Efficiently Increasing Map Density in Visual SLAM Using Planar Features with Adaptive Measurement

Jose Martinez Carranza; Andrew Calway

Efficiently Increasing Map Density in Visual SLAM Using Planar Features with Adaptive Measurement

Jose Martinez Carranza, Andrew Calway

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

6 Citations (Scopus)

Abstract

Point based visual SLAM suffers from a trade off between map density and computa- tional efﬁciency. With too few mapped points, tracking range is restricted and resistance to occlusion is reduced, whilst expanding the map to give dense representation signiﬁ- cantly increases computation. We address this by introducing higher order structure into the map using planar features. The parameterisation of structure allows frame by frame adaptation of measurements according to visibility criteria, increasing the map density without increasing computational load. This facilitates robust camera tracking over wide changes in viewpoint at signiﬁcantly reduced computational cost. Results of real-time experiments with a hand-held camera demonstrate the effectiveness of the approach.

Translated title of the contribution	Efficiently Increasing Map Density in Visual SLAM Using Planar Features with Adaptive Measurement
Original language	English
Title of host publication	British Machine Vision Conference
Publisher	British Machine Vision Association
Publication status	Published - 2009

Bibliographical note

Other page information: -
Conference Proceedings/Title of Journal: British Machine Vision Conference
Other identifier: 2001079

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=2001079

Fingerprint Dive into the research topics of 'Efficiently Increasing Map Density in Visual SLAM Using Planar Features with Adaptive Measurement'. Together they form a unique fingerprint.

Cite this

@inproceedings{4ba36ccc150e4a28a1869cb0a9d989d9,

title = "Efficiently Increasing Map Density in Visual SLAM Using Planar Features with Adaptive Measurement",

abstract = " Point based visual SLAM suffers from a trade off between map density and computa- tional efﬁciency. With too few mapped points, tracking range is restricted and resistance to occlusion is reduced, whilst expanding the map to give dense representation signiﬁ- cantly increases computation. We address this by introducing higher order structure into the map using planar features. The parameterisation of structure allows frame by frame adaptation of measurements according to visibility criteria, increasing the map density without increasing computational load. This facilitates robust camera tracking over wide changes in viewpoint at signiﬁcantly reduced computational cost. Results of real-time experiments with a hand-held camera demonstrate the effectiveness of the approach. ",

author = "Carranza, {Jose Martinez} and Andrew Calway",

note = "Other page information: - Conference Proceedings/Title of Journal: British Machine Vision Conference Other identifier: 2001079",

year = "2009",

language = "English",

booktitle = "British Machine Vision Conference",

publisher = "British Machine Vision Association",

}

TY - GEN

T1 - Efficiently Increasing Map Density in Visual SLAM Using Planar Features with Adaptive Measurement

AU - Carranza, Jose Martinez

AU - Calway, Andrew

N1 - Other page information: - Conference Proceedings/Title of Journal: British Machine Vision Conference Other identifier: 2001079

PY - 2009

Y1 - 2009

N2 - Point based visual SLAM suffers from a trade off between map density and computa- tional efﬁciency. With too few mapped points, tracking range is restricted and resistance to occlusion is reduced, whilst expanding the map to give dense representation signiﬁ- cantly increases computation. We address this by introducing higher order structure into the map using planar features. The parameterisation of structure allows frame by frame adaptation of measurements according to visibility criteria, increasing the map density without increasing computational load. This facilitates robust camera tracking over wide changes in viewpoint at signiﬁcantly reduced computational cost. Results of real-time experiments with a hand-held camera demonstrate the effectiveness of the approach.

AB - Point based visual SLAM suffers from a trade off between map density and computa- tional efﬁciency. With too few mapped points, tracking range is restricted and resistance to occlusion is reduced, whilst expanding the map to give dense representation signiﬁ- cantly increases computation. We address this by introducing higher order structure into the map using planar features. The parameterisation of structure allows frame by frame adaptation of measurements according to visibility criteria, increasing the map density without increasing computational load. This facilitates robust camera tracking over wide changes in viewpoint at signiﬁcantly reduced computational cost. Results of real-time experiments with a hand-held camera demonstrate the effectiveness of the approach.

M3 - Conference Contribution (Conference Proceeding)

BT - British Machine Vision Conference

PB - British Machine Vision Association

ER -