A Mobile Vision System for Multimedia Tourist Applications in Urban Environments

L. Paletta; G. Fritz; C. Seifert; P. Luley; A. Almer

doi:10.1109/ITSC.2006.1706801

A Mobile Vision System for Multimedia Tourist Applications in Urban Environments

L. Paletta
, G. Fritz
, C. Seifert
, P. Luley
, A. Almer

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

7 Citations (Scopus)

Abstract

We present a computer vision system for the detection and identification of urban objects from mobile phone imagery, e.g., for the application of tourist information services. Recognition is based on MAP decision making over weak object hypotheses from local descriptor responses in the mobile imagery. We present an improvement over the standard SIFT key detector [1] by selecting only informative (i-SIFT) keys for descriptor matching. Selection is applied first to reduce the complexity of the object model and second to accelerate detection by selective filtering. We present results on the MPG-20 mobile phone imagery with severe illumination, scale and viewpoint changes in the images, performing with 98% accuracy in identification, efficient (100 background rejection, effficient (0 false alarm rate, and reliable quality of service under extreme illumination conditions, significantly improving standard SIFT based recognition in every sense, providing (important for mobile vision ) runtimes which are 8 (24) times faster for the MPG-20 (ZuBuD) database.

Original language	English
Title of host publication	Proceedings of the IEEE ITSC 2006
Subtitle of host publication	2006 IEEE Intelligent Transportation Systems Conference
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	566-572
ISBN (Print)	1-4244-0094-5
DOIs	https://doi.org/10.1109/ITSC.2006.1706801
Publication status	Published - 1 Sept 2006
Externally published	Yes
Event	9th IEEE International Conference on Intelligent Transportation Systems, ITSC 2006 - Toronto, Canada Duration: 17 Sept 2006 → 20 Sept 2006 Conference number: 9

Conference

Conference	9th IEEE International Conference on Intelligent Transportation Systems, ITSC 2006
Abbreviated title	ITSC
Country/Territory	Canada
City	Toronto
Period	17/09/06 → 20/09/06

Access to Document

10.1109/ITSC.2006.1706801

Cite this

@inproceedings{2ca261a2823441f7bdccbbd016a8a901,

title = "A Mobile Vision System for Multimedia Tourist Applications in Urban Environments",

abstract = "We present a computer vision system for the detection and identification of urban objects from mobile phone imagery, e.g., for the application of tourist information services. Recognition is based on MAP decision making over weak object hypotheses from local descriptor responses in the mobile imagery. We present an improvement over the standard SIFT key detector [1] by selecting only informative (i-SIFT) keys for descriptor matching. Selection is applied first to reduce the complexity of the object model and second to accelerate detection by selective filtering. We present results on the MPG-20 mobile phone imagery with severe illumination, scale and viewpoint changes in the images, performing with 98\% accuracy in identification, efficient (100 background rejection, effficient (0 false alarm rate, and reliable quality of service under extreme illumination conditions, significantly improving standard SIFT based recognition in every sense, providing (important for mobile vision ) runtimes which are 8 (24) times faster for the MPG-20 (ZuBuD) database.",

author = "L. Paletta and G. Fritz and C. Seifert and P. Luley and A. Almer",

year = "2006",

month = sep,

day = "1",

doi = "10.1109/ITSC.2006.1706801",

language = "English",

isbn = "1-4244-0094-5",

pages = "566--572",

booktitle = "Proceedings of the IEEE ITSC 2006",

publisher = "IEEE",

address = "United States",

note = "9th IEEE International Conference on Intelligent Transportation Systems, ITSC 2006, ITSC ; Conference date: 17-09-2006 Through 20-09-2006",

}

Paletta, L, Fritz, G, Seifert, C, Luley, P & Almer, A 2006, A Mobile Vision System for Multimedia Tourist Applications in Urban Environments. in Proceedings of the IEEE ITSC 2006: 2006 IEEE Intelligent Transportation Systems Conference. IEEE, Piscataway, NJ, pp. 566-572, 9th IEEE International Conference on Intelligent Transportation Systems, ITSC 2006, Toronto, Ontario, Canada, 17/09/06. https://doi.org/10.1109/ITSC.2006.1706801

A Mobile Vision System for Multimedia Tourist Applications in Urban Environments. / Paletta, L.; Fritz, G.; Seifert, C. et al.
Proceedings of the IEEE ITSC 2006: 2006 IEEE Intelligent Transportation Systems Conference. Piscataway, NJ: IEEE, 2006. p. 566-572.

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

TY - GEN

T1 - A Mobile Vision System for Multimedia Tourist Applications in Urban Environments

AU - Paletta, L.

AU - Fritz, G.

AU - Seifert, C.

AU - Luley, P.

AU - Almer, A.

N1 - Conference code: 9

PY - 2006/9/1

Y1 - 2006/9/1

N2 - We present a computer vision system for the detection and identification of urban objects from mobile phone imagery, e.g., for the application of tourist information services. Recognition is based on MAP decision making over weak object hypotheses from local descriptor responses in the mobile imagery. We present an improvement over the standard SIFT key detector [1] by selecting only informative (i-SIFT) keys for descriptor matching. Selection is applied first to reduce the complexity of the object model and second to accelerate detection by selective filtering. We present results on the MPG-20 mobile phone imagery with severe illumination, scale and viewpoint changes in the images, performing with 98% accuracy in identification, efficient (100 background rejection, effficient (0 false alarm rate, and reliable quality of service under extreme illumination conditions, significantly improving standard SIFT based recognition in every sense, providing (important for mobile vision ) runtimes which are 8 (24) times faster for the MPG-20 (ZuBuD) database.

AB - We present a computer vision system for the detection and identification of urban objects from mobile phone imagery, e.g., for the application of tourist information services. Recognition is based on MAP decision making over weak object hypotheses from local descriptor responses in the mobile imagery. We present an improvement over the standard SIFT key detector [1] by selecting only informative (i-SIFT) keys for descriptor matching. Selection is applied first to reduce the complexity of the object model and second to accelerate detection by selective filtering. We present results on the MPG-20 mobile phone imagery with severe illumination, scale and viewpoint changes in the images, performing with 98% accuracy in identification, efficient (100 background rejection, effficient (0 false alarm rate, and reliable quality of service under extreme illumination conditions, significantly improving standard SIFT based recognition in every sense, providing (important for mobile vision ) runtimes which are 8 (24) times faster for the MPG-20 (ZuBuD) database.

U2 - 10.1109/ITSC.2006.1706801

DO - 10.1109/ITSC.2006.1706801

M3 - Conference contribution

SN - 1-4244-0094-5

SP - 566

EP - 572

BT - Proceedings of the IEEE ITSC 2006

PB - IEEE

CY - Piscataway, NJ

T2 - 9th IEEE International Conference on Intelligent Transportation Systems, ITSC 2006

Y2 - 17 September 2006 through 20 September 2006

ER -

A Mobile Vision System for Multimedia Tourist Applications in Urban Environments

Abstract

Conference

Access to Document

Fingerprint

Cite this