The cost and effort of modelling existing bridges from point clouds currently outweighs the perceived benefits of the resulting model. The time required for generating a geometric Bridge Information Model, a holistic data model which has recently become known as a "Digital Twin", of an existing bridge from Point Cloud Data is roughly ten times greater than laser scanning it. There is a pressing need to automate this process. This is particularly true for the highway infrastructure sector because Bridge Digital Twin Generation is an efficient means for documenting bridge condition data. Based on a two-year inspection cycle, there is a need for at least 315,000 bridge inspections per annum across the United States and the United Kingdom. This explains why there is a huge market demand for less labour-intensive bridge documentation techniques that can efficiently boost bridge management productivity. Previous research has achieved the automatic generation of surface primitives combined with rule-based classification to create labelled cuboids and cylinders from point clouds. While existing methods work well in synthetic datasets or simplified cases, they encounter huge challenges when dealing with real-world bridge point clouds, which are often unevenly distributed and suffer from occlusions. In addition, real bridge topology is much more complicated than idealized cases. Real bridge geometries are defined with curved horizontal alignments, and varying vertical elevations and cross-sections. These characteristics increase the modelling difficulties, which is why none of the existing methods can handle reliably. The objective of this PhD research is to devise, implement, and benchmark a novel framework that can reasonably generate labelled geometric object models of constructed bridges comprising concrete elements in an established data format (i.e. Industry Foundation Classes). This objective is achieved by answering the following research questions: (1) how to effectively detect reinforced concrete bridge components in Point Cloud Data? And (2) how to effectively fit 3D solid models in the format of Industry Foundation Classes to the detected point clusters? The proposed framework employs bridge engineering knowledge that mimics the intelligence of human modellers to detect and model reinforced concrete bridge objects in point clouds. This framework directly extracts structural bridge components and then models them without generating low-level shape primitives. Experimental results suggest that the proposed framework can perform quickly and reliably with complex and incomplete real-world bridge point clouds encounter occlusions and unevenly distributed points. The results of experiments on ten real-world bridge point clouds indicate that the framework achieves an overall micro-average detection F1-score of 98.4%, an average modelling accuracy of (C2C) ̅_Auto 7.05 cm, and the average modelling time of merely 37.8 seconds. Compared to the laborious and time-consuming manual practice, the proposed framework can realize a direct time-savings of 95.8%. This is the first framework of its kind to achieve such high and reliable performance of geometric digital twin generation of existing bridges. Contributions. This PhD research provides the unprecedented ability to rapidly model geometric bridge concrete elements, based on quantitative measurements. This is a huge leap over the current practice of Bridge Digital Twin Generation, which performs this operation manually. The presented research activities will create the foundations for generating meaningful digital twins of existing bridges that can be used over the whole lifecycle of a bridge. As a result, the knowledge created in this PhD research will enable the future development of novel, automated applications for real-time condition assessment and retrofit engineering.

This study investigates how a statistical filter affects the quality of point cloud segmentation using a Difference of Normals (DoN) multiscale segmentation approach. A system of DoN segmentation combined with a statistical filter was implemented with the help of an open-source Point Cloud Library (PCL) and evaluated on a publicly available dataset containing large point clouds with labeled ground truth objects. The results shows that when a small number of points is filtered results in an improvement of segmentation quality whereas a large number of filtered points decreases segmentation quality. In conclusion, the statistical filter can be combined with DoN segmentation to achieve segmentations of high quality however, non carefully selected thresholds for the statistical filter decreases segmentation quality drastically.

<p>This work deals with the problem of estimating the intrinsic dimension of noisy, high-dimensional point clouds. A general class of sets which are locally well-approximated by <italic>k</italic> dimensional planes but which are embedded in a <italic>D</italic>>><italic>k</italic> dimensional Euclidean space are considered. Assuming one has samples from such a set, possibly corrupted by high-dimensional noise, if the data is linear the dimension can be recovered using PCA. However, when the data is non-linear, PCA fails, overestimating the intrinsic dimension. A multiscale version of PCA is thus introduced which is robust to small sample size, noise, and non-linearities in the data.</p> / Dissertation

This report evaluates possibilities to combine volumetric ultrasound (us) data together with the recent work published on advanced skin rendering techniques. We focus mainly on how to filter us data and localize surfaces within us data. We also evaluate recent skin rendering techniques in order to have a good understanding of what is needed from the us for rendering realistic skin. us data is acquired using sonography and have a low signal-to-noise ratio by nature, this makes it harder to extract surfaces compared to other medical data acquisition methods such as ct and mr. This report present an algorithm which implements a variational classification technique to emphasize surfaces within us and using a rbf network to fit an implicit function to these surfaces. Using this approach presented we have successfully extract smooth meshes from the noisy us data.

This thesis presents possibilities of 3D point cloud and true colored digital video fusion that can be used in the process of robot teleoperation. Advantages of a 3D environment visualization combining more than one sensor data, tools to facilitate such data fusion, as well as two alternative practical implementations of combined data visualization are discussed. First proposed alternative estimates view frustum of the robot's camera and maps real colored video to a semi-transparent polygon placed in the view frustum. The second option is a direct coloring of the point cloud data creating a colored point cloud representing color as well as depth information about an environment.

Autonomous driving requires lightweight and robust perception systems that can rapidly and accurately interpret the complex driving environment. This dissertation investigates the transformative capacity of discrete wavelet transform (DWT), inverse DWT, CNNs, and transformers as foundational elements to develop lightweight perception architectures for autonomous vehicles. The inherent properties of DWT, including its invertibility, sparsity, time-frequency localization, and ability to capture multi-scale information, present an inductive bias. Similarly, transformers capture long-range dependency between features. By harnessing these attributes, novel wavelet-enhanced deep learning architectures are introduced. The first contribution is introducing a lightweight backbone network that can be employed for real-time processing. This network balances processing speed and accuracy, outperforming established models like ResNet-50 and VGG16 in terms of accuracy while remaining computationally efficient. Moreover, a multiresolution attention mechanism is introduced for CNNs to enhance feature extraction. This mechanism directs the network's focus toward crucial features while suppressing less significant ones. Likewise, a transformer model is proposed by leveraging the properties of DWT with vision transformers. The proposed wavelet-based transformer utilizes the convolution theorem in the frequency domain to mitigate the computational burden on vision transformers caused by multi-head self-attention. Furthermore, a proposed wavelet-multiresolution-analysis-based 3D object detection model exploits DWT's invertibility, ensuring comprehensive environmental information capture. Lastly, a multimodal fusion model is presented to use information from multiple sensors. Sensors have limitations, and there is no one-fits-all sensor for specific applications. Therefore, multimodal fusion is proposed to use the best out of different sensors. Using a transformer to capture long-range feature dependencies, this model effectively fuses the depth cues from LiDAR with the rich texture derived from cameras. The multimodal fusion model is a promising approach that integrates backbone networks and transformers to achieve lightweight and competitive results for 3D object detection. Moreover, the proposed model utilizes various network optimization methods, including pruning, quantization, and quantization-aware training, to minimize the computational load while maintaining optimal performance. The experimental results across various datasets for classification networks, attention mechanisms, 3D object detection, and multimodal fusion indicate a promising direction in developing a lightweight and robust perception system for robotics, particularly in autonomous driving.

No description available.

The goal of the present dissertation is to develop and apply novel and systematic data-driven optimization approaches that can efficiently optimize Additive Manufacturing (AM) systems with respect to targeted properties of final parts. The proposed approaches are capable of achieving sets of process parameters that result in the satisfactory level of part quality in an accelerated manner. First, an Accelerated Process Optimization (APO) methodology is developed to optimize an individual scalar property of parts. The APO leverages data from similar—but non-identical—prior studies to accelerate sequential experimentation for optimizing the AM system in the current study. Using Bayesian updating, the APO characterizes and updates the difference between prior and current experimental studies. The APO accounts for the differences in experimental conditions and utilizes prior data to facilitate the optimization procedure in the current study. The efficiency and robustness of the APO is tested against an extensive simulation studies and a real-world case study for optimizing relative density of stainless steel parts fabricated by a Selective Laser Melting (SLM) system. Then, we extend the idea behind the APO in order to handle multi-objective process optimization problems in which some of the characteristics of the AMabricated parts are uncorrelated. The proposed Multi-objective Process Optimization (m-APO) breaks down the master multi-objective optimization problem into a series of convex combinations of single-objective sub-problems. The m-APO maps and scales experimental data from previous sub-problems to guide remaining sub-problems that improve the solutions while reducing the number of experiments required. The robustness and efficiency of the m-APO is verified by conducting a series of challenging simulation studies and a real-world case study to minimize geometric inaccuracy of parts fabricated by a Fused Filament Fabrication () system. At the end, we apply the proposed m-APO to maximize the mechanical properties of AMabricated parts that show conflicting behavior in the optimal window, namely relative density and elongation-toailure. Numerical studies show that the m-APO can achieve the best trade-off among conflicting mechanical properties while significantly reducing the number of experimental runs compared with existing methods.