It is well established that acquiring large amounts of range data with vision sensors can quickly lead to important data management challenges where processing capabilities become saturated and pre-empt full usage of the information available for autonomous systems to make educated decisions. While sub-sampling offers a naïve solution for reducing dataset dimension after acquisition, it does not capitalize on the knowledge available in already acquired data to selectively and dynamically drive the acquisition process over the most significant regions in a scene, the latter being generally characterized by variations in depth and surface shape in the context of 3D imaging. This thesis discusses the development of two formal improvement measures, the first based upon surface meshes and Ordinary Kriging that focuses on improving scene accuracy, and the second based upon probabilistic occupancy grids that focuses on improving scene coverage. Furthermore, three selection processes to automatically choose which locations within the field of view of a range sensor to acquire next are proposed based upon the two formal improvement measures. The first two selection processes each use only one of the proposed improvement measures. The third selection process combines both improvement measures in order to counterbalance the parameters of the accuracy of knowledge about the scene and the coverage of the scene. The proposed algorithms mainly target applications using random access range sensors, defined as sensors that can acquire depth measurements at a specified location within their field of view. Additionally, the algorithms are applicable to the case of estimating the improvement and point selection from within a single point of view, with the purpose of guiding the random access sensor to locations it can acquire. However, the framework is developed to be independent of the range sensing technology used, and is validated with range data of several scenes acquired from many different sensors employing various sensing technologies and configurations. Furthermore, the experimental results of the proposed selection processes are compared against those produced by a random sampling process, as well as a neural gas selective sensing algorithm.

This thesis addresses the generation of behaviourally useful, robust representations of the sensory world in the context of machine vision and behaviour. The goals of the work presented in this thesis are to investigate strategies for representing the visual world in a way which is behaviourally useful, to investigate the use of a neurally inspired early perceptual organisation system upon high-level processing in an object recognition system and to investigate the use of a perceptual organisation system on driving an object-based selection process. To address these problems, a biologically inspired framework for machine attention has been developed at a high level of neural abstraction, which has been heavily inspired by the psychological and physiological literature. The framework is described in this thesis, and three system implementations, which investigate the above issues, are described and analysed in detail. The primate brain has access to a coherent representation of the external world, which appears as objects at different spatial locations. It is through these representations that appropriate behavioural responses may be generated. For example, we do not become confused by cluttered scenes or by occluded objects. The representation of the visual scene is generated in a hierarchical computing structure in the primate brain: while shape and position information are able to drive attentional selection rapidly, high-level processes such as object recognition must be performed serially, passing through an attentional bottleneck. Through the process of attentional selection, the primate visual system identifies behaviourally relevant regions of the visual scene, which allows it to prioritise serial attentional shifts towards certain locations. In primates, the process of attentional selection is complex, operating upon surface representations which are robust to occlusion. Attention itself suppresses neural activity related to distractor objects, while sustaining activity relating to the target, allowing the target object to have a clear neural representation upon which the recognition process can operate. This thesis concludes that dynamic representations that are both early and robust against occlusion have the potential to be highly useful in machine vision and behaviour applications.

To optimize production at Tyco Electronics Czech s.r.o. I designed and implemented an automated classification cell with a collaborative manipulator Universal Robots UR5e and a Cognex camera system. The classification cell is supposed to pick up the loose parts and then optically test them, sorting the parts into output binders following the inspection results. First of all, I had to learn programming language for Universal Robots manipulators and Cognex vision system. Next step was to design and draw an electrical diagram. According to the diagram, I connected the cabinet and other peripherals. I also programmed an algorithm controlling the manipulator arm and inspecting of both cameras. Finally, I successfully tested the functionality of the entire classification cell.

The advent of the industrial revolution has brought a great number of changes in the functioning of various processes in manufacturing industries. The ways and means of working have evolved exponentially with the implementation of advanced technology. Moreover, with the increasing technology, the customer demands have also been varying dynamically due to changes in customer requirements focusing on individual customization. To cope with the dynamic demand, manufacturing industries had to make sure their products are manufactured with higher quality and shorter lead times. Implementation and efficient usage of technology has provided industries with the necessary tools to achieve market demand and stay competitive by growing continuously. The transformation aims to reach the level of zero-defect manufacturing and ensure higher first-time right yield capability with minimum utilization of available resources. However, technological advancements have not developed the quality inspection process of the manufacturing industry at the same level as other processes. Due to this, the quality inspection processes are still human dependent which requires a highly skilled human operator to perform inspection procedures using sensory abilities to detect deviations. Research suggests that human quality inspection is prone to errors due to fatigue as the process is continuous, strenuous, and tedious work. The efficiency of human inspection is around 80% which becomes a chronic problem in safety-critical and high-value manufacturing environments. Moreover, with the increasing level of customization and technology, the products are becoming more complex with intricate shapes and only human inspection is not enough to meet the customer requirements. Especially in the case of automotive industry in Body in White applications, human inspection of outer body panels, engine parts with tighter tolerances alone does not make the cut. Advancements in the field of metrology have led to the introduction of Coordinate measuring machines (CMM), which are classified as contact and non-contact measuring machines. The measurements are performed offline away from the production line, using the sampling method. The contact measuring machines are equipped with touch trigger probe devices that travel all over the part to make a virtual image of the product which is time-consuming but accurate. Whereas the noncontact measuring machines are equipped with laser scanners or optical devices which scan the part and develop a virtual model which is fast but has accuracy and repeatability issues due to external factors. But coordinate measuring machines have proven to be bottlenecks as they were not able to synchronize with the production pace and could not perform aninspection on all the produced parts, which would help in collecting data. The gathered data can be used to analyse root causes and generate trends in defect detection. With the advancements in non-contact measuring systems, automotive industries have also realized the potential of implementing inline measurement techniques to perform quality inspection. The non-contact measuring system consists of a robotic arm or setup which is equipped with a camera, sensors, and a complex algorithm to identify defects. This provides the robotic arm with machine vision which is works by taking a series of images of the product from various and process these images to detect deviations using digital image processing techniques. The inline measurement has proven to be accurate, fast, and repeatable to be implemented in synchronization with the production line. Further, the automotive industries are moving towards hybrid inspection systems which capitalize on the measuring speed of the robot and the fast decision-making ability of human senses.

This diploma thesis is dealing with an issue of machine vision in the field of traffic signs recognition. The first part is devoted to machine vision in general traffic situations. Together with traffic applications there is paid attention to a possible autonomous vehicle and applications for the traffic signs recognition. The main part of this work is devoted to a description and an implementation of several methods for colour and pattern localisation of traffic signs in the scene and to identification algorithms. Apart from the implementation itself, these algorithms are submitted to several experiments for a valorisation of their success. The thesis also includes a gallery of images with traffic signs including a file with descriptive annotation for an automatic testing of algorithms.

Master’s thesis is describing main terms in machine vision. It defines the basic working principles, its advantages and disadvantages. It is dividing machine vision systems into several classes. The thesis is solving design of an end effector, of an inspection process and program for smart camera Siemens SIMATIC VS722A, of a program for KUKA KR3 and of mutual communication. At the end the demonstrational application verifying the functionality of entire system is introduced.

Diploma thesis deals with a robot vision and its application to the problem of manipulation of coincidentally placed objects. There is mentioned an overview of current principles of the most frequently used vision systems on the market. With regard to the required task to be solved, there are mentioned various possibilities of using basic softsensors during the recognition of different objects. The objective of this Diploma thesis is also programming and realization of a demonstration application applying knowledge of PLC programming, knowledge of expert programming KRL language (for KUKA robots), knowledge of designing scripts for smart camera in Spectation software and knowledge of network communication among all devices used in this case.

The aim of my thesis is a comperation with Linde Pohony s.r.o. Our aim is to suggest the realization of automatic control of pre-assembly of planetary wheels. The solution with CCD cameras and sensors is interpreted in a detailed way - treir reliability suggestibility by milieu and attendance service.The second part continue of a suggestion of automized workplace with a full detailed drawings. Abstrakt

Master´s thesis is describing basic concepts in machine vision. Used camera systems and possible imaging 2D and 3D are described. Practical part deals with constructin of scanning device with linear actuator, conveyor belt, camera and laser. For experimental use is construction of scanning device made for 2D and 3D image using several methods.

This thesis deals with the possibilities of 3D vision. The theoretical part describes the principles of machine vision, constitutes the basic elements, description and the methods of measurement and 3D. The practical part is focused on the design of experimental workplace, which is consists of conveyor, experimental stand, industrial robot and PLC control. The system used to recognize and grasp objects undirected. Construction chapter focuses on the treatment needs of the conveyor for sensing applications and design of experimental stand with linear axis, which is equipped with camera and lasers. Furthermore solved by a communication network between the elements of work includes the design of their communications with the description of the control of its individual elements.