Sökning: "Segment Anything Model."
Visar resultat 1 - 5 av 8 uppsatser innehållade orden Segment Anything Model..
1. Automatic Semantic Segmentation of Indoor Datasets
Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskapSammanfattning : Background: In recent years, computer vision has undergone significant advancements, revolutionizing fields such as robotics, augmented reality, and autonomoussystems. Key to this transformation is Simultaneous Localization and Mapping(SLAM), a fundamental technology that allows machines to navigate and interactintelligently with their surroundings. LÄS MER
2. Mutual Enhancement of Environment Recognition and Semantic Segmentation in Indoor Environment
Master-uppsats,Sammanfattning : Background:The dynamic field of computer vision and artificial intelligence has continually evolved, pushing the boundaries in areas like semantic segmentation andenvironmental recognition, pivotal for indoor scene analysis. This research investigates the integration of these two technologies, examining their synergy and implicayions for enhancing indoor scene understanding. LÄS MER
3. Data Augmentations for Improving Vision-Based Damage Detection : in Land Transport Infrastructure
Master-uppsats, KTH/Lantmäteri – fastighetsvetenskap och geodesiSammanfattning : Crack, a typical term most people know, is a common form of distress or damage in road pavements and railway sleepers. It poses significant challenges to their structural integrity, safety, and longevity. Over the years, researchers have developed various data-driven technologies for image-based crack detection in road and sleeper applications. LÄS MER
4. Instance Segmentation for Printed Circuit Board (PCB) Component Analysis : Exploring CNNs and Transformers for Component Detection on Printed Circuit Boards
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In the intricate domain of Printed Circuit Boards (PCBs), object detection poses unique challenges, particularly given the broad size spectrum of components, ranging from a mere 2 pixels to several thousand pixels within a single high-resolution image, often averaging 4000x3000 pixels. Such resolutions are atypical in the realm of deep learning for computer vision, making the task even more demanding. LÄS MER
5. Finite element modelling of strained nanowire heterostructures
Kandidat-uppsats, Lunds universitet/Synkrotronljusfysik; Lunds universitet/Fysiska institutionenSammanfattning : When two materials with different lattice constants are grown together, this generates stress between them, and therefore strain. This strain causes them to have different thermal and electrical properties, and this is especially important on the nanoscale where changes have large impacts. LÄS MER