We present a novel point of interest (POI) construction approach based on street-level imagery (SLI) such as Google StreetView. Our method consists of: (1) the creation of a conflation map between an SLI trace and a vector map; (2) the detection of the corresponding buildings between the SLI scene and the conflation map; and (3) POI name extraction from a signboard in the SLI scene by user-interactive text recognition. Finally, a POI is generated through a combination of the POI name and attributes of the building object on a vector map. The proposed method showed recall of 92.99% and precision of 97.10% for real-world POIs.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Chillo GA, Jeongho LEE, Won Hee LEE, Kiyun YU, "New POI Construction with Street-Level Imagery" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 1, pp. 129-133, January 2013, doi: 10.1587/transinf.E96.D.129.
Abstract: We present a novel point of interest (POI) construction approach based on street-level imagery (SLI) such as Google StreetView. Our method consists of: (1) the creation of a conflation map between an SLI trace and a vector map; (2) the detection of the corresponding buildings between the SLI scene and the conflation map; and (3) POI name extraction from a signboard in the SLI scene by user-interactive text recognition. Finally, a POI is generated through a combination of the POI name and attributes of the building object on a vector map. The proposed method showed recall of 92.99% and precision of 97.10% for real-world POIs.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.129/_p
Copy
@ARTICLE{e96-d_1_129,
author={Chillo GA, Jeongho LEE, Won Hee LEE, Kiyun YU, },
journal={IEICE TRANSACTIONS on Information},
title={New POI Construction with Street-Level Imagery},
year={2013},
volume={E96-D},
number={1},
pages={129-133},
abstract={We present a novel point of interest (POI) construction approach based on street-level imagery (SLI) such as Google StreetView. Our method consists of: (1) the creation of a conflation map between an SLI trace and a vector map; (2) the detection of the corresponding buildings between the SLI scene and the conflation map; and (3) POI name extraction from a signboard in the SLI scene by user-interactive text recognition. Finally, a POI is generated through a combination of the POI name and attributes of the building object on a vector map. The proposed method showed recall of 92.99% and precision of 97.10% for real-world POIs.},
keywords={},
doi={10.1587/transinf.E96.D.129},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - New POI Construction with Street-Level Imagery
T2 - IEICE TRANSACTIONS on Information
SP - 129
EP - 133
AU - Chillo GA
AU - Jeongho LEE
AU - Won Hee LEE
AU - Kiyun YU
PY - 2013
DO - 10.1587/transinf.E96.D.129
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2013
AB - We present a novel point of interest (POI) construction approach based on street-level imagery (SLI) such as Google StreetView. Our method consists of: (1) the creation of a conflation map between an SLI trace and a vector map; (2) the detection of the corresponding buildings between the SLI scene and the conflation map; and (3) POI name extraction from a signboard in the SLI scene by user-interactive text recognition. Finally, a POI is generated through a combination of the POI name and attributes of the building object on a vector map. The proposed method showed recall of 92.99% and precision of 97.10% for real-world POIs.
ER -