Anomaly detection is an important first step of quality control in manufacturing processes. In wooden planks, anomalies such as broken knots and resin pockets can lower the quality of the final product. With the help of machine vision, inspections can be made faster, at higher accuracy, and at a lower cost. Therefore, this Master's Thesis project aims to explore different machine vision-based machine learning methods for anomaly detection in images of wooden planks. Both unsupervised and supervised methods were used. The evaluated unsupervised methods were two variations of student-teacher frameworks, while the supervised methods were different semantic segmentation models. The evaluation results showed that the pre-trained DeepLabV3 semantic segmentation model performed the best, with a pixel-level IoU of 0.780, an object-level precision of 89.3% and object-level recall of 96.9%. Findings suggest that for this data set of images of wooden planks, the benefits of training on labeled data outweigh the time cost of annotation.

Quality control is a necessity when it comes to automating a biological lab with the help of robotics. Two major quality control objectives are targeted by the research group PharmBio at Uppsala University: (1) barcode recognition and decoding, and (2) determining the position and orientation of microplates relative the gripper at the end of an industrial robot arm. In order to achieve these objectives, a hardware package with a camera and microcomputer has been designed and built, which can be attached next to the gripper. In addition to the hardware solution, a software stack has been developed and implemented which utilizes the camera and microcomputer to capture digital images. These images are enhanced and processed using machine vision software on the microcomputer, after which the final generated data is sent to an external system for further handling. The final system consisting of integrated hardware and software is capable of achieving both goals: barcode recognition and plate pose determination. However, due to changes in the group’s project plan during the current Master’s project, final implementation of the plate pose determination software remains as future work for a later version. / Kvalitetskontroll är en nödvändighet när det gäller automatiseringen av ett biologiskt lab med hjälp av robotik. Forskargruppen PharmBio vid Uppsala universitet har två huvudsakliga mål gällande kvalitetskontroll: (1) igenkänning och avläsning av streckkoder, och (2) fastställandet av position och riktning av en mikrotiterplatta relativt en gripklo på änden av en robotarm. För att uppnå dessa mål har en enhet innehållandes en kamera och enkortsdator designats och byggts, tänkt att fästas intill gripklon. Utöver denna enhet har ett mjukvarusystem som använder kameran och datorn för att ta bilder utvecklats och implementerats. Dessa bilder behandlas med hjälp av machine vision-mjukvara på enkortsdatorn innan framtagen data skickas vidare till ett externt datorsystem för ytterligare hantering. Det slutgiltiga systemet bestående av integrerad hård- och mjukvara är kapabel att uppnå båda projektmål: streckkodsavläsning och avgöra position/riktning hos en mikrotiterplatta. På grund av ändrad planering hos forskargruppen under arbetets gång kommer dock implementation av mjukvaran framtagen för positions- och riktningsigenkänning dröja till en senare version av projektet.

This thesis evaluates the AMLAS methodology. To support the evaluation, literature studies are conducted and a machine learning dependent system that detects people and helmets is implemented. The practical work is performed according to the documentation of AMLAS. Alongside this work, a user interface is developed. The user interface and the machine learning component is merged to create the complete system. The results show that AMLAS contributes with safety, structure and reliability to the system. However, the findings show that AMLAS is missing some aspects. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>

Unmanned ground vehicles (UGVs) can be used in the military to mitigate risks taken by soldiers as well as to provide solutions to physically demanding, dull or dangerous tasks. While there are benefits of using UGVs, there are also needs and limitations that come with them. This thesis explores what the end user, a light infantry battalion in the Swedish Armed Forces, wants in terms of functions for a UGV designed for military oper- ations in urban terrain. This was done through a explorative case study with focus groups, where soldiers and officers from the 31st Ranger Battalion got to use two different UGV prototypes to complete tasks. This was followed by semi structured group discussions, where needs, limitations and requirements were explored. The collected data was then analysed by a thematic analysis approach. The results from the thematic analysis found several reoccurring opinions regarding requirements from the focus groups. The requirements were grouped into four categories; (1) Speed, (2) Use cases, (3) Image generating sensors, and (4) Autonomous functions. In conclusion, this thesis identified a total of 13 requirements within the four categories. To summarise, these requirements imply that a UGV meant for military operations in urban terrain must be able to keep up with sprinting soldiers, provide visual cover, be able to interact with nearby objects, have several high quality sensors and robust autonomous functions, allowing the soldiers to focus on other things than controlling the UGV.

As a part of the manufacturing process at the forging shop of Alleima AB in Sandviken, materials are heated in a furnace and then quenched in a quench tank. A temperature sensor in the outlet of the tank indicates the time when the temperature rises inside the quench tank. Since the cooling system is dynamic (has inertia), the temperature sensor registers a temperature rise with a delay. Considering the rapid change in the mechanical properties of hot materials, it is important to determine the exact time when the cooling begins. This project proposed a vision system-based automatic timestamp registration technique to facilitate the need. The proposed mechanism first detects the hot metal bars and then uses an event-based technique to determine the timestamp. Finally, the obtained timestamp has been compared with the temperature sensor measurement to determine the delay. This project uses the iba-system to perform the entire procedure. The video sequence is collected using ibaCapture and the image processing took place in ibaVision. The recorded timestamp is then transferred to ibaPDA for further analysis. The main goal is to combine temperature measurement and a computer vision system to automatically determine the delay registered by the temperature sensor. In addition to the proposed solution, this project analysed the image processing plug-in concept of ibaVision and its interface connection with other iba-modules such as ibaPDA and ibaCapture.

No description available.

No description available.

No description available.

No description available.

<p>Accurate measurement of surface grids through imaging enables a variety of applications. One important example can be found in automotive manufacturing, where deformed sheet metal surface strains must be validated in safety critical regions, and rapidly measured to correct process variations. This thesis advances machine vision techniques in the context of close-range surface imaging and measurement. Sheet metal surface strain analysis provides a motivating application, but the contributions may be directly transferred to a variety of other machine vision applications where reliable, accurate measurements are required in adverse imaging conditions.</p> <p>Close-range imaging in practical environments presents a number of challenges, primarily relating to depth of field blur and the regional field of view. This thesis contributes to three major components required for close-range optically-based surface measurement. First, an approach for grid line intersection measurement in the presence of significant and varying depth-of-field blur is considered, with a solution based on scale-space ridge extraction. An architecture for acceleration of the computationally intensive algorithm is then developed, and implemented using state of the art graphics (GPU) hardware. Acceleration to camera video frame rates is achieved.</p> <p>The second contribution is a novel approach for interframe motion tracking of uniform gridded surfaces. The algorithm exploits topological structure of the imaged grid pattern, thereby reducing dimensionality of the interframe tracking problem. Intrinsic fiducial measurement is proposed to avoid the need for explicit feature detectors that locate fiducials in the presence of varying size and blur. Close-range interframe tracking is demonstrated, and statistics are presented on the registration objective function.</p> <p>Finally, an approach is considered for camera and hand-eye calibration of a monocular camera mounted to the tool point of a coordinate measuring machine (CMM). Pre-processing algorithms are contributed to prepare close-range gridded image data for the calibration process. Ideal model coordinate points are coherently assigned to detected grid features across video sequences, and grid approximation is performed for highly blurred image frames where reliable features have not been extracted.</p> <p>The contributions of this thesis make significant progress toward enabling video frame rate, close-range, computer vision-based sheet metal surface strain analysis, and other applications where challenging image conditions impede measurement.</p> / Doctor of Philosophy (PhD)