Laser-based systems, essential in diverse applications, demand accurate geometric calibration to ensure precise performance. The process of the system requires establishing a reliable relationship between input parameters and corresponding 3D description outgoing laser beams. quality depends on dataset measured lines. To address this challenge, we present stochastic method for measuring coordinates these lines, considering both camera uncertainties measurement noise inherent dot detection...

Data-driven techniques are finding their way into the calibration procedure of galvanometric setups. However, they bypass underlying physical or mathematical model completely. Recent work has shown that a simple assumption about an truth can improve predictions: laser beams leaving device follow straight line. In this article, we take approach step further. Both inputs (the pairs rotations two mirrors) and outputs lines) lie on manifold. We incorporate prior knowledge in via constraints...

We address the challenge of determining a valid set parameters for dynamic line scan thermography setup. Traditionally, this optimization process is labor- and time-intensive work, even an expert skilled in art. Nowadays, simulations software can reduce some that burden. However, when faced with many to optimize, all which cover large range values, still time-consuming endeavor. A number are needed adequately capture underlying physical reality. propose emulate simulator by means Gaussian...

The close relation between spatial kinematics and line geometry has been proven to be fruitful in surface detection reconstruction. However, methods based on this approach are limited simple geometric shapes that can formulated as a linear subspace of or element space. core is principal component formulation find best-fit approximant possibly noisy impartial given an unordered set points point cloud. We expand by introducing the Gaussian process latent variable model, probabilistic...

We propose a new paradigm for modelling and calibrating laser scanners with rotation symmetry, as is the case lidars or galvanometric systems one two rotating mirrors. Instead of bothering about intrinsic parameters physical model, we use geometric properties device to model it specific configuration lines, which can be recovered by line-data-driven procedure. Compared universal data-driven methods that train general line models, our algebraic-geometric approach only requires few...

Accurate checkerboard detection is of vital importance for computer vision applications, and a variety detectors have been developed in the past decades. While some are able to handle partially occluded checkerboards, they fail when large occlusion completely divides checkerboard. We propose new pipeline checkerboards that has robust performance under varying levels noise, blurring, distortion, imaging modalities. This consists detector enhancement with Gaussian processes (GP). By learning...

This work presents our vision and work-in-progress on a new platform for immersive virtual augmented reality (AR) training. ImmersiMed is aimed at medical educational professional institutions educating nurses, doctors, other personnel. created with multi-platform support extensibility in mind. By creating consistent experiences across different platforms applications, intends to increase simulation availability. Furthermore, it expected improve the quality of training prepare students...

Traditionally, calibration of a galvanometric setup is based upon mathematical model an underlying physical reality. These models make considerable number assumptions and simplifications. Moreover, they tend to be nongeneralizable lead nonconvex optimization problems encompassing many parameters. Alternatively, several data-driven statistical approaches have been proposed, in which any the reality completely bypassed. The often black-box trained purely on data itself. Although some...

Bayesian inference using Gaussian processes on large datasets have been studied extensively over the past few years. However, little attention has given how to apply these a high resolution input space. By approximating set of test points (where we want make predictions, not training in dataset) by kd-tree, multi-resolution data structure arises that allows for considerable gains performance and memory usage without significant loss accuracy. In this paper, study feasibility efficiency...

Camera calibration is a first and fundamental step in various computer vision applications. Despite being an active field of research, Zhang's method remains widely used for camera due to its implementation popular toolboxes. However, this initially assumes pinhole model with oversimplified distortion models. In work, we propose novel approach that involves pre-processing remove distortions from images by means Gaussian processes. Our does not need assume any can be applied severely warped...

This study addresses the challenge of mechanism design optimization, particularly focusing on energy efficiency and space reciprocating mechanisms. The research question centers how to effectively utilize Computer-Aided Design (CAD) simulations alongside Bayesian optimization (BO) a constrained streamline process, overcoming limitations traditional kinematic dynamic analysis methods. objective is investigate develop novel framework that integrates CAD-based with BO approach. To achieve this,...

Optimizing process outcomes by tuning parameters through an automated system is common in industry. Ideally, this optimization performed as efficiently possible, using the minimum number of steps to achieve optimal configuration. However, care must often be taken ensure that, pursuing solution, does not enter “unsafe” state (for itself or its surroundings). Safe Bayesian a viable method such contexts, it guarantees constraint fulfillment during process, ensuring remains safe. This assumes...

We propose a new paradigm for modelling and calibrating laser scanners with rotation symmetry, as is the case Lidars or galvanometric systems one two rotating mirrors. Instead of bothering about intrinsic parameters physical model, we use geometric properties device to model it specific configuration lines, which can be recovered by line-data-driven procedure. Compared universal data-driven methods that train general line models, our algebraic-geometric approach only requires few...

Visuospatial neglect is a disorder characterised by impaired awareness for visual stimuli located in regions of space and frames reference. It often associated with stroke. Patients can struggle all aspects daily living community participation. Assessment methods are limited show several shortcomings, considering they mainly performed on paper do not implement the complexity life. Similarly, treatment options sparse only small improvements. We present an artificial intelligence solution...

We propose a new paradigm for modelling and calibrating line-based sensors. elaborate on the special but important case of laser scanners with rotation symmetry, as it is Lidars, or galvanometric systems one two rotating mirrors. Instead bothering about intrinsic parameters physical model, we use geometric properties device to model specific line variety. Compared data-driven methods that train general models, our algebraic-geometric approach only needs few measurements. For example, scanner...