.png){kind=icon}
.png){kind=icon}
Return
Verification of road databases using multiple road models
.png){kind=icon}
PRE
AI
DOI：10.1016/j.isprsjprs.2017.05.005.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper a new approach for automatic road database verification based on remote sensing images is presented. In contrast to existing methods, the applicability of the new approach is not restricted to specific road types, context areas or geographic regions. This is achieved by combining several stateof-the-art road detection and road verification approaches that work well under different circumstances. Each one serves as an independent module representing a unique road model and a specific processing strategy. All modules provide independent solutions for the verification problem of each road object stored in the database in form of two probability distributions, the first one for the state of a database object (correct or incorrect), and a second one for the state of the underlying road model (applicable or not applicable). In accordance with the Dempster-Shafer Theory, both distributions are mapped to a new state space comprising the classes correct, incorrect and unknown. Statistical reasoning is applied to obtain the optimal state of a road object. A comparison with state-of-the-art road detection approaches using benchmark datasets shows that in general the proposed approach provides results with larger completeness. Additional experiments reveal that based on the proposed method a highly reliable semiautomatic approach for road data base verification can be designed. (C) 2017 Published by Elsevier B.V. on behalf of International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS).
Keywords:
Data fusion
Object classification
Image analysis
Geo-spatial databases
Road verification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
12.2
Papers:
4.4K
Citations:
3.2W