No description available.

Today, there is an increasing demand for smart robots that can make decisions on their own and cooperate with humans in changing environments. The application areas for robotic arms with camera vision are likely to increase in the future of artificial intelligence as algorithms become more adaptable and intelligent than ever. The purpose of this bachelor’s thesis is to develop a robotic arm that recognises arbitrarily placed objects with camera vision and has the ability to pick and place the objects when they appear in unpredictable positions. The robotic arm has three degrees of freedom and the construction is modularised and 3D-printed with respect to maintenance, but also in order to be adaptive to new applications. The camera vision sensor is integrated in an external camera tripod with its field of view over the workspace. The camera vision sensor recognises objects through colour filtering and it uses an edge detection algorithm to return measurements of detected objects. The measurements are then used as input for the inverse kinematics, that calculates the rotation of each stepper motor. Moreover, there are three different angular potentiometers integrated in each axis to regulate the rotation by each stepper motor. The results in this thesis show that the robotic arm is able to pick up to 90% of the detected objects when using barrel distortion correction in the algorithm. The findings in this thesis is that barrel distortion, that comes with the camera lens, significantly impacts the precision of the robotic arm and thus the results. It can also be stated that the method for barrel distortion correction is affected by the geometry of detected objects and differences in illumination over the workspace. Another conclusion is that correct illumination is needed in order for the vision sensor to differentiate objects with different hue and saturation. / Idag ökar efterfrågan på smarta robotar som kan ta egna beslut och samarbeta med människor i föränderliga miljöer. Tillämpningsområdena för robotar med kamerasensorer kommer sannolikt att öka i en framtid av artificiell intelligens med algoritmer som blir mer intelligenta och anpassningsbara än tidigare. Syftet med detta kandidatexamensarbete är att utveckla en robotarm som, med hjälp av en kamerasensor, kan ta upp och sortera godtyckliga objekt när de uppträder på oförutsägbara positioner. Robotarmen har tre frihetsgrader och hela konstruktionen är 3D-printad och modulariserad för att vara underhållsvänlig, men också anpassningsbar för nya tillämpningsområden. Kamerasensorn ¨ar integrerad i ett externt kamerastativ med sitt synfält över robotarmens arbetsyta. Kamerasensorn detekterar objekt med hjälp av en färgfiltreringsalgoritm och returnerar sedan storlek, position och signatur för objekten med hjälp av en kantdetekteringsalgoritm. Objektens storlek används för att kalibrera kameran och kompensera för den radiella förvrängningen hos linsen. Objektens relativa position används sedan till invers kinematik för att räkna ut hur mycket varje stegmotor ska rotera för att erhålla den önskade vinkeln på varje axel som gör att gripdonet kan nå det detekterade objektet. Robotarmen har även tre olika potentiometrar integrerade i varje axel för att reglera rotationen av varje stegmotor. Resultaten i denna rapport visar att robotarmen kan detektera och plocka upp till 90% av objekten när kamerakalibrering används i algoritmen. Slutsatsen från rapporten är att förvrängningen från kameralinsen har störst påverkan på robotarmens precision och därmed resultatet. Det går även att konstatera att metoden som används för att korrigera kameraförvrängningen påverkas av geometrin samt orienteringen av objekten som ska detekteras, men framför allt variationer i belysning och skuggor över arbetsytan. En annan slutsats är att belysningen över arbetsytan är helt avgörande för om kamerasensorn ska kunna särskilja objekt med olika färgmättad och nyans.

Health is a fundamental human right. To increase global health, research in the medical sector is of great importance. Decreasing time consumption of biomedical testing could accelerate the research and development of new drugs and vaccines. This could be achieved by automation of biomedical analysis, using computerized methods. In order to perform analysis on pictures of biomedical tests, it is important to identify the area of interest (AOI) of the test. For example, cells and bacteria are commonly grown in petri dishes, in this case the AOI is the bottom area of the dish, since this is where the object of analysis is located.This study was performed with the aim to compare a few computerized methods for identifying the AOI in pictures of biomedical tests. In the study, biomedical images from a testing method called ELISpot have been used. ELISpot uses plates with up to 96 circular wells, where pictures of the separate wells were used in order to find the AOI corresponding to the bottom area of each well. The focus has been on comparing the performance of three edge detection methods. More specifically, their ability to accurately detect the edges of the well. Furthermore, a method for identifying a circle based on the detected edges was used to specify the AOI.The study shows that methods using second order derivatives for edge detection, gives the best results regarding to robustness.

This study has put three different object detecting techniques to the test. The goal was to investigate small and fast-moving objects to see which technique’s performance is most suitable within the sports of Padel. The study aims to cover and explain different affecting conditions that could cause better but also worse performance for small and fast object detection. The three techniques use different approaches for detecting one or multiple objects and could be a guideline for future object detection development. The proposed techniques utilize background histogram calculation, HSV masking with edge detection and DNN frameworks together with the COCO dataset. The process is tested through outdoor video footage across all techniques to generate data, which indicates that Canny edge detection is a prominent suggestion for further research given its high detection rate. However, YOLO shows excellent potential for multiple object detection at a very high confidence grade, which provides reliable and accurate detection of a targeted object. This study’s conclusion is that depending on what the end purpose aims to achieve, Canny and YOLO have potential for future small and fast object detection.

With the growth of computer power, Digital Image Processing plays a more and more important role in the modern world, including the field of industry, medical, communications, spaceflight technology etc. There is no clear definition how to divide the digital image processing, but normally, digital image processing includes three main steps: low-level, mid-level and highlevel processing. Low-level processing involves primitive operations, such as: image preprocessing to reduce the noise, contrast enhancement, and image sharpening. Mid-level processing on images involves tasks such as segmentation (partitioning an image into regions or objects), description of those objects to reduce them to a form suitable for computer processing, and classification (recognition) of individual objects. Finally, higher-level processing involves "making sense" of an ensemble of recognised objects, as in image analysis. Based on the theory just described in the last paragraph, this thesis is organised in three parts: Colour Edge and Face Detection; Hand motion detection; Hand Gesture Detection and Medical Image Processing. II In Colour Edge Detection, two new images G-image and R-image are built through colour space transform, after that, the two edges extracted from G-image and R-image respectively are combined to obtain the final new edge. In Face Detection, a skin model is built first, then the boundary condition of this skin model can be extracted to cover almost all of the skin pixels. After skin detection, the knowledge about size, size ratio, locations of ears and mouth is used to recognise the face in the skin regions. In Hand Motion Detection, frame differe is compared with an automatically chosen threshold in order to identify the moving object. For some special situations, with slow or smooth object motion, the background modelling and frame differencing are combined in order to improve the performance. In Hand Gesture Recognition, 3 features of every testing image are input to Gaussian Mixture Model (GMM), and then the Expectation Maximization algorithm (EM)is used to compare the GMM from testing images and GMM from training images in order to classify the results. In Medical Image Processing (mammograms), the Artificial Neural Network (ANN) and clustering rule are applied to choose the feature. Two classifier, ANN and Support Vector Machine (SVM), have been applied to classify the results, in this processing, the balance learning theory and optimized decision has been developed are applied to improve the performance.

The use of external dimensions in products has great importance in numerous areas and a digital measurement can lead to a more streamlined workflow. In this project are the suitability of sensors for measuring irregularly shaped objects investigated and a prototype for digital measurement built. The prototype consists of a measuring cart, Raspberry Pi, two cameras and MQTT with React web front-end. Measurement is started by a client and reported back to the client with the measurement station’s established measurement values. The result is presented as 79% of measured dimensions ending up within ±10 mm margin of the manually measured value. The result is based on tests of 10 objects with deviating characteristics to challenge the measurement capacity. The biggest challenge that has arisen has been the handling of objects’ perspectives in relation to the cameras. It is one of the areas that could be further developed to improve the reliability of the measuring station. / Användningen av yttermått hos produkter har en stor betydelse inom en stor mängd områden och en digital mätning av detta kan medföra en mer strömlinjeformad arbetsgång. I detta projektet undersöks sensorers lämplighet för mätning av oregelbundet formade objekt och det byggs en prototyp för digital mätning. Prototypen består av en mätvagn, Raspberry Pi, två kameror och MQTT med React-baserat webbgränssnitt. Mätning startas av en klient och rapporteras tillbaka till klienten med mätstationens fastslagna mätvärdena. Resultatet slutar i att 79% av uppmätta dimensioner hamnar inom ±10 mm marginal av manuellt uppmätt värde. Ett resultat som baseras på tester av 10 objekt med avvikande egenskaper för att utmana mätkapaciteten. Det största utmaningen som uppkommit har varit hanteringen av objekts perspektiv i förhållande till kamerorna. Det är ett av områdena som fortsatt har möjlighet att vidarutvecklas för att ytterliggare förbättra mätstationens pålitlighet.

The task of detecting human faces within either a still image or a video frame is one of the most popular object detection problems. For the last twenty years researchers have shown great interest in this problem because it is an essential pre-processing stage for computing systems that process human faces as input data. Example applications include face recognition systems, vision systems for autonomous robots, human computer interaction systems (HCI), surveillance systems, biometric based authentication systems, video transmission and video compression systems, and content based image retrieval systems. In this thesis, non-traditional methods are investigated for detecting human faces within color images or video frames. The attempted methods are chosen such that the required computing power and memory consumption are adequate for real-time hardware implementation. First, a standard color image database is introduced in order to accomplish fair evaluation and benchmarking of face detection and skin segmentation approaches. Next, a new pre-processing scheme based on skin segmentation is presented to prepare the input image for feature extraction. The presented pre-processing scheme requires relatively low computing power and memory needs. Then, several feature extraction techniques are evaluated. This thesis introduces feature extraction based on Two Dimensional Discrete Cosine Transform (2D-DCT), Two Dimensional Discrete Wavelet Transform (2D-DWT), geometrical moment invariants, and edge detection. It also attempts to construct a hybrid feature vector by the fusion between 2D-DCT coefficients and edge information, as well as the fusion between 2D-DWT coefficients and geometrical moments. A self organizing map (SOM) based classifier is used within all the experiments to distinguish between facial and non-facial samples. Two strategies are tried to make the final decision from the output of a single SOM or multiple SOM. Finally, an FPGA based framework that implements the presented techniques, is presented as well as a partial implementation. Every presented technique has been evaluated consistently using the same dataset. The experiments show very promising results. The highest detection rate of 89.2% was obtained when using a fusion between DCT coefficients and edge information to construct the feature vector. A second highest rate of 88.7% was achieved by using a fusion between DWT coefficients and geometrical moments. Finally, a third highest rate of 85.2% was obtained by calculating the moments of edges. / Master of Science

No / Edges are important visual features, providing many cues to the three-dimensional structure of the world. One of these cues is edge blur. Sharp edges tend to be caused by object boundaries, while blurred edges indicate shadows, surface curvature, or defocus due to relative depth. Edge blur also drives accommodation and may be implicated in the correct development of the eye's optical power. Here we use classification image techniques to reveal the mechanisms underlying blur detection in human vision. Observers were shown a sharp and a blurred edge in white noise and had to identify the blurred edge. The resultant smoothed classification image derived from these experiments was similar to a derivative of a Gaussian filter. We also fitted a number of edge detection models (MIRAGE, N(1), and N(3)(+)) and the ideal observer to observer responses, but none performed as well as the classification image. However, observer responses were well fitted by a recently developed optimal edge detector model, coupled with a Bayesian prior on the expected blurs in the stimulus. This model outperformed the classification image when performance was measured by the Akaike Information Criterion. This result strongly suggests that humans use optimal edge detection filters to detect edges and encode their blur.

It is well understood that multiple video cameras and computer vision (CV) technology can be used in sport for match officiating, statistics and player performance analysis. A review of the literature reveals a number of existing solutions, both commercial and theoretical, within this domain. However, these solutions are expensive and often complex in their installation. The hypothesis for this research states that by considering only changes in ball motion, automatic event classification is achievable with low-cost monocular video recording devices, without the need for 3-dimensional (3D) positional ball data and representation. The focus of this research is a rigorous empirical study of low cost single consumer-grade video camera solutions applied to table tennis, confirming that monocular CV based detected ball location data contains sufficient information to enable key match-play events to be recognised and measured. In total a library of 276 event-based video sequences, using a range of recording hardware, were produced for this research. The research has four key considerations: i) an investigation into an effective recording environment with minimum configuration and calibration, ii) the selection and optimisation of a CV algorithm to detect the ball from the resulting single source video data, iii) validation of the accuracy of the 2-dimensional (2D) CV data for motion change detection, and iv) the data requirements and processing techniques necessary to automatically detect changes in ball motion and match those to match-play events. Throughout the thesis, table tennis has been chosen as the example sport for observational and experimental analysis since it offers a number of specific CV challenges due to the relatively high ball speed (in excess of 100kph) and small ball size (40mm in diameter). Furthermore, the inherent rules of table tennis show potential for a monocular based event classification vision system. As the initial stage, a proposed optimum location and configuration of the single camera is defined. Next, the selection of a CV algorithm is critical in obtaining usable ball motion data. It is shown in this research that segmentation processes vary in their ball detection capabilities and location out-puts, which ultimately affects the ability of automated event detection and decision making solutions. Therefore, a comparison of CV algorithms is necessary to establish confidence in the accuracy of the derived location of the ball. As part of the research, a CV software environment has been developed to allow robust, repeatable and direct comparisons between different CV algorithms. An event based method of evaluating the success of a CV algorithm is proposed. Comparison of CV algorithms is made against the novel Efficacy Metric Set (EMS), producing a measurable Relative Efficacy Index (REI). Within the context of this low cost, single camera ball trajectory and event investigation, experimental results provided show that the Horn-Schunck Optical Flow algorithm, with a REI of 163.5 is the most successful method when compared to a discrete selection of CV detection and extraction techniques gathered from the literature review. Furthermore, evidence based data from the REI also suggests switching to the Canny edge detector (a REI of 186.4) for segmentation of the ball when in close proximity to the net. In addition to and in support of the data generated from the CV software environment, a novel method is presented for producing simultaneous data from 3D marker based recordings, reduced to 2D and compared directly to the CV output to establish comparative time-resolved data for the ball location. It is proposed here that a continuous scale factor, based on the known dimensions of the ball, is incorporated at every frame. Using this method, comparison results show a mean accuracy of 3.01mm when applied to a selection of nineteen video sequences and events. This tolerance is within 10% of the diameter of the ball and accountable by the limits of image resolution. Further experimental results demonstrate the ability to identify a number of match-play events from a monocular image sequence using a combination of the suggested optimum algorithm and ball motion analysis methods. The results show a promising application of 2D based CV processing to match-play event classification with an overall success rate of 95.9%. The majority of failures occur when the ball, during returns and services, is partially occluded by either the player or racket, due to the inherent problem of using a monocular recording device. Finally, the thesis proposes further research and extensions for developing and implementing monocular based CV processing of motion based event analysis and classification in a wider range of applications.

La tomographie 3D par rayons X, utilisée tant pour le diagnostic médical que pour le contrôle non-destructif industriel, permet de reconstruire un objet en 3D à partir d’un ensemble de ses projections 2D. Le volume de reconstruction est usuellement discrétisé sur une grille régulière de voxels isotropes ce qui implique une augmentation de leur nombre pour atteindre une bonne résolution spatiale. Une telle représentation peut donc engendrer des coûts calculatoires et un volume mémoire de stockage particulièrement conséquents. Ce manuscrit présente une méthode permettant de discrétiser l’espace 3D de reconstruction de façon pertinente directement à partir de l’information structurelle contenue dans les données de projection. L’idée est d’obtenir une représentation adaptée à l’objet étudié. Ainsi, en lieu et place d’une grille voxélisée, on a recourt ici à un maillage tétraédrique épousant la structure de l’objet : la densité de mailles s’adapte en fonction des interfaces et des régions homogènes. Pour batir un tel maillage, la première étape de la méthode consiste à détecter les bords dans les données de projections 2D. Afin d’assurer une segmentation efficace et de bonne qualité, nous proposons d’exploiter le formalisme des tests statistiques pour paramétrer de façon optimale, automatique et rapide le filtre de Canny. L’information structurelle ainsi obtenue est ensuite fusionnée dans l’espace de reconstruction afin de construire un nuage de points échantillonnant les interfaces 3D de l’objet imagé. Pour ce faire, on procède à une rétroprojection directe des images de bords 2D pour obtenir une cartographie brute des interfaces 3D recherchées. Au moyen d’un filtrage automatisé par méthode statistique, on sélectionne les points les plus représentatifs, délimitant les interfaces avec précision. Le maillage adapté est finalement obtenu par tétraédrisation de Delaunay contrainte par ce nuage de points. Une reconstruction tomographique peut alors être réalisée sur une telle représentation en utilisant des schémas itératifs usuels pour lesquels les modèles de projecteur/rétroprojecteur sont adaptés. Nos expérimentations montrent qu’à partir d’un nombre restreint de projections sur 360° – i.e. 30 – notre méthode permet d’obtenir un nuage de points en très bonne adéquation avec les interfaces de l’objet étudié. La compression obtenue tant en termes de nombre d’inconnues à estimer qu’en espace mémoire nécessaire pour le stockage des volumes reconstruits est importante - jusqu’à 90% - attestant ainsi de l’intérêt de cette discrétisation. Les reconstructions obtenues sont prometteuses et les maillages générés de qualité suffisante pour envisager leur utilisation dans des applications de simulations – éléments finis ou autres. / 3D X-Ray computed tomography reconstruction is a method commonly used, nowadays, in both medical and non destructive testing fields to reconstruct a 3D object from a set of its 2D projections. The reconstruction space usually is sampled on a regular grid of isotropic voxels, thus inducing an increase in the number of cells used in order to get a satisfactory spatial resolution. This representation hence have a direct impact on the growth in computational cost of each reconstruction iteration and imposes the storage of volumes of considerable memory storage footprints. This dissertation introduces an approach to build an adapted sampling of the object of interest directly from a sparse dataset of projections and prior to any tomographic reconstruction. Instead of the usual voxel lattice, we make use of a tetrahedral mesh that tightly fits the object structure : cells density increases close to its interfaces and decreases in homogeneous regions. To create such a mesh, the first step of this work consists in the detection of edges in the 2D projection images. Segmentation quality being paramount for further stages, we introduce a statistical approach to automatically select crucial parameters of the selected edge detector - Canny's filter. This structural information then is merged within the 3D volume of reconstruction as a pointcloud adequately sampling the 3D interfaces of the studied object. To do so, we perform a direct backprojection of the 2D edge maps to obtain a rough 3D map of the desired interfaces. The points composing the cloud are placed according to this map by automated filtering of the rough map. This automation is attained by statistical approach. The adapted mesh is finally obtained by classical constrained Delaunay tetrahedralization algorithm on this cloud. CT reconstruction is performed on this new sampling by using usual iterative algorithms for which suitable models of projector/backprojector are proposed. Our experiments show that, using a sparse dataset - e.g. 30 projections - our method provides pointclouds tightly sampling the object interfaces. The compression achieved in the number of unknowns to estimate and in memory consumption for volume storage is sizable, vouching for the relevance of this sampling. Produced reconstructions are promising and the quality of meshes sufficient to contemplate their use in simulation applications, such as finite element methods.