Henken, R (2010) A Performance Evaluation of a 3D MLI Time-of-Flight-sensor for applications in a domestic niche. Bachelor's Thesis, Artificial Intelligence.
|
Text
AI-BA-2010-R.Henken.pdf - Published Version Download (1MB) | Preview |
Abstract
When an autonomous robot is placed in an unknown environment, it does not yet have a map. To be able to build a map it is important that landmarks can be extracted from the environment. In this bachelor project we have attempted to extract landmarks from a domestic environment using a 3D MLI Time-of-Flight (ToF) sensor. The sensor uses the phase change of the reflection of actively emitted infrared light to determine the distance to objects. The sensor has a range from approximately 200 mm to 7000 mm and a resolution of 56 by 61 pixels. We used the sensor to build a dataset of gray-scale intensity images. We applied the SIFT feature detection method to detect and describe features in the gray-scale images and used SIFT matching to match the features. The experiment shows that by using this method it is quite difficult to extract reliable landmarks from the environment.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Jong, S. de and Kloosterman, H |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 15 Feb 2018 07:44 |
| Last Modified: | 02 May 2019 11:37 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/9343 |
Actions (login required)
 |
View Item |