No description available.

В области компьютерного зрения оценка позы человека приобретает все большее значение. Это одна из самых привлекательных областей исследований, и она вызывает большой интерес благодаря своей полезности и гибкости в самых разных областях, включая здравоохранение, игры, дополненную реальность, виртуальные тренировки и спорт. На ряду с этим люди все чаще начинают заниматься спортом. А в спорте травмы неизбежны. В данной статье предлагается приложение для оценки выполнения фитнес-упражнений, которое контролирует правильность техники и дает обратную связь по ее исправлению, что помогает уменьшить травматизм при занятиях. Предварительно обученная модель MediaPipe использовалась для оценки поз, по результатам которой вычисляются углы между конкретными суставами. / In the field of computer vision, human pose estimation is becoming increasingly important. This is one of the most attractive areas of research, and it is of great interest due to its usefulness and flexibility in a wide variety of fields, including healthcare, games, augmented reality, virtual training, and sports. Along with this, people are increasingly starting to do sports. And in sports, injuries are inevitable. This article offers an application for evaluating the performance of fitness exercises, which monitors the correctness of the technique and gives feedback on its correction, which helps to reduce injuries during classes. A pre-trained MediaPipe model was used to evaluate poses, based on the results of which the angles between specific joints are calculated.

The deep learning technique Human Pose Estimation (or Human Keypoint Detection) is a promising field in tracking a person and identifying its posture. As posture and balance are two closely related concepts, the use of human pose estimation could be applied to fall prevention. By deriving the location of a persons Center of Mass and thereafter its Center of Pressure, one can evaluate the balance of a person without the use of force plates or sensors and solely using cameras. In this study, a human pose estimation model together with a predefined human weight distribution model were used to extract the location of a persons Center of Pressure in real time. The proposed method utilized two different methods of acquiring depth information from the frames - stereoscopy through two RGB-cameras and with the use of one RGB-depth camera. The estimated location of the Center of Pressure were compared to the location of the same parameter extracted while using the force plate Wii Balance Board. As the proposed method were to operate in real-time and without the use of computational processor enhancement, the choice of human pose estimation model were aimed to maximize software input/output speed. Thus, three models were used - one smaller and faster model called Lightweight Pose Network, one larger and accurate model called High-Resolution Network and one model placing itself somewhere in between the two other models, namely Pose Residual Network. The proposed method showed promising results for a real-time method of acquiring balance parameters. Although the largest source of error were the acquisition of depth information from the cameras. The results also showed that using a smaller and faster human pose estimation model proved to be sufficient in relation to the larger more accurate models in real-time usage and without the use of computational processor enhancement. / Djupinlärningstekniken Kroppshållningsestimation är ett lovande medel gällande att följa en person och identifiera dess kroppshållning. Eftersom kroppshållning och balans är två närliggande koncept, kan användning av kroppshållningsestimation appliceras till fallprevention. Genom att härleda läget för en persons tyngdpunkt och därefter läget för dess tryckcentrum, kan utvärdering en persons balans genomföras utan att använda kraftplattor eller sensorer och att enbart använda kameror. I denna studie har en kroppshållningsestimationmodell tillsammans med en fördefinierad kroppsviktfördelning använts för att extrahera läget för en persons tryckcentrum i realtid. Den föreslagna metoden använder två olika metoder för att utvinna djupseende av bilderna från kameror - stereoskopi genom användning av två RGB-kameror eller genom användning av en RGB-djupseende kamera. Det estimerade läget av tryckcentrat jämfördes med läget av samma parameter utvunnet genom användning av tryckplattan Wii Balance Board. Eftersom den föreslagna metoden var ämnad att fungera i realtid och utan hjälp av en GPU, blev valet av kroppshållningsestimationsmodellen inriktat på att maximera mjukvaruhastighet. Därför användes tre olika modeller - en mindre och snabbare modell vid namn Lightweight Pose Network, en större och mer träffsäker modell vid namn High-Resolution Network och en model som placerar sig någonstans mitt emellan de två andra modellerna gällande snabbhet och träffsäkerhet vid namn Pose Resolution Network. Den föreslagna metoden visade lovande resultat för utvinning av balansparametrar i realtid, fastän den största felfaktorn visade sig vara djupseendetekniken. Resultaten visade att användning av en mindre och snabbare kroppshållningsestimationsmodellen påvisar att hålla måttet i jämförelse med större och mer träffsäkra modeller vid användning i realtid och utan användning av externa dataprocessorer.

Interaktiv projicerad förstärkt verklighet är ett delområde inom projicerad förstärktverklighet, där interaktiviteten handlar om att projicera virtuelldata på en entitet somär rörlig. Denna projektion kan åstadkommas genom att använda en kalibrerad projektor-djupkamerasystem som detekterar entitet med hjälp av datorseende. Dettainteraktiva system har varierande antal tillämpningsområden, dock framkommer enkritisk problemformulering, vilket är noggrannheten för dessa system. Noggrannheten i detta fall är hur korrekt projektionen sker på den specifika entiteten, noggrannheten är därför en viktig aspekt för att validera ifall vissa tillämpningar är möjliga implementera. Lösningen för detta problem är att implementera interaktiv projicerad förstärkt verklighet och utföra prototyptester med det implementerade systemet och sedan vidare analysera noggrannheten med testdata. Prototypen kalibrerasmed befintliga verktyg från tidigare studier, detekterar med hjälp av positionsuppskattning och kan sedan projicera punkter på specifika kroppsdelar som även följerpersonen vid rörelse. Resultatet som framkom blev en prototyp som testades för noggrannheten. Testernasker med hjälp av datorseende för att extrahera mätdata såsom projicerade punktenoch förväntade punkten. Från analysen av testdata framkom det att projektionensnoggrannhet är lämplig för tillämpningar som inte kräver exceptionell noggrannhet,såsom nöje, konst, spel och med mera. Ytterligare forskning krävs för användningsområden som kräver exceptionell noggrannhet som tillämpningar inom sjukvård ochkirurgi. / Interactive projected augmented reality is a subfield within projected augmented reality, where the interactivity is about projecting virtual data onto an entity that canpotentially be in movement. This projection can be accomplished by using a calibrated projector-depth camera system that detects entities using computer vision.This interactive system has a varying number of application areas; however, a criticalproblem emerges, which is the accuracy of these systems. The accuracy in this caseis how correctly the projection takes place on the specific entity, the accuracy istherefore an important aspect to validate if certain applications are possible to implement correctly. The solution for this problem is by implementing interactive projectedaugmented reality and perform prototype tests with the implemented system andthen further analyzing the accuracy with test data. The prototype is calibrated withexisting tools from previous studies, detects using pose detection, which can thenproject points on specific body parts that also follows the person during movement.The result that got developed was a prototype that was tested for accuracy. The testsare done using computer vision to extract measurement data such as the projectedpoint and the expected point. The result from the analysis of the test data showedthat the accuracy of the projection is suitable for applications that do not requireexceptional accuracy, such as entertainment, art, games and so on. Further research is required for applications that require exceptional accuracy such ashealthcare and surgical applications.

Autonomous navigation for ground vehicles has many challenges. Autonomous systems must be able to self-localise, avoid obstacles and determine navigable surfaces. This thesis studies several aspects of autonomous navigation with a particular emphasis on vision, motivated by it being a primary component for navigation in many high-level biological organisms.  The key problem of self-localisation or pose estimation can be solved through analysis of the changes in appearance of rigid objects observed from different view points. We therefore describe a system for structure and motion estimation for real-time navigation and obstacle avoidance. With the explicit assumption of a calibrated camera, we have studied several schemes for increasing accuracy and speed of the estimation.The basis of most structure and motion pose estimation algorithms is a good point tracker. However point tracking is computationally expensive and can occupy a large portion of the CPU resources. In thisthesis we show how a point tracker can be implemented efficiently on the graphics processor, which results in faster tracking of points and the CPU being available to carry out additional processing tasks.In addition we propose a novel view interpolation approach, that can be used effectively for pose estimation given previously seen views. In this way, a vehicle will be able to estimate its location by interpolating previously seen data.Navigation and obstacle avoidance may be carried out efficiently using structure and motion, but only whitin a limited range from the camera. In order to increase this effective range, additional information needs to be incorporated, more specifically the location of objects in the image. For this, we propose a real-time object recognition method, which uses P-channel matching, which may be used for improving navigation accuracy at distances where structure estimation is unreliable. / Diplecs

This thesis aimed to assess the feasibility of using an off-the-shelf virtual reality tracking system as a low cost precision pose estimation solution for robotic operations in both indoor and outdoor environments. Such a tracking solution has the potential of assisting critical operations related to planetary exploration missions, parcel handling/delivery, and wildfire detection/early warning systems. The boom of virtual reality experiences has accelerated the development of various low-cost, precision indoor tracking technologies. For the purpose of this thesis we choose to adapt the SteamVR Lighthouse system developed by Valve, which uses photo-diodes on the trackers to detect the rotating IR laser sheets emitted from the anchored base stations, also known as lighthouses. Some previous researches had been completed using the first generation of lighthouses, which has a few limitations on communication from lighthouses to the tracker. A NASA research has cited poor tracking performance under sunlight. We choose to use the second generation lighthouses which has improved the method of communication from lighthouses to the tracker, and we performed various experiments to assess their performance outdoors, including under sunlight. The studies of this thesis have two stages, the first stage focused on a controlled, indoor environment, having an Unmanned Aerial Vehicle (UAS) perform repeatable flight patterns and simultaneously tracked by the Lighthouse and a reference indoor tracking system, which showed that the tracking precision of the lighthouse is comparable to the industrial standard indoor tracking solution. The second stage of the study focused on outdoor experiments with the tracking system, comparing UAS flights between day and night conditions as well as positioning accuracy assessments with a CNC machine under indoor and outdoor conditions. The results showed matching performance between day and night while still comparable to industrial standard indoor tracking solution down to centimeter precision, and matching simulated CNC trajectory down to millimeter precision. There is also some room for improvement in regards to the experimental method and equipment used, as well as improvements on the tracking system itself needed prior to adaptation in real-world applications. / Master of Science / This thesis aimed to assess the feasibility of using an off-the-shelf virtual reality tracking system as a low cost precision pose estimation solution for robotic operations in both indoor and outdoor environments. Such a tracking solution has the potential of assisting critical operations related to planetary exploration missions, parcel handling/delivery, and wildfire detection/early warning systems. The boom of virtual reality experiences has accelerated the development of various low-cost, precision indoor tracking technologies. For the purpose of this thesis we choose to adapt the SteamVR Lighthouse system developed by Valve, which uses photo-diodes on the trackers to detect the rotating IR laser sheets emitted from the anchored base stations, also known as lighthouses. Some previous researches had been completed using the first generation of lighthouses, which has a few limitations on communication from lighthouses to the tracker. A NASA research has cited poor tracking performance under sunlight. We choose to use the second generation lighthouses which has improved the method of communication from lighthouses to the tracker, and we performed various experiments to assess their performance outdoors, including under sunlight. The studies of this thesis have two stages, the first stage focused on a controlled, indoor environment, having an Unmanned Aerial Vehicle (UAS) perform repeatable flight patterns and simultaneously tracked by the Lighthouse and a reference indoor tracking system, which showed that the tracking precision of the lighthouse is comparable to the industrial standard indoor tracking solution. The second stage of the study focused on outdoor experiments with the tracking system, comparing UAS flights between day and night conditions as well as positioning accuracy assessments with a CNC machine under indoor and outdoor conditions. The results showed matching performance between day and night while still comparable to industrial standard indoor tracking solution down to centimeter precision, and matching simulated CNC trajectory down to millimeter precision. There is also some room for improvement in regards to the experimental method and equipment used, as well as improvements on the tracking system itself needed prior to adaptation in real-world applications.

<p dir="ltr">Object Recognition and Retrieval is a fundamental problem in Computer Vision that involves recognizing objects and retrieving similar object images through visual queries. While deep metric learning is commonly employed to learn image embeddings for solving such problems, the representations learned using existing methods are not robust to changes in viewpoint, pose, and object state, especially for fine-grained recognition and retrieval tasks. To overcome these limitations, this dissertation aims to learn robust object representations that remain invariant to such transformations for fine-grained tasks. First, it focuses on learning dual pose-invariant embeddings to facilitate recognition and retrieval at both the category and finer object-identity levels by learning category and object-identity specific representations in separate embedding spaces simultaneously. For this, the PiRO framework is introduced that utilizes an attention-based dual encoder architecture and novel pose-invariant ranking losses for each embedding space to disentangle the category and object representations while learning pose-invariant features. Second, the dissertation introduces ranking losses that cluster multi-view images of an object together in both the embedding spaces while simultaneously pulling the embeddings of two objects from the same category closer in the category embedding space to learn fundamental category-specific attributes and pushing them apart in the object embedding space to learn discriminative features to distinguish between them. Third, the dissertation addresses state-invariance and introduces a novel ObjectsWithStateChange dataset to facilitate research in recognizing fine-grained objects with state changes involving structural transformations in addition to pose and viewpoint changes. Fourth, it proposes a curriculum learning strategy to progressively sample object images that are harder to distinguish for training the model, enhancing its ability to capture discriminative features for fine-grained tasks amidst state changes and other transformations. Experimental evaluations demonstrate significant improvements in object recognition and retrieval performance compared to previous methods, validating the effectiveness of the proposed approaches across several challenging datasets under various transformations.</p>

Ice hockey is a sport whose athletes are at high risk for traumatic head injuries due to the violence of potential impacts with other athletes, ice, or glass during games. In order to develop the best protective strategies for the players, it is necessary to have a deep understanding of accident mechanisms during ice hockey games. Accident reconstructions using the finite element (FE) method are a way to perform a systematic analysis of impact cases, but require input data on the circumstances of the accidents. Thus, this project focused on finding a way to extract the position and velocity of the players involved from readily available videos of ice hockey accidents using motion tracking methods. This project included two parts: pose estimation and velocity estimation. The pose estimation aimed to align a human body model (HBM) with the players' poses and the key steps included estimating 2D joints from impact images, estimating the players' 3D poses, skeleton inferencing, and aligning the results with the baseline HBM via pelvic registration. The velocity estimation defined the initial conditions for simulating the collision and key steps included identifying the players' 2D joints across impact video frames, tracking of the players using a simplified pelvis projection on the rink plane, and estimating the players’ velocity using homography to identify their position on the ice hockey rink. Then, both parts were applied to accident cases from a video database of collisions that occurred during a hockey league season. The cases in which the pipeline was fully applied ultimately resulted in LS-DYNA positioning files for the Total Human Model for Safety (THUMS) model, and problematic cases were used to get an overview of the limits of the chosen methodology. Said limitations were mostly linked to the quality of the source videos, which is highly dependent on the source of the videos and possibly not controllable. Due to this, selection criteria are required, such as checking the blurriness and quality of the videos and the viewing angles to ensure as few occlusions as possible. Overall, this project resulted in a working semi-automatic pipeline for pose and velocity estimation in contact sports collisions, as well as a first set of personalized input information that should allow the reconstruction of ice hockey accidents using FE simulations. / Ishockey är en sport vars utövare löper stor risk att drabbas av traumatiska huvudskador på grund av de våldsamma potentiella kollisionerna med andra utövare, is eller glas under matcherna. För att kunna utveckla de bästa skyddsstrategierna för spelarna är det nödvändigt att ha en djup förståelse för olycksmekanismerna under ishockeymatcher. Olycksrekonstruktioner med hjälp av finita elementmetoden är ett sätt att utföra en systematisk analys av kollisionsfall, men kräver indata om omständigheterna kring olyckorna. Detta projekt fokuserade därför på att hitta ett sätt att extrahera de inblandade spelarnas position och hastighet från lättillgängliga videor av ishockeyolyckor med hjälp av rörelsespårningsmetoder. Projektet bestod av två delar: poseuppskattning och hastighetsuppskattning. Poseuppskattningen syftade till att anpassa en humanmodell till spelarnas poser och de viktigaste stegen omfattade uppskattning av 2D-leder från kollisionsbilder, uppskattning av spelarnas 3D-poser, skelettinferens och anpassning av resultaten till baslinjen HBM via bäckenregistrering. Hastighets-uppskattningen definierade de initiala villkoren för simulering av kollisionen och viktiga steg inkluderade identifiering av spelarnas 2D-led i videobilder av kollisionen, spårning av spelarna med hjälp av en förenklad bäckenprojektion på rinkplanet och uppskattning av spelarnas hastighet med hjälp av homografi för att identifiera deras position på ishockeyrinken. Därefter tillämpades båda delarna på olycksfall från en videodatabas med kollisioner som inträffade under en säsong i en hockeyliga. De fall där pipelinen tillämpades fullt ut resulterade slutligen i LS-DYNA-positioneringsfiler, och problematiska fall användes för att få en överblick över gränserna för den valda metoden. Begränsningarna var främst kopplade till kvaliteten på källvideorna, som är starkt beroende av källan till videorna och eventuellt inte kan kontrolleras. På grund av detta krävs urvalskriterier, t.ex. kontroll av videornas oskärpa och kvalitet samt betraktningsvinklar för att säkerställa så få ocklusioner som möjligt. Sammantaget resulterade detta projekt i en fungerande halvautomatisk pipeline för pose- och hastighetsuppskattning vid kollisioner i kontaktsporter, samt en första uppsättning personlig indatainformation som bör möjliggöra rekonstruktion av ishockeyolyckor med hjälp av simulering med finita element.

Diplomová práce je zaměřena na problematiku detekce a sledování polohy hlavy v obraze jako jednu s možností jak zlepšit možnosti interakce mezi počítačem a člověkem. Hlavním přínosem diplomové práce je využití inovativních hardwarových a softwarových technologií jakými jsou Microsoft Kinect, Point Cloud Library a CImg Library. Na úvod je představeno shrnutí předchozích prací na podobné téma. Následuje charakteristika a popis databáze, která byla vytvořena pro účely diplomové práce. Vyvinutý systém pro detekci a sledování polohy hlavy je založený na akvizici 3D obrazových dat a registračním algoritmu Iterative Closest Point. V závěru diplomové práce je nabídnuto hodnocení vzniklého systému a jsou navrženy možnosti jeho budoucího zlepšení.

Une vidéo est une source particulièrement riche en informations. Parmi tous les objets que nous pouvons y trouver, les visages humains sont assurément les plus saillants, ceux qui attirent le plus l’attention des spectateurs. Considérons une séquence vidéo dont chaque trame contient un ou plusieurs visages en mouvement. Ils peuvent appartenir à des personnes connues ou qui apparaissent de manière récurrente dans la vidéo Cette thèse a pour but de créer une méthodologie afin d’extraire une ou plusieurs images de visage en vue d’appliquer, par la suite, un algorithme de reconnaissance du visage. La principale hypothèse de cette thèse réside dans le fait que certains exemplaires d’un visage sont meilleurs que d’autres en vue de sa reconnaissance. Un visage est un objet 3D non rigide projeté sur un plan pour obtenir une image. Ainsi, en fonction de la position relative de l’objectif par rapport au visage, l’apparence de ce dernier change. Considérant les études sur la reconnaissance de visages, on peut supposer que les exemplaires d’un visage, les mieux reconnus sont ceux de face. Afin d’extraire les exemplaires les plus frontaux possibles, nous devons d’une part estimer la pose de ce visage. D’autre part, il est essentiel de pouvoir suivre le visage tout au long de la séquence. Faute de quoi, extraire des exemplaires représentatifs d’un visage perd tout son sens. Les travaux de cette thèse présentent trois parties majeures. Dans un premier temps, lorsqu’un visage est détecté dans une séquence, nous cherchons à extraire position et taille des yeux, du nez et de la bouche. Notre approche se base sur la création de cartes d’énergie locale principalement à direction horizontale. Dans un second temps, nous estimons la pose du visage en utilisant notamment les positions relatives des éléments que nous avons extraits. Un visage 3D a trois degrés de liberté : le roulis, le lacet et le tangage. Le roulis est estimé grâce à la maximisation d’une fonction d’énergie horizontale globale au visage. Il correspond à la rotation qui s’effectue parallèlement au plan de l’image. Il est donc possible de le corriger pour qu’il soit nul, contrairement aux autres rotations. Enfin, nous proposons un algorithme de suivi de visage basé sur le suivi des yeux dans une séquence vidéo. Ce suivi repose sur la maximisation de la corrélation des cartes d’énergie binarisées ainsi que sur le suivi des éléments connexes de cette carte binaire. L’ensemble de ces trois méthodes permet alors tout d’abord d’évaluer la pose d’un visage qui se trouve dans une trame donnée puis de lier tous les visages d’une même personne dans une séquence vidéo, pour finalement extraire plusieurs exemplaires de ce visage afin de les soumettre à un algorithme de reconnaissance du visage. / The aim of this thesis is to create a methodology in order to extract one or a few representative face images of a video sequence with a view to apply a face recognition algorithm. A video is a media particularly rich. Among all the objects present in the video, human faces are, for sure, the most salient objects. Let us consider a video sequence where each frame contains a face of the same person. The primary assumption of this thesis is that some samples of this face are better than the others in terms of face recognition. A face is a non-rigid 3D object that is projected on a plan to form an image. Hence, the face appearance changes according to the relative positions of the camera and the face. Many works in the field of face recognition require faces as frontal as possible. To extract the most frontal face samples, on the one hand, we have to estimate the head pose. On the other hand, tracking the face is also essential. Otherwise, extraction representative face samples are senseless. This thesis contains three main parts. First, once a face has been detected in a sequence, we try to extract the positions and sizes of the eyes, the nose and the mouth. Our approach is based on local energy maps mainly with a horizontal direction. In the second part, we estimate the head pose using the relative positions and sizes of the salient elements detected in the first part. A 3D face has 3 degrees of freedom: the roll, the yaw and the pitch. The roll is estimated by the maximization of a global energy function computed on the whole face. Since this roll corresponds to the rotation which is parallel to the image plan, it is possible to correct it to have a null roll value face, contrary to other rotations. In the last part, we propose a face tracking algorithm based on the tracking of the region containing both eyes. This tracking is based on the maximization of a similarity measure between two consecutive frames. Therefore, we are able to estimate the pose of the face present in a video frame, then we are also able to link all the faces of the same person in a video sequence. Finally, we can extract several samples of this face in order to apply a face recognition algorithm on them.