Proceedings 1992 IEEE International Conference on Robotics and Automation
DOI: 10.1109/robot.1992.220122
|View full text |Cite
|
Sign up to set email alerts
|

Extraction and interpretation of semantically significant line segments for a mobile robot

Abstract: This paper describes new algorithms for detecting and interpreting linear features of a real scene as imaged by a single camera on a mobile robot. The lowlevel processing stages are specifically designed to increase the usefulness and the quality of the extracted features for a semantic interpretation. The detection and interpretation processes provide a 3-D orientation hypothesis for each 2-D segment. This in turn is used to estimate the robot's orientation and relative position in the environment and to deli… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Publication Types

Select...
4
2
1

Relationship

1
6

Authors

Journals

citations
Cited by 26 publications
(6 citation statements)
references
References 9 publications
0
6
0
Order By: Relevance
“…They do not assume any a priori world model or landmarks to be available. Lebègue and Aggarwal [85], [86] propose a scheme for the extraction an interpretation of of semantically significant line segments for a mobile robot. The detection and interpretation processes provide a 3-D orientation hypothesis for each 2-D segment.…”
Section: Environment Map Buildingmentioning
confidence: 99%
See 1 more Smart Citation
“…They do not assume any a priori world model or landmarks to be available. Lebègue and Aggarwal [85], [86] propose a scheme for the extraction an interpretation of of semantically significant line segments for a mobile robot. The detection and interpretation processes provide a 3-D orientation hypothesis for each 2-D segment.…”
Section: Environment Map Buildingmentioning
confidence: 99%
“…Some systems such as those of Rimey and Brown [25] do not make any explicit assumptions about the viewing geometry. Systems such as that of Basri and Rivlin [96] explicitly assume weak perspective projection, while those of Lebègue and Aggarwal [85], [86] assume perspective projection. (3) Representation of domain knowledge Different scene analysis applications need different representation schemes to fulfill their requirements.…”
Section: Reactive Robot Navigationmentioning
confidence: 99%
“…The second stage is autonomous navigation. Lebégue and Aggarwal [3], [4] developed an integrated system to generate architectural CAD models using a mobile robot. The system consists of a segment detector, a tracker and a CAD modeler optimized for environments with prominent threedimensional (3-D) orientations.…”
Section: B Survey Of Related Studiesmentioning
confidence: 99%
“…This section briefly reviews the most important results of [8], which presented a system to observe and accurately reconstruct 3-D segments in indoor scenes. The reader is encouraged to refer to this previous publication for details and explanations.…”
Section: Previous Resultsmentioning
confidence: 99%
“…In [8], a special line detector was introduced to simultaneously extract 2-D segments from an image and estimate their most likely 3-D orientations. The line detector also provides information to prevent the odometers of the robot from drifting, so that the motion of the camera may be estimated correctly even after hundreds of meters of travel.…”
Section: Previous Resultsmentioning
confidence: 99%