University of Twente Student Theses
Comparative Analysis of Dynamic Object Segmentation Networks for Tele-robotic Applications
D'Souza, C.D.D. (2024) Comparative Analysis of Dynamic Object Segmentation Networks for Tele-robotic Applications.
|
PDF
5MB |
| Abstract: | The task involves refining dynamic object tracking within SLAM for accurate VR map updates in a remote environment. Evaluating diverse algorithms for real-time object detection, a hybrid approach combining deep learning with traditional computer vision methods emerges as a promising solution, leveraging their respective strengths. Model selection involves balancing factors like computational resources, accuracy, and real-time performance, enriching the toolkit for addressing semantic segmentation challenges in computer vision. A detailed comparative analysis highlights various model strengths but refrains from favoring a specific one, as each excels in different scenarios. This thorough exploration aims to enhance understanding and decision-making in selecting suitable models for dynamic object segmentation in telerobotic applications. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 50 technical science in general |
| Programme: | Electrical Engineering MSc (60353) |
| Link to this item: | https://purl.utwente.nl/essays/97938 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page