2001
DOI: 10.1007/3-540-45324-5_28
|View full text |Cite
|
Sign up to set email alerts
|

Vision-based Localization in RoboCup Environments

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
7
0

Year Published

2001
2001
2022
2022

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 15 publications
(7 citation statements)
references
References 1 publication
0
7
0
Order By: Relevance
“…These features are fixed on the ground with regard to world coordinate, so the robot pose can be inferred through observations. 29,30 The rotation is described by Euler coordinates in this paper. The map used here is the standard field used in the competition, and the location of features relative to the map is known.…”
Section: Front-end Visual Feature Matchingmentioning
confidence: 99%
“…These features are fixed on the ground with regard to world coordinate, so the robot pose can be inferred through observations. 29,30 The rotation is described by Euler coordinates in this paper. The map used here is the standard field used in the competition, and the location of features relative to the map is known.…”
Section: Front-end Visual Feature Matchingmentioning
confidence: 99%
“…Instead of maintaining a belief for all poses, only a set of weighted samples is updated by equation 7 and 8. Since the method has been well documented by several other researchers [13,4], we will not discuss it in detail any further here. Instead, we will focus on the perceptual model and its integration to the sensor container.…”
Section: Plugin Based Localizationmentioning
confidence: 99%
“…As this is much easier than generating a position hypothesis through feature extraction and model matching, all algorithms based on raw distance data used Markov localization or more precise MCL, which became one of the most popular localization methods. Enderle et al [2] presented an approach using the distance to walls extracted from camera images, while Hundelshausen et al [12], Röfer et al [9,10] and Menegatti et al [8] used the distance to the field markings. These algorithms mainly differ in the efficiency of the assessment of position estimates and the number of samples needed for the localization.…”
Section: Introductionmentioning
confidence: 99%