Indoor signage detection based on saliency map and bipartite graph matching

Shuihua Wang; Yingli Tian

doi:10.1109/BIBMW.2011.6112422

Indoor signage detection based on saliency map and bipartite graph matching

Shuihua Wang^*, Yingli Tian

^*Corresponding author for this work

City University of New York

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

9 Citations (Scopus)

Abstract

Object detection plays a very important role in many applications such as image retrieval, surveillance, robot navigation, wayfinding, etc. In this paper, we propose a novel approach to detect indoor signage to help blind people find their destinations in unfamiliar environments. Our method first extracts the attended areas by using a saliency map. Then the signage is detected in the attended areas by using bipartite graph matching. The proposed method can handle multiple signage detection. Experimental results on our collected indoor signage dataset demonstrate the effectiveness and efficiency of our proposed method. Furthermore, saliency maps could eliminate the interference information and improve the accuracy of the detection results.

Original language	English
Title of host publication	2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011
Pages	518-525
Number of pages	8
DOIs	https://doi.org/10.1109/BIBMW.2011.6112422
Publication status	Published - 2011
Externally published	Yes
Event	2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011 - Atlanta, GA, United States Duration: 12 Nov 2011 → 15 Nov 2011

Publication series

Name	2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011

Conference

Conference	2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011
Country/Territory	United States
City	Atlanta, GA
Period	12/11/11 → 15/11/11

Access to Document

10.1109/BIBMW.2011.6112422

Cite this

@inproceedings{0861673502984708816ef8790b6a66db,

title = "Indoor signage detection based on saliency map and bipartite graph matching",

abstract = "Object detection plays a very important role in many applications such as image retrieval, surveillance, robot navigation, wayfinding, etc. In this paper, we propose a novel approach to detect indoor signage to help blind people find their destinations in unfamiliar environments. Our method first extracts the attended areas by using a saliency map. Then the signage is detected in the attended areas by using bipartite graph matching. The proposed method can handle multiple signage detection. Experimental results on our collected indoor signage dataset demonstrate the effectiveness and efficiency of our proposed method. Furthermore, saliency maps could eliminate the interference information and improve the accuracy of the detection results.",

author = "Shuihua Wang and Yingli Tian",

year = "2011",

doi = "10.1109/BIBMW.2011.6112422",

language = "English",

isbn = "9781457716133",

series = "2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011",

pages = "518--525",

booktitle = "2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011",

note = "2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011 ; Conference date: 12-11-2011 Through 15-11-2011",

}

Wang, S & Tian, Y 2011, Indoor signage detection based on saliency map and bipartite graph matching. in 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011., 6112422, 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011, pp. 518-525, 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011, Atlanta, GA, United States, 12/11/11. https://doi.org/10.1109/BIBMW.2011.6112422

Indoor signage detection based on saliency map and bipartite graph matching. / Wang, Shuihua; Tian, Yingli.
2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011. 2011. p. 518-525 6112422 (2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011).

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

TY - GEN

T1 - Indoor signage detection based on saliency map and bipartite graph matching

AU - Wang, Shuihua

AU - Tian, Yingli

PY - 2011

Y1 - 2011

N2 - Object detection plays a very important role in many applications such as image retrieval, surveillance, robot navigation, wayfinding, etc. In this paper, we propose a novel approach to detect indoor signage to help blind people find their destinations in unfamiliar environments. Our method first extracts the attended areas by using a saliency map. Then the signage is detected in the attended areas by using bipartite graph matching. The proposed method can handle multiple signage detection. Experimental results on our collected indoor signage dataset demonstrate the effectiveness and efficiency of our proposed method. Furthermore, saliency maps could eliminate the interference information and improve the accuracy of the detection results.

AB - Object detection plays a very important role in many applications such as image retrieval, surveillance, robot navigation, wayfinding, etc. In this paper, we propose a novel approach to detect indoor signage to help blind people find their destinations in unfamiliar environments. Our method first extracts the attended areas by using a saliency map. Then the signage is detected in the attended areas by using bipartite graph matching. The proposed method can handle multiple signage detection. Experimental results on our collected indoor signage dataset demonstrate the effectiveness and efficiency of our proposed method. Furthermore, saliency maps could eliminate the interference information and improve the accuracy of the detection results.

UR - http://www.scopus.com/inward/record.url?scp=84862946866&partnerID=8YFLogxK

U2 - 10.1109/BIBMW.2011.6112422

DO - 10.1109/BIBMW.2011.6112422

M3 - Conference Proceeding

AN - SCOPUS:84862946866

SN - 9781457716133

T3 - 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011

SP - 518

EP - 525

BT - 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011

T2 - 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011

Y2 - 12 November 2011 through 15 November 2011

ER -

Indoor signage detection based on saliency map and bipartite graph matching

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this