moving. From the testing that were done some conclusions could be drawn about the light levels, surfaces and differences between a moving and stationary device. More research and testing following these principles need to be done to draw even more conclusions of the system and its limitations. How these should be done is presented and discussed. / Forstarkt verklighet (augmented reality) har stigit under en tid och börjat ta sig in på mobilmarknaden for både IOS och Android. År 2017 släppte Apple ARKit för IOS vilket är en utvecklingsplattform för att utveckla applikationer inom förstärkt verklighet. Som svar på detta så slappte Google sin egna utvecklingsplattform vid namn ARCore, som släpptes den 1 mars 2018. ARCore är också en utvecklingsplattform för utvecklandet av applikationer inom förstarkt verklighet men istället inom Android, Unity och Unreal. Sedan ARCore släpptes nyligen är det fortfarande okant vilka särskilda begränsningar som kan finnas för det. Syftet med denna avhandling är att ge företag och utvecklare en indikation om ARCores potentiella begränsningar. Målet med denna avhandling och arbete är att kartlägga hur väl ARCore fungerar under olika omstandigheter, och i synnerhet hur dess struktursdetektor fungerar och beter sig. En kvantitativ forskning gjordes med användning av fallstudie metoden. Olika tester utfördes med en modifierad test-applikation från Google. Testerna inkluderade testning av hur ARCores struktursdetektor, processen som analyserar miljön runt om sig, fungerar. Denna teknik möjliggor att användaren av en applikation kan placera ett virtuellt objekt på den fysiska miljön. Testen innebar att se hur ARCore arbetar under olika ljusnivåer, olika typer av ytor, olika vinklar och skillnaden mellan att ha enheten stationär eller rör på sig. Från testningen som gjordes kan man dra några slutsatser om ljusnivåer, ytor och skillnader mellan en rörlig och stationar enhet. Mer forskning och testning enligt dessa principer måste göras för att dra ännu mer slutsatser av systemet och dess begränsningar. Hur dessa ska göras presenteras och diskuteras.