FPGA-based Real-time Moving Object Detection for Walking Robots

Andreas Laika; Johny Paul; Christopher Claus; Walter Stechele; Adam El Sayed Auf; Erik Maehle

doi:10.1109/SSRR.2010.5981554

FPGA-based Real-time Moving Object Detection for Walking Robots

Andreas Laika, Johny Paul, Christopher Claus, Walter Stechele, Adam El Sayed Auf, Erik Maehle

Institute of Computer Engineering

Abstract

In a rescue operation walking robots offer a great deal of flexibility in traversing uneven terrain in an uncontrolled environment. For such a rescue robot each motion is a potential vital sign but the existing techniques for motion detection have severe limitations in dealing with strong levels of ego-motion on walking robots. This paper proposes an optical flow based method for the detection of moving objects using a single camera mounted on a hexapod robot for an application in a rescue scenario. The proposed algorithm estimates and compensates ego-motion to allow for object detection while the robot is moving. Our algorithm can deal with strong rotation and translation in 3D, using a first-order-flow motion model, with four degrees of freedom. Two alternative object detection methods using a 2D-histogram based vector clustering and motion compensated frame differencing respectively are examined for the detection of slow and fast moving objects. In addition to a software implementation, the system was implemented on an FPGA, enabling processing in real-time at 31 fps.

Original language	English
Title of host publication	2010 IEEE Safety Security and Rescue Robotics
Number of pages	8
Publisher	IEEE
Publication date	01.12.2010
Pages	1-8
Article number	5981554
ISBN (Print)	978-1-4244-8898-8
ISBN (Electronic)	978-1-4244-8899-5
DOIs	https://doi.org/10.1109/SSRR.2010.5981554
Publication status	Published - 01.12.2010
Event	8th IEEE International Workshop on Safety, Security, and Rescue Robotics - Bremen, Germany Duration: 26.07.2010 → 30.07.2010 Conference number: 86439

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/SSRR.2010.5981554

Cite this

@inproceedings{d3a9935d2c334572a3daf01d71b255e9,

title = "FPGA-based Real-time Moving Object Detection for Walking Robots",

abstract = "In a rescue operation walking robots offer a great deal of flexibility in traversing uneven terrain in an uncontrolled environment. For such a rescue robot each motion is a potential vital sign but the existing techniques for motion detection have severe limitations in dealing with strong levels of ego-motion on walking robots. This paper proposes an optical flow based method for the detection of moving objects using a single camera mounted on a hexapod robot for an application in a rescue scenario. The proposed algorithm estimates and compensates ego-motion to allow for object detection while the robot is moving. Our algorithm can deal with strong rotation and translation in 3D, using a first-order-flow motion model, with four degrees of freedom. Two alternative object detection methods using a 2D-histogram based vector clustering and motion compensated frame differencing respectively are examined for the detection of slow and fast moving objects. In addition to a software implementation, the system was implemented on an FPGA, enabling processing in real-time at 31 fps.",

author = "Andreas Laika and Johny Paul and Christopher Claus and Walter Stechele and Auf, {Adam El Sayed} and Erik Maehle",

year = "2010",

month = dec,

day = "1",

doi = "10.1109/SSRR.2010.5981554",

language = "English",

isbn = " 978-1-4244-8898-8",

series = " International Workshop on Safety, Security, and Rescue Robotics",

publisher = "IEEE",

pages = "1--8",

booktitle = "2010 IEEE Safety Security and Rescue Robotics",

note = "8th IEEE International Workshop on Safety, Security, and Rescue Robotics <br/>, SSRR-2010 ; Conference date: 26-07-2010 Through 30-07-2010",

}

Laika, A, Paul, J, Claus, C, Stechele, W, Auf, AES & Maehle, E 2010, FPGA-based Real-time Moving Object Detection for Walking Robots. in 2010 IEEE Safety Security and Rescue Robotics., 5981554, International Workshop on Safety, Security, and Rescue Robotics, IEEE, pp. 1-8, 8th IEEE International Workshop on Safety, Security, and Rescue Robotics
, Bremen, Bremen, Germany, 26.07.10. https://doi.org/10.1109/SSRR.2010.5981554

FPGA-based Real-time Moving Object Detection for Walking Robots. / Laika, Andreas; Paul, Johny; Claus, Christopher et al.
2010 IEEE Safety Security and Rescue Robotics. IEEE, 2010. p. 1-8 5981554 ( International Workshop on Safety, Security, and Rescue Robotics).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - FPGA-based Real-time Moving Object Detection for Walking Robots

AU - Laika, Andreas

AU - Paul, Johny

AU - Claus, Christopher

AU - Stechele, Walter

AU - Auf, Adam El Sayed

AU - Maehle, Erik

N1 - Conference code: 86439

PY - 2010/12/1

Y1 - 2010/12/1

N2 - In a rescue operation walking robots offer a great deal of flexibility in traversing uneven terrain in an uncontrolled environment. For such a rescue robot each motion is a potential vital sign but the existing techniques for motion detection have severe limitations in dealing with strong levels of ego-motion on walking robots. This paper proposes an optical flow based method for the detection of moving objects using a single camera mounted on a hexapod robot for an application in a rescue scenario. The proposed algorithm estimates and compensates ego-motion to allow for object detection while the robot is moving. Our algorithm can deal with strong rotation and translation in 3D, using a first-order-flow motion model, with four degrees of freedom. Two alternative object detection methods using a 2D-histogram based vector clustering and motion compensated frame differencing respectively are examined for the detection of slow and fast moving objects. In addition to a software implementation, the system was implemented on an FPGA, enabling processing in real-time at 31 fps.

AB - In a rescue operation walking robots offer a great deal of flexibility in traversing uneven terrain in an uncontrolled environment. For such a rescue robot each motion is a potential vital sign but the existing techniques for motion detection have severe limitations in dealing with strong levels of ego-motion on walking robots. This paper proposes an optical flow based method for the detection of moving objects using a single camera mounted on a hexapod robot for an application in a rescue scenario. The proposed algorithm estimates and compensates ego-motion to allow for object detection while the robot is moving. Our algorithm can deal with strong rotation and translation in 3D, using a first-order-flow motion model, with four degrees of freedom. Two alternative object detection methods using a 2D-histogram based vector clustering and motion compensated frame differencing respectively are examined for the detection of slow and fast moving objects. In addition to a software implementation, the system was implemented on an FPGA, enabling processing in real-time at 31 fps.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-80052576109&origin=inward&txGid=a30cf25baffe97b6f910596deec33f98

U2 - 10.1109/SSRR.2010.5981554

DO - 10.1109/SSRR.2010.5981554

M3 - Conference contribution

SN - 978-1-4244-8898-8

T3 - International Workshop on Safety, Security, and Rescue Robotics

SP - 1

EP - 8

BT - 2010 IEEE Safety Security and Rescue Robotics

PB - IEEE

T2 - 8th IEEE International Workshop on Safety, Security, and Rescue Robotics <br/>

Y2 - 26 July 2010 through 30 July 2010

ER -

FPGA-based Real-time Moving Object Detection for Walking Robots

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this