Sökning: "semantic annotations"

Visar resultat 1 - 5 av 15 uppsatser innehållade orden semantic annotations.

1. 1. Toward Equine Gait Analysis : Semantic Segmentation and 3D Reconstruction

   Master-uppsats, Linköpings universitet/Datorseende

   Författare :Evelina Hult; [2023]
   Nyckelord :Deep Learning; Computer Vision; Semantic Segmentation; Structure-from-Motion; Equine Gait Analysis; Harness Racing Horses; Engineering and Technology; Natural Sciences; Computer Vision Laboratory;

   Sammanfattning : Harness racing horses are exposed to high workload and consequently, they are at risk of joint injuries and lameness. In recent years, the interest in applications to improve animal welfare has increased and there is a demand for objective assessment methods that can enable early and robust diagnosis of injuries. LÄS MER

3. 2. Aerial View Image-Goal Localization with Reinforcement Learning

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :John Backsund; Anton Samuelsson; [2022]
   Nyckelord :reinforcement learning; UAV; machine learning; policy gradient; artificial intelligence; reinforce; Technology and Engineering;

   Sammanfattning : With an increased amount and availability of unmanned aerial vehicles (UAVs) and other remote sensing devices (e.g. satellites) we have recently seen an explosion in computer vision methodologies tailored towards processing and understanding aerial view data. LÄS MER

4. 3. Classification of Terrain Roughness from Nationwide Data Sources Using Deep Learning

   Master-uppsats, Linköpings universitet/Institutionen för systemteknik

   Författare :Emily Fredriksson; [2022]
   Nyckelord :Computer vision; Machine learning; 3D semantic segmentation; Airborne LiDAR data; Terrain classification;

   Sammanfattning : 3D semantic segmentation is an expanding topic within the field of computer vision, which has received more attention in recent years due to the development of more powerful GPUs and the newpossibilities offered by deep learning techniques. Simultaneously, the amount of available spatial LiDAR data over Sweden has also increased. LÄS MER

5. 4. Deep Learning for Earth Observation: improvement of classification methods for land cover mapping : Semantic segmentation of satellite image time series

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

   Författare :Benjamin Carpentier; [2021]
   Nyckelord :Satellite Image Time Series; Remote sensing; Land Cover Classification; Deep Learning; Convolutional Neural Network; Tidsserier av satellitbilder; Fjärranalys; Classificering; Djupinlärning; KonvolutionelltNeuralt Nätverk;

   Sammanfattning : Satellite Image Time Series (SITS) are becoming available at high spatial, spectral and temporal resolutions across the globe by the latest remote sensing sensors. These series of images can be highly valuable when exploited by classification systems to produce frequently updated and accurate land cover maps. LÄS MER

7. 5. Learning from Synthetic Data : Towards Effective Domain Adaptation Techniques for Semantic Segmentation of Urban Scenes

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

   Författare :Gerard Valls I Ferrer; [2021]
   Nyckelord :Semantic Segmentation; Synthetic Data; Autonomous Driving; Domain Shift; Domain Adaptation; Domain Generalisation; Semantisk Segmentering; Syntetiska Data; Autonom Körning; Domänskift; Domänanpassning; Domängeneralisering;

   Sammanfattning : Semantic segmentation is the task of predicting predefined class labels for each pixel in a given image. It is essential in autonomous driving, but also challenging because training accurate models requires large and diverse datasets, which are difficult to collect due to the high cost of annotating images at pixel-level. LÄS MER