Dense Tracking and Mapping with a Quadrocopter

Jürgen Sturm; Erik Bylow; Christian Kerl; Fredrik Kahl; Daniel Cremers

Dense Tracking and Mapping with a Quadrocopter

Jürgen Sturm, Erik Bylow, Christian Kerl, Fredrik Kahl, Daniel Cremers

Research output: Contribution to conference › Paper, not in proceeding › peer-review

503 Downloads (Pure)

Abstract

In this paper, we present an approach for acquiring textured 3D
models of room-sized indoor spaces using a quadrocopter. Such
room models are for example useful for architects and interior
designers as well as for factory planners and construction man-
agers. The model is internally represented by a signed distance
function (SDF) and the SDF is used to directly track the camera
with respect to the model. Our solution enables accurate position
control of the quadrocopter, so that it can automatically follow a
pre-defined flight pattern. Our system provides live feedback of
the acquired 3D model to the user. The final model consisting of a
textured 3D triangle mesh can be saved in several standard CAD
file formats.

Original language	English
Publication status	Published - 2013
Event	UAV-g 2013 - Rostock, Germany Duration: 2013 Sept 3 → 2013 Sept 6

Conference

Conference	UAV-g 2013
Country/Territory	Germany
City	Rostock
Period	2013/09/03 → 2013/09/06

Subject classification (UKÄ)

Computer graphics and computer vision
Mathematical Sciences

Free keywords

quadrocopter
localization
3D reconstruction
RGB-D sensors
real-time

Access to Document

sturm_etal_2013uavg

1 Doctoral Thesis (compilation)

Optimization Methods for 3D Reconstruction: Depth Sensors, Distance Functions and Low-Rank Models
Bylow, E., 2018, Department of Mathematics, Lund University.
Research output: Thesis › Doctoral Thesis (compilation)

Open Access
File

Cite this

@conference{b7448b359d44463ab13bcc47c972c13c,

title = "Dense Tracking and Mapping with a Quadrocopter",

abstract = "In this paper, we present an approach for acquiring textured 3D models of room-sized indoor spaces using a quadrocopter. Such room models are for example useful for architects and interior designers as well as for factory planners and construction man- agers. The model is internally represented by a signed distance function (SDF) and the SDF is used to directly track the camera with respect to the model. Our solution enables accurate position control of the quadrocopter, so that it can automatically follow a pre-defined flight pattern. Our system provides live feedback of the acquired 3D model to the user. The final model consisting of a textured 3D triangle mesh can be saved in several standard CAD file formats.",

keywords = "quadrocopter, localization, 3D reconstruction, RGB-D sensors, real-time",

author = "J{\"u}rgen Sturm and Erik Bylow and Christian Kerl and Fredrik Kahl and Daniel Cremers",

year = "2013",

language = "English",

note = "UAV-g 2013 ; Conference date: 03-09-2013 Through 06-09-2013",

}

TY - CONF

T1 - Dense Tracking and Mapping with a Quadrocopter

AU - Sturm, Jürgen

AU - Bylow, Erik

AU - Kerl, Christian

AU - Kahl, Fredrik

AU - Cremers, Daniel

PY - 2013

Y1 - 2013

N2 - In this paper, we present an approach for acquiring textured 3D models of room-sized indoor spaces using a quadrocopter. Such room models are for example useful for architects and interior designers as well as for factory planners and construction man- agers. The model is internally represented by a signed distance function (SDF) and the SDF is used to directly track the camera with respect to the model. Our solution enables accurate position control of the quadrocopter, so that it can automatically follow a pre-defined flight pattern. Our system provides live feedback of the acquired 3D model to the user. The final model consisting of a textured 3D triangle mesh can be saved in several standard CAD file formats.

AB - In this paper, we present an approach for acquiring textured 3D models of room-sized indoor spaces using a quadrocopter. Such room models are for example useful for architects and interior designers as well as for factory planners and construction man- agers. The model is internally represented by a signed distance function (SDF) and the SDF is used to directly track the camera with respect to the model. Our solution enables accurate position control of the quadrocopter, so that it can automatically follow a pre-defined flight pattern. Our system provides live feedback of the acquired 3D model to the user. The final model consisting of a textured 3D triangle mesh can be saved in several standard CAD file formats.

KW - quadrocopter

KW - localization

KW - 3D reconstruction

KW - RGB-D sensors

KW - real-time

M3 - Paper, not in proceeding

T2 - UAV-g 2013

Y2 - 3 September 2013 through 6 September 2013

ER -

Dense Tracking and Mapping with a Quadrocopter

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Research output

Optimization Methods for 3D Reconstruction: Depth Sensors, Distance Functions and Low-Rank Models

Cite this