Sökning: "invariant features"
Visar resultat 1 - 5 av 31 uppsatser innehållade orden invariant features.
1. Localization of Combat Aircraft at High Altitude using Visual Odometry
Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysikSammanfattning : Most of the navigation systems used in today’s aircraft rely on Global Navigation Satellite Systems (GNSS). However, GNSS is not fully reliable. For example, it can be jammed by attacks on the space or ground segments of the system or denied at inaccessible areas. LÄS MER
2. Evaluating the effects of data augmentations for specific latent features : Using self-supervised learning
M1-uppsats, KTH/Hälsoinformatik och logistikSammanfattning : Supervised learning requires labeled data which is cumbersome to produce, making it costly and time-consuming. SimCLR is a self-supervising framework that uses data augmentations to learn without labels. This thesis investigates how well cropping and color distorting augmentations work for two datasets, MPI3D and Causal3DIdent. LÄS MER
3. Invariant Propagation for Solvers of Constraint-Based Local Search Technology
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : Constraint-based local search is a technology for solving constrained optimisation problems and constraint satisfaction problems. Solvers of this kind rely on the notion of invariants and an invariant propagation algorithm during search. LÄS MER
4. Topological Band Theory, An Overview
Master-uppsats, Göteborgs universitet / Institutionen för fysikSammanfattning : Topological insulators, superconductors and semi-metals are states of ma er with unique features such as quantized macroscopic observables and robust, gapless edge states. ese states can not be explained by standard quantum mechanics, but require also the framework of topology to be properly characterized. LÄS MER
5. Shape Detection in Images Using Machine Learning
Uppsats för yrkesexamina på grundnivå, Örebro universitet/Institutionen för naturvetenskap och teknikSammanfattning : Rapporten undersöker hur man ska gå tillväga för att implementera en support vector machinesom kan klassificera olika former i bilder med hjälp av OpenCV libraryt i Python. Dettakommer att göras genom att beräkna scale-invariant features. De scale-invariant features somkommer undersökas är simple features och Hu moments. LÄS MER