Sökning: "object localisation"

Visar resultat 1 - 5 av 10 uppsatser innehållade orden object localisation.

1. 1. Development of a real-time navigation and collisionavoidance system for an autonomous naval rover : A Contribution to the Environmental Initiative for Flexible andReal-time Water Monitoring of the CatFish team

   Magister-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Esmee Tackx; [2023]
   Nyckelord :;

   Sammanfattning : This thesis explores the design and optimisation of a sensor system for real-time position determination of the Fish component in the CatFish naval drone and the development of a sonar sensor system for accurate object localisation and safe navigation in dynamic and uncertain underwater conditions. Through comprehensive experimentation and analysis, this thesis demonstrates the effectiveness of the proposed sensor system and sonar sensing system in enhancing underwater navigation and obstacle avoidance capabilities. LÄS MER

3. 2. Deep neural networks for food waste analysis and classification : Subtraction-based methods for the case of data scarcity

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Signaler och system

   Författare :David Brunell; [2022]
   Nyckelord :Siamese network; convolutional neural network;

   Sammanfattning : Machine learning generally requires large amounts of data, however data is often limited. On the whole the amount of data needed grows with the complexity of the problem to be solved. Utilising transfer learning, data augmentation and problem reduction, acceptable performance can be achieved with limited data for a multitude of tasks. LÄS MER

4. 3. Instance Segmentation on depth images using Swin Transformer for improved accuracy on indoor images

   Master-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystem

   Författare :Alfred Hagberg; Mustaf Abdullahi Musse; [2022]
   Nyckelord :Instance Segmentation; segmentation; deep learning; semantic segmentation; swin transformer; mask rcnn; rcnn; cascade mask rcnn; slam; simultaneous localization and mapping; object detection; COCO; NYU dataset; vision transformer;

   Sammanfattning : The Simultaneous Localisation And Mapping (SLAM) problem is an open fundamental problem in autonomous mobile robotics. One of the latest most researched techniques used to enhance the SLAM methods is instance segmentation. LÄS MER

5. 4. Markov Chain Monte Carlo (MCMC) and Bayesian Inference for Gravitational Waves

   Kandidat-uppsats, Lunds universitet/Astronomi - Genomgår omorganisation

   Författare :Christine Andersson; [2021]
   Nyckelord :Gravitational Waves; LISA; LISA mission; Bayesian Inference; Markov Chain Monte Carlo; MCMC; Bayes’ Theorem; stochastic sampling; Metropolis Hastings; histograms; Physics and Astronomy;

   Sammanfattning : The Laser Interferometer Space Antenna (LISA) is a space borne gravitational wave detec- tor set to launch in 2034, with the objective of detecting and studying the Gravitational Waves (GWs) of our universe. So far, ground-based detectors such as the Laser Interferometer Gravitational-Wave Observatory (LIGO) have been successful in detecting GWs, but the limitations of ground based detectors is what makes LISA so special. LÄS MER

7. 5. Object Detection in Domain Specific Stereo-Analysed Satellite Images

   Master-uppsats, Linköpings universitet/Datorseende

   Författare :Fredrik Grahn; Kristian Nilsson; [2019]
   Nyckelord :object detection; object classification; clustering; hierarchical clustering; object localisation; machine learning; ai; image localisation; image segmentation; semantic segmentation; remote sensing images; satellite images; domain knowledge; support vector machines; svm; convolutional neural network; cnn; fully convolutional network; fcn; region-based convolutional neural network; you only look once; yolo; network fusion;

   Sammanfattning : Given satellite images with accompanying pixel classifications and elevation data, we propose different solutions to object detection. The first method uses hierarchical clustering for segmentation and then employs different methods of classification. LÄS MER