Real-time rotationally invariant features for environmental feature detection by mobile robots and sensor networks

Andre Barczak; Chris Messom; Ravi Chemudugunta

doi:10.1109/ROSE.2007.4373961

Real-time rotationally invariant features for environmental feature detection by mobile robots and sensor networks

Andre Barczak, Chris Messom, Ravi Chemudugunta

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

1 Citation (Scopus)

Abstract

We introduce a mobile and/ or remote sensor framework for computationally fast rotationally invariant feature detection. The sensor and computational system is small enough to be carried by a mobile robot platform with a relatively low power requirement allowing the system to be deployed without the need for frequent recharges of the batteries. The rotationally invariant Haar-like features are introduced and evaluated both at feature level and in classifiers. Other invariant approaches such as moment based approaches do not offer the same discriminatory power as the Haar-like rotationally invariant features to detect complex objects such as hands and faces.

Original language	English
Title of host publication	ROSE 2007 - International Workshop on Robotic and Sensor Environments, Proceedings
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	19-24
Number of pages	6
ISBN (Print)	1424415276, 9781424415274
DOIs	https://doi.org/10.1109/ROSE.2007.4373961
Publication status	Published - 2007
Externally published	Yes
Event	2007 IEEE International Workshop on Robotic and Sensor Environments, ROSE 2007 - Ottawa, ON, Canada Duration: 12 Oct 2007 → 13 Oct 2007

Conference

Conference	2007 IEEE International Workshop on Robotic and Sensor Environments, ROSE 2007
Country/Territory	Canada
City	Ottawa, ON
Period	12/10/07 → 13/10/07

Keywords

Fast computation
Mobile sensor systems
Rotationally invariant features
Vision based senor networks

Access to Document

10.1109/ROSE.2007.4373961

Cite this

@inproceedings{d650857ea7cf41d2bad1a92eb0bf2ce4,

title = "Real-time rotationally invariant features for environmental feature detection by mobile robots and sensor networks",

abstract = "We introduce a mobile and/ or remote sensor framework for computationally fast rotationally invariant feature detection. The sensor and computational system is small enough to be carried by a mobile robot platform with a relatively low power requirement allowing the system to be deployed without the need for frequent recharges of the batteries. The rotationally invariant Haar-like features are introduced and evaluated both at feature level and in classifiers. Other invariant approaches such as moment based approaches do not offer the same discriminatory power as the Haar-like rotationally invariant features to detect complex objects such as hands and faces.",

keywords = "Fast computation, Mobile sensor systems, Rotationally invariant features, Vision based senor networks",

author = "Andre Barczak and Chris Messom and Ravi Chemudugunta",

year = "2007",

doi = "10.1109/ROSE.2007.4373961",

language = "English",

isbn = "1424415276",

pages = "19--24",

booktitle = "ROSE 2007 - International Workshop on Robotic and Sensor Environments, Proceedings",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "2007 IEEE International Workshop on Robotic and Sensor Environments, ROSE 2007 ; Conference date: 12-10-2007 Through 13-10-2007",

}

Barczak, A, Messom, C & Chemudugunta, R 2007, Real-time rotationally invariant features for environmental feature detection by mobile robots and sensor networks. in ROSE 2007 - International Workshop on Robotic and Sensor Environments, Proceedings. IEEE, Institute of Electrical and Electronics Engineers, pp. 19-24, 2007 IEEE International Workshop on Robotic and Sensor Environments, ROSE 2007, Ottawa, ON, Canada, 12/10/07. https://doi.org/10.1109/ROSE.2007.4373961

Real-time rotationally invariant features for environmental feature detection by mobile robots and sensor networks. / Barczak, Andre; Messom, Chris; Chemudugunta, Ravi.
ROSE 2007 - International Workshop on Robotic and Sensor Environments, Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2007. p. 19-24.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Real-time rotationally invariant features for environmental feature detection by mobile robots and sensor networks

AU - Barczak, Andre

AU - Messom, Chris

AU - Chemudugunta, Ravi

PY - 2007

Y1 - 2007

N2 - We introduce a mobile and/ or remote sensor framework for computationally fast rotationally invariant feature detection. The sensor and computational system is small enough to be carried by a mobile robot platform with a relatively low power requirement allowing the system to be deployed without the need for frequent recharges of the batteries. The rotationally invariant Haar-like features are introduced and evaluated both at feature level and in classifiers. Other invariant approaches such as moment based approaches do not offer the same discriminatory power as the Haar-like rotationally invariant features to detect complex objects such as hands and faces.

AB - We introduce a mobile and/ or remote sensor framework for computationally fast rotationally invariant feature detection. The sensor and computational system is small enough to be carried by a mobile robot platform with a relatively low power requirement allowing the system to be deployed without the need for frequent recharges of the batteries. The rotationally invariant Haar-like features are introduced and evaluated both at feature level and in classifiers. Other invariant approaches such as moment based approaches do not offer the same discriminatory power as the Haar-like rotationally invariant features to detect complex objects such as hands and faces.

KW - Fast computation

KW - Mobile sensor systems

KW - Rotationally invariant features

KW - Vision based senor networks

UR - http://www.scopus.com/inward/record.url?scp=48049100931&partnerID=8YFLogxK

U2 - 10.1109/ROSE.2007.4373961

DO - 10.1109/ROSE.2007.4373961

M3 - Conference Paper

AN - SCOPUS:48049100931

SN - 1424415276

SN - 9781424415274

SP - 19

EP - 24

BT - ROSE 2007 - International Workshop on Robotic and Sensor Environments, Proceedings

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - 2007 IEEE International Workshop on Robotic and Sensor Environments, ROSE 2007

Y2 - 12 October 2007 through 13 October 2007

ER -

Real-time rotationally invariant features for environmental feature detection by mobile robots and sensor networks

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this