Real-time diffuse behavior detection of pixels from outdoor image sequence

Brajesh B. Lal; Claus B. Madsen

doi:10.1109/IMVIP.2011.37

Real-time diffuse behavior detection of pixels from outdoor image sequence

Department of Architecture, Design and Media Technology

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

Abstract

We have proposed a technique to detect diffuse reflectance behavior pixels in real-time from a time-lapsed low dynamic range image sequence of the outdoor scene under few assumptions, unknown dynamic illumination and without using calibration objects. Each pixel analysis is done at the arrival of the every input image of the image sequence. In this process we incrementally compute new mean and standard deviation of each pixel on the arrival of the new input image and perform Z-test on each pixel for its outlier value. Shadow and specular candidature failure of a pixel along with its inbound Z-test result signifies pixel is having diffuse behavior.

Original language	English
Title of host publication	Proceedings - 2011 Irish Machine Vision and Image Processing Conference, IMVIP 2011
Number of pages	2
Publisher	IEEE
Publication date	2011
Pages	127-128
Article number	6167859
ISBN (Print)	978-0-7695-4629-2
DOIs	https://doi.org/10.1109/IMVIP.2011.37
Publication status	Published - 2011
Event	2011 15th Irish Machine Vision and Image Processing Conference, IMVIP 2011 - Dublin, Ireland Duration: 8 Sept 2011 → 9 Sept 2011

Conference

Conference	2011 15th Irish Machine Vision and Image Processing Conference, IMVIP 2011
Country/Territory	Ireland
City	Dublin
Period	08/09/2011 → 09/09/2011
Sponsor	IEEE Comput. Soc. Tech. Comm. Pattern Anal., Mach. Intell. (TCPAMI), Centre for Image Processing and Analysis, DCU, Office of Vice-President for Research (OVPR), DCU, Jaliko Ltd, TSI Flowmeters Ltd

Keywords

Augmented reality
Reflectance estimation
Stereo

Access to Document

10.1109/IMVIP.2011.37

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{37ed4a7b12cc48e0b30df0b6aaf0b9b1,

title = "Real-time diffuse behavior detection of pixels from outdoor image sequence",

abstract = "We have proposed a technique to detect diffuse reflectance behavior pixels in real-time from a time-lapsed low dynamic range image sequence of the outdoor scene under few assumptions, unknown dynamic illumination and without using calibration objects. Each pixel analysis is done at the arrival of the every input image of the image sequence. In this process we incrementally compute new mean and standard deviation of each pixel on the arrival of the new input image and perform Z-test on each pixel for its outlier value. Shadow and specular candidature failure of a pixel along with its inbound Z-test result signifies pixel is having diffuse behavior.",

keywords = "Augmented reality, Reflectance estimation, Stereo",

author = "Lal, {Brajesh B.} and Madsen, {Claus B.}",

year = "2011",

doi = "10.1109/IMVIP.2011.37",

language = "English",

isbn = "978-0-7695-4629-2",

pages = "127--128",

booktitle = "Proceedings - 2011 Irish Machine Vision and Image Processing Conference, IMVIP 2011",

publisher = "IEEE",

address = "United States",

note = "2011 15th Irish Machine Vision and Image Processing Conference, IMVIP 2011 ; Conference date: 08-09-2011 Through 09-09-2011",

}

TY - GEN

T1 - Real-time diffuse behavior detection of pixels from outdoor image sequence

AU - Lal, Brajesh B.

AU - Madsen, Claus B.

PY - 2011

Y1 - 2011

N2 - We have proposed a technique to detect diffuse reflectance behavior pixels in real-time from a time-lapsed low dynamic range image sequence of the outdoor scene under few assumptions, unknown dynamic illumination and without using calibration objects. Each pixel analysis is done at the arrival of the every input image of the image sequence. In this process we incrementally compute new mean and standard deviation of each pixel on the arrival of the new input image and perform Z-test on each pixel for its outlier value. Shadow and specular candidature failure of a pixel along with its inbound Z-test result signifies pixel is having diffuse behavior.

AB - We have proposed a technique to detect diffuse reflectance behavior pixels in real-time from a time-lapsed low dynamic range image sequence of the outdoor scene under few assumptions, unknown dynamic illumination and without using calibration objects. Each pixel analysis is done at the arrival of the every input image of the image sequence. In this process we incrementally compute new mean and standard deviation of each pixel on the arrival of the new input image and perform Z-test on each pixel for its outlier value. Shadow and specular candidature failure of a pixel along with its inbound Z-test result signifies pixel is having diffuse behavior.

KW - Augmented reality

KW - Reflectance estimation

KW - Stereo

UR - http://www.scopus.com/inward/record.url?scp=84880984006&partnerID=8YFLogxK

U2 - 10.1109/IMVIP.2011.37

DO - 10.1109/IMVIP.2011.37

M3 - Article in proceeding

AN - SCOPUS:84880984006

SN - 978-0-7695-4629-2

SP - 127

EP - 128

BT - Proceedings - 2011 Irish Machine Vision and Image Processing Conference, IMVIP 2011

PB - IEEE

T2 - 2011 15th Irish Machine Vision and Image Processing Conference, IMVIP 2011

Y2 - 8 September 2011 through 9 September 2011

ER -

Real-time diffuse behavior detection of pixels from outdoor image sequence

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this