Sökning: "Objektsdetektering"

Visar resultat 1 - 5 av 9 uppsatser innehållade ordet Objektsdetektering.

1. 1. Velocity Obstacle method adapted for Dynamic Window Approach

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

   Författare :Florian Coissac; [2023]
   Nyckelord :Autonomous navigation; Local planning; Dynamic obstacle avoidance; ROS; Autonom navigering; Lokal planering; Dynamiskt undvikande av hinder; ROS;

   Sammanfattning : This thesis project is part of an internship at Visual Behavior. The company aims at producing computer vision models for robotics, helping the machine to better understand the world through the camera eye. The image holds many features that deep learning models are able to extract: navigable area, depth inference and object detection. LÄS MER

3. 2. TransRUnet: 2D Detection and Segmentation of Lymphoma Lesions in Full-Body PET-CT Images

   Master-uppsats, KTH/Medicinteknik och hälsosystem

   Författare :Lasse Stahnke; [2023]
   Nyckelord :Lymphoma; PET-CT; Deep Learning; CNN; Retina U-Net; Feature Pyramid Transformer; Detection; Segmentation; Lymfom; PET-CT; djupinlärning; CNN; Retina U-Net; Feature Pyramid Transformer; detektion; segmentering;

   Sammanfattning : Identification and localization of FDG-avid lymphoma lesions in PET-CT image volumes is of high importance for the diagnosis and monitoring of treatment progress in lymphoma patients. This process is tedious, time-consuming, and error-prone, due to large image volumes and the heterogeneity of lesions. LÄS MER

4. 3. VTG-Fusion : A GAN-ViT-Based Infrared and Visible ImageFusion Method

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

   Författare :Geng Jiaqi; [2022]
   Nyckelord :Infrared and visible image fusion; deep learning; Generative adversarial network; Transformer; Infraröd och synlig bildfusion; djupinlärning; GAN; Transformator;

   Sammanfattning : Infrared and visible image fusion targets generating one image with texture details from visible images and highlighted objects from the infrared images. It has been widely used in object recognition and object detection. LÄS MER

5. 4. Efficient and robust reduction of bounding boxes of a multi-class neural network’s output for vehicular radar-systems

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

   Författare :Elazab Gasser; [2022]
   Nyckelord :Non-maximum suppression; Deep Learning; Machine Learning; Autonomous Vehicles; Determinantal Point Process; Icke-maximal undertryckning; Djupinlärning; Maskininlärning; Autonoma fordon; Determinant punktprocess;

   Sammanfattning : Object detection has been a fundamental part of many emerging technologies, such as autonomous vehicles, robotics, and security. As deep learning is the main reason behind the leap of performance in object detection, it has mostly been associated with a post-processing step of non-maximum suppression (NMS) to reduce the number of resulting bounding boxes output from the network to, ideally, one box per object. LÄS MER

7. 5. Pruning a Single-Shot Detector for Faster Inference : A Comparison of Two Pruning Approaches

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

   Författare :Karl Beckman; [2022]
   Nyckelord :Computer Vision; Object Detection; Single-Shot Detector; SSD-MobileNetV2; Iterative Pruning; Datorseende; Objektdetektering; Enstegsdetektor; SDD-MobileNet-V2; Iterativ Beskärning;

   Sammanfattning : Modern state-of-the-art object detection models are based on convolutional neural networks and can be divided into single-shot detectors and two-stage detectors. Two-stage detectors exhibit impressive detection performance but their complex pipelines make them slow. LÄS MER