Sökning: "sub-sampling"

Visar resultat 1 - 5 av 10 uppsatser innehållade ordet sub-sampling.

1. 1. Monocular Visual Odometry for Autonomous Underwater Navigation : An analysis of learning-based monocular visual odometry approaches in underwater scenarios

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Andrea Caraffa; [2021]
   Nyckelord :Deep Learning; Monocular Visual Odometry; Computer Vision; Autonomous Underwater Navigation; Autonomous Underwater Vehicle; Djupinlärning; Monokulär Visuell Odometri; Datorseende; Autonom Undervattensnavigering; Autonomt Undervattensfordon;

   Sammanfattning : Visual Odometry (VO) is the process of estimating the relative motion of a vehicle by using solely image data gathered from the camera. In underwater environments, VO becomes extremely challenging but valuable since ordinary sensors for on-road localization are usually unpractical in these hostile environments. LÄS MER

3. 2. An investigation of average stable ranks : On plane geometric objects and financial transaction data

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Linn Odelius; [2020]
   Nyckelord :Topological data analysis; TDA; Mathematics; Stable rank; Topology; Data analysis; Financial transactions; Topologisk dataanalys; Topologi; TDA; Matematik; Teoretisk Matematik; Dataanalys; Finans; Stabil rang;

   Sammanfattning : This thesis concerns the topological features of plane geometric shapes and financial transaction data. Topological properties of the data such as homology groups and their stable ranks are analysed. LÄS MER

4. 3. Segmentation in Skeletal Scintigraphy Images using Convolutional Neural Networks

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :Konrad Gjertsson; [2017]
   Nyckelord :Image Analysis; Deep Learning; Convolutional Neural Networks; Scintigraphy; Mathematics and Statistics;

   Sammanfattning : In this work we have addressed the task of segmentation in skeletal scintigraphy images with deep learning models, where we research different approaches to convert convolutional neural networks designed for classification tasks to powerful pixel wise predictors. We explore different network architectures where two primary research paths have been followed. LÄS MER

5. 4. Sparsity Analysis of Deep Learning Models and Corresponding Accelerator Design on FPGA

   Uppsats för yrkesexamina på grundnivå, KTH/Skolan för informations- och kommunikationsteknik (ICT)

   Författare :Yantian You; [2016]
   Nyckelord :Deep machine learning; DBN; CNN; Multiplication-avoiding; FPGA; MNIST;

   Sammanfattning : Machine learning has achieved great success in recent years, especially the deep learning algorithms based on Artificial Neural Network. However, high performance and large memories are needed for these models , which makes them not suitable for IoT device, as IoT devices have limited performance and should be low cost and less energy-consuming. LÄS MER

7. 5. Cambrian stratigraphy and depositional dynamics based on the Tomten-1 drill core, Falbygden, Västergötland, Sweden

   Master-uppsats, Lunds universitet/Geologiska institutionen

   Författare :Frans Lundberg; [2016]
   Nyckelord :biostratigraphy; Sweden; Västergötland; drill core; agnostoids; trilobites; δ13 excursion DICE ; Cambrian; carbon isotope stratigraphy; Earth and Environmental Sciences;

   Sammanfattning : The Tomten-1 drilling at Torbjörntorp in Västergötland, southern Sweden, penetrated 29.85 m of Cambrian Series 2 and 3, Furongian, and Lower and Middle Ordovician strata. The biostratigraphy, sedimentology and carbon isotope (δ[sup]13[/sup]C[sub]org[/sub]) stratigraphy of the core have been analysed. LÄS MER