This thesis addresses the pose stabilization of a car-like vehicle using omnidirectional visual feedback. The presented method allows a vehicle to servo to a pre-learnt target pose based on feature bearing angle and range discrepancies between the vehicle's current view of the environment and that seen at the learnt location. The best example of such a task is the use of visual feedback for autonomous parallel-parking of an automobile. Much of the existing work in pose stabilization is highly theoretical in nature with few examples of implementations on 'real' vehicles, let alone vehicles representative of those found in industry. The work in this thesis develops a suitable test platform and implements vision-based pose stabilization techniques. Many of the existing techniques were found to fail due to vehicle steering and velocity loop dynamics, and more significantly, with steering input saturation. A technique which does cope with the characteristics of 'real' vehicles is to divide the task into predefined stages, essentially dividing the state space into sub-manifolds. For a car-like vehicle, the strategy used is to stabilize the vehicle to the line which has the correct orientation and contains the target location. Once on the line, the vehicle then servos to the desired pose. This strategy can accommodate velocity and steering loop dynamics, and input saturation. It can also allow the use of linear control techniques for system analysis and tuning of control gains. To perform pose stabilization, good estimates of vehicle pose are required. A simple, yet robust, method derived from the visual homing literature is to sum the range vectors to all the landmarks in the workspace and divide by the total number of landmarks--the Improved Average Landmark Vector. By subtracting the IALV at the target location from the currently calculated IALV, an estimate of vehicle pose is obtained. In this work, views of the world are provided by an omnidirectional camera, while a magnetic compass provides a reference direction. The landmarks used are red road cones which are segmented from the omnidirectional colour images using a pre-learnt, two-dimensional lookup table of their colour profile. Range to each landmark is estimated using a model of the optics of the system, based on a flat-Earth assumption. A linked-list based method is used to filter the landmarks over time. Complementary filtering techniques, which combine the vision data with vehicle odometry, are used to improve the quality of the measurements.

Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: This thesis presents the design and implementation of all the subsystems required to perform precision autonomous helicopter landings within a low-cost framework. To obtain high-accuracy state estimates during the landing phase a vision-based approach, with a downwards facing camera on the helicopter and a known landing target, was used. An e cient monocular-view pose estimation algorithm was developed to determine the helicopter's relative position and attitude during the landing phase. This algorithm was analysed and compared to existing algorithms in terms of sensitivity, robustness and runtime. An augmented kinematic state estimator was developed to combine measurements from low-cost GPS and inertial measurement units with the high accuracy measurements from the camera system. High-level guidance algorithms, capable of performing waypoint navigation and autonomous landings, were developed. A visual position and attitude measurement (VPAM) node was designed and built to perform the pose estimation and execute the associated algorithms. To increase the node's throughput, a compression scheme is used between the image sensor and the processor to reduce the amount of data that needs to be processed. This reduces processing requirements and allows the entire system to remain on-board with no reliance on radio links. The functionality of the VPAM node was con rmed through a number of practical tests. The node is able to provide measurements of su cient accuracy for the subsequent systems in the autonomous landing system. The functionality of the full system was con rmed in a software environment, as well as through testing using a visually augmented hardware-in-the-loop environment. / AFRIKAANSE OPSOMMING: Hierdie tesis beskryf die ontwikkeling van die substelsels wat vir akkurate outonome helikopter landings benodig word. 'n Onderliggende doel was om al die ontwikkeling binne 'n lae-koste raamwerk te voltooi. Hoe-akkuraatheid toestande word benodig om akkurate landings te verseker. Hierdie metings is verkry deur middel van 'n optiese stelsel, bestaande uit 'n kamera gemonteer op die helikopter en 'n bekende landingsteiken, te ontwikkel. 'n Doeltreffende mono-visie posisie-en-orientasie algoritme is ontwikkel om die helikopter se posisie en orientasie, relatief tot die landingsteiken, te bepaal. Hierdie algoritme is deeglik ondersoek en vergelyk met bestaande algoritmes in terme van sensitiwiteit, robuustheid en uitvoertyd. 'n Optimale kinematiese toestandswaarnemer, wat metings van GPS en inersiele sensore kombineer met die metings van die optiese stelsel, is ontwikkel en deur simulasie bevestig. Hoe-vlak leidingsalgoritmes is ontwikkel wat die helikopter in staat stel om punt-tot-punt navigasie en die landingsprosedure uit te voer. 'n Visuele posisie-en-orientasie meetnodus is ontwikkel om die mono-visie posisie-en orientasie algoritmes uit te voer. Om die deurset te verhoog is 'n saampersingsalgoritme gebruik wat die hoeveelheid data wat verwerk moet word, te verminder. Dit het die benodigde verwerkingskrag verminder, wat verseker het dat alle verwerking op aanboord stelsels kan geskied. Die meetnodus en mono-visie algoritmes is deur middel van praktiese toetse bevestig en is in staat om metings van voldoende akkuraatheid aan die outonome landingstelsel te verskaf. Die werking van die volledige stelsel is, deur simulasies in 'n sagteware en hardeware-indie- lus omgewing, bevestig.

Articulated Heavy Goods Vehicles (HGVs) are more efficient than conventional rigid lorries, but exhibit reduced low-speed manoeuvrability and high-speed stability. Technologies such as autonomous reversing and path-following trailer steering can mitigate this, but practical limitations of the available sensing technologies restrict their commercialisation potential. This dissertation describes the development of practical vision-based articulation angle and trailer off-tracking sensing for HGVs. Chapter 1 provides a background and literature review, covering important vehicle technologies, existing commercial and experimental sensors for articulation angle and off-tracking measurement, and relevant vision-based technologies. This is followed by an introduction to pertinent computer vision theory and terminology in Chapter 2. Chapter 3 describes the development and simulation-based assessment of an articulation angle sensing concept. It utilises a rear-facing camera mounted behind the truck or tractor, and one of two proposed image processing methods: template-matching and Parallel Tracking and Mapping (PTAM). The PTAM-based method was shown to be the more accurate and versatile method in full-scale vehicle tests. RMS measurement errors of 0.4-1.6° were observed in tests on a tractor semi-trailer (Chapter 4), and 0.8-2.4° in tests on a Nordic combination with two articulation points (Chapter 5). The system requires no truck-trailer communication links or artificial markers, and is compatible with multiple trailer shapes, but was found to have increasing errors at higher articulation angles. Chapter 6 describes the development and simulation-based assessment of a trailer off-tracking sensing concept, which utilises a trailer-mounted stereo camera pair and visual odometry. The concept was evaluated in full-scale tests on a tractor semi-trailer combination in which camera location and stereo baseline were varied, presented in Chapter 7. RMS measurement errors of 0.11-0.13 m were obtained in some tests, but a sensitivity to camera alignment was discovered in others which negatively affected results. A very stiff stereo camera mount with a sub-0.5 m baseline is suggested for future experiments. A summary of the main conclusions, a review of the objectives, and recommendations for future work are given in Chapter 8. Recommendations include further refinement of both sensors, an investigation into lighting sensitivity, and alternative applications of the sensors.

The use of robotics has recently seen significant growth in various domains such as unmanned ground/underwater/aerial vehicles, smart manufacturing, and humanoid robots. However, one of the most important and essential capabilities required for long term autonomy, which is the ability to operate robustly and safely in real-world environments, in contrast to industrial and laboratory setup is largely missing. Designing robots that can operate reliably and efficiently in cluttered and changing environments is non-trivial, especially for high degree-of-freedom (DoF) systems, i.e. robots with multiple actuators. On one hand, the dexterity offered by the kinematic redundancy allows the robot to perform dexterous manipulation tasks in complex environments, whereas on the other hand, such complex system also makes controlling and planning very challenging. To address such two interrelated problems, we exploit robot motion synthesis from three perspectives that feed into each other: end-pose planning, motion planning and motion adaptation. We propose several novel ideas in each of the three phases, using which we can efficiently synthesise dexterous manipulation motion for fixed-base robotic arms, mobile manipulators, as well as humanoid robots in cluttered and potentially changing environments. Collision-free inverse kinematics (IK), or so-called end-pose planning, a key prerequisite for other modules such as motion planning, is an important and yet unsolved problem in robotics. Such information is often assumed given, or manually provided in practice, which significantly limiting high-level autonomy. In our research, by using novel data pre-processing and encoding techniques, we are able to efficiently search for collision-free end-poses in challenging scenarios in the presence of uneven terrains. After having found the end-poses, the motion planning module can proceed. Although motion planning has been claimed as well studied, we find that existing algorithms are still unreliable for robust and safe operations in real-world applications, especially when the environment is cluttered and changing. We propose a novel resolution complete motion planning algorithm, namely the Hierarchical Dynamic Roadmap, that is able to generate collision-free motion trajectories for redundant robotic arms in extremely complicated environments where other methods would fail. While planning for fixed-base robotic arms is relatively less challenging, we also investigate into efficient motion planning algorithms for high DoF (30 - 40) humanoid robots, where an extra balance constraint needs to be taken into account. The result shows that our method is able to efficiently generate collision-free whole-body trajectories for different humanoid robots in complex environments, where other methods would require a much longer planning time. Both end-pose and motion planning algorithms compute solutions in static environments, and assume the environments stay static during execution. While human and most animals are incredibly good at handling environmental changes, the state-of-the-art robotics technology is far from being able to achieve such an ability. To address this issue, we propose a novel state space representation, the Distance Mesh space, in which the robot is able to remap the pre-planned motion in real-time and adapt to environmental changes during execution. By utilizing the proposed end-pose planning, motion planning and motion adaptation techniques, we obtain a robotic framework that significantly improves the level of autonomy. The proposed methods have been validated on various state-of-the-art robot platforms, such as UR5 (6-DoF fixed-base robotic arm), KUKA LWR (7-DoF fixed-base robotic arm), Baxter (14-DoF fixed-base bi-manual manipulator), Husky with Dual UR5 (15-DoF mobile bi-manual manipulator), PR2 (20-DoF mobile bi-manual manipulator), NASA Valkyrie (38-DoF humanoid) and many others, showing that our methods are truly applicable to solve high dimensional motion planning for practical problems.

This thesis presents a complete and fully automatic method for estimating the volume of an airbag, through all stages of its inflation, with multiple synchronized high-speed cameras. Using recorded contours of the inflating airbag, its visual hull is reconstructed with a novel method: The intersections of all back-projected contours are first identified with an accelerated epipolar algorithm. These intersections, together with additional points sampled from concave surface regions of the visual hull, are then Delaunay triangulated to a connected set of tetrahedra. Finally, the visual hull is extracted by carving away the tetrahedra that are classified as inconsistent with the contours, according to a voting procedure. The volume of an airbag's visual hull is always larger than the airbag's real volume. By projecting a known synthetic model of the airbag into the cameras, this volume offset is computed, and an accurate estimate of the real airbag volume is extracted. Even though volume estimates can be computed for all camera setups, the cameras should be specially posed to achieve optimal results. Such poses are uniquely found for different airbag models with a separate, fully automatic, simulated annealing algorithm. Satisfying results are presented for both synthetic and real-world data.

Today modern industry systems are almost fully automated. The high requirements regarding speed, flexibility, precision and reliability makes it in some cases very difficult to create. One of the most willingly researched solution to solve many processes without human influence is bin-picking. Bin picking is a very complex process which integrates devices such as: robotic grasping arm, vision system, collision avoidance algorithms and many others. This paper describes the creation of a vision system - the most important part of the whole bin-picking system. Authors propose a model-based solution for estimating a best pick-up candidate position and orientation. In this method database is created from 3D CAD model, compared with processed image from the 3D scanner. Paper widely describes database creation from 3D STL model, Sick IVP 3D scanner configuration and creation of the comparing algorithm based on autocorrelation function and morphological operators. The results shows that proposed solution is universal, time efficient, robust and gives opportunities for further work. / +4915782529118

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 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

>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.