Sökning: "dense semantic segmentation"

Visar resultat 1 - 5 av 7 uppsatser innehållade orden dense semantic segmentation.

1. 1. Enhancement-basedSmall TargetDetection for InfraredImages

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

   Författare :Yang Hanqi; [2023]
   Nyckelord :Infrared Images; Small targets; Dilated Convolution; Infraröda bilder; Små mål; Dilaterad konvolution;

   Sammanfattning : Infrared small target detection is widely used in fields such as military and security. UNet, which is a classical semantic segmentation method proposed in 2015, has shown excellent performance and robustness. However, U-Net suffers from the problem of losing small targets in deep layers after multiple down-sampling operations. LÄS MER

3. 2. Semi-Supervised Domain Adaptation for Semantic Segmentation with Consistency Regularization : A learning framework under scarce dense labels

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

   Författare :Daniel Morales Brotons; [2023]
   Nyckelord :Domain Adaptation; Semi-Supervised Learning; Semi-Supervised Domain Adaptation; Semantic Segmentation; Consistency Regularization; Domain Adaptation; Semi-Supervised Learning; Semi-Supervised Domain Adaptation; Semantisk Segmentering; Konsistensregularisering;

   Sammanfattning : Learning from unlabeled data is a topic of critical significance in machine learning, as the large datasets required to train ever-growing models are costly and impractical to annotate. Semi-Supervised Learning (SSL) methods aim to learn from a few labels and a large unlabeled dataset. LÄS MER

4. 3. Towards Visual-Inertial SLAM for Dynamic Environments Using Instance Segmentation and Dense Optical Flow

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

   Författare :Luis Alejandro Sarmiento Gonzalez; [2021]
   Nyckelord :Semantic SLAM; Stereo Vision; VisualInertial SLAM; Motion likelihood; Stereo disparity; Dense optical flow; Dynamic objects.; Semantisk SLAM; Stereo Vision; Visual-Inertial SLAM; Sannolikhet för rörelse; Stereoskillnader; Tätt optiskt flöde; Dynamiska objekt.;

   Sammanfattning : Dynamic environments pose an open problem for the performance of visual SLAM systems in real-life scenarios. Such environments involve dynamic objects that can cause pose estimation errors. LÄS MER

5. 4. Semantic Stixels fusing LIDAR for Scene Perception

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

   Författare :Olof Forsberg; [2018]
   Nyckelord :Stixels; Perception; Scene Perception; Autonomous driving; AD; LIDAR; Semantic Segmentation; Scene model; Real time; Dynamic Programing;

   Sammanfattning : Autonomous driving is the concept of a vehicle that operates in traffic without instructions from a driver. A major challenge for such a system is to provide a comprehensive, accurate and compact scene model based on information from sensors. LÄS MER

7. 5. 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