Sökning: "point cloud"

Visar resultat 21 - 25 av 351 uppsatser innehållade orden point cloud.

1. 21. LiDAR Perception in a Virtual Environment Using Deep Learning : A comparative study of state-of-the-art 3D object detection models on synthetic data

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

   Författare :Samuel Skoog; [2023]
   Nyckelord :Object Detection; LiDAR; CARLA; Deep Learning; Autonomous Vehicles; Objektdetektering; LiDAR; CARLA; Djupinlärning; Autonoma fordon;

   Sammanfattning : Perceiving the environment is a crucial aspect of autonomous vehicles. To plan the route, the autonomous vehicle needs to be able to detect objects such as cars and pedestrians. This is possible through 3D object detection. However, labeling this type of data is time-consuming. LÄS MER

3. 22. A Holistic Framework for Analyzing the Reliability of IoT Devices

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

   Författare :Leonardo Manca; [2023]
   Nyckelord :Canvas Learning Management System; Docker containers; Performance tuning Performance tuning; Internet of Things IoT ; Reliability; Failure rate; Availability; Comprehensive framework; IoT architecture; Failure modes; Reliability Block Diagram RBD ; Prestandajustering; Sakernas internet IoT ; Tillförlitlighet; Felfrekvens; Tillgänglighet; Heltäckande ramverk; IoT-arkitektur; Felfunktioner; Till-förlitlighetsblockdiagram RBD Canvas Lärplattform; Dockerbehållare; Prestandajustering;

   Sammanfattning : In the rapidly evolving landscape of the Internet of Things (IoT), ensuring consistency and reliability becomes a top priority for a seamless user experience. In many instances, reliability is assessed through Quality of Service (QoS) metrics, sidelining traditional reliability metrics that thrive on time-dependent failure rates. LÄS MER

4. 23. Clustering on groups for human tracking with 3D LiDAR

   Master-uppsats, Umeå universitet/Institutionen för datavetenskap

   Författare :Simon Utterström; [2023]
   Nyckelord :Computer Vision; Computer Science; AI; Machine Learning; clustering; Kernel Density Clustering; tracking; LiDAR; 3D LiDAR; tracking; human; pedestrian; real time; Datavetenskap; Dataseende; clustering; SLR; CVC; KDEG; KDE; Kernel Density Clustering; HDBSCAN; DBSCAN; LiDAR; point cloud; tracking; human; pedestrian;

   Sammanfattning : 3D LiDAR people detection and tracking applications rely on extracting individual people from the point cloud for reliable tracking. A recurring problem for these applications is under-segmentation caused by people standing close or interacting with each other, which in turn causes the system to lose tracking. LÄS MER

5. 24. Domain Adaptation Of Front View Synthetic Point Clouds Using GANs For Autonomous Driving

   Master-uppsats, KTH/Väg- och spårfordon samt konceptuell fordonsdesign

   Författare :Friedemann Kleinsteuber; [2023]
   Nyckelord :LiDAR; Domain Adaptation; GAN; CycleGAN; Simulation; LiDAR; Domänadaption; GAN; CycleGAN; Simulation;

   Sammanfattning : The perception of the environment is one of the main enablers of Autonomous Driving and is driven by Cameras, RADAR, and LiDAR sensors. Deep Learning algorithms used in perception need a vast amount of labeled, high-quality data which is costly to obtain for LiDAR sensors. LÄS MER

7. 25. Robust Multi-Modal Fusion for 3D Object Detection : Using multiple sensors of different types to robustly detect, classify, and position objects in three dimensions.

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

   Författare :Viktor Kårefjärd; [2023]
   Nyckelord :Computer Vision; 3D Object Detection; Multi-Modal Fusion; Deep Learning; Datorseenden; 3D-objektdetektion; Multimodal fusion; Djupinlärning;

   Sammanfattning : The computer vision task of 3D object detection is fundamentally necessary for autonomous driving perception systems. These vehicles typically feature a multitude of sensors, such as cameras, radars, and light detection and ranging sensors. LÄS MER