Paper Info
Title
A proposal for semantic map representation and evaluation
Abstract
Semantic mapping is the incremental process of “mapping” relevant information of the world (i.e., spatial information, temporal events, agents and actions) to a formal description supported by a reasoning engine. Current research focuses on learning the semantic of environments based on their spatial location, geometry and appearance. Many methods to tackle this problem have been proposed, but the lack of a uniform representation, as well as standard benchmarking suites, prevents their direct comparison. In this paper, we propose a standardization in the representation of semantic maps, by defining an easily extensible formalism to be used on top of metric maps of the environments. Based on this, we describe the procedure to build a dataset (based on real sensor data) for benchmarking semantic mapping techniques, also hypothesizing some possible evaluation metrics. Nevertheless, by providing a tool for the construction of a semantic map ground truth, we aim at the contribution of the scientific community in acquiring data for populating the dataset.
Year
DOI
Venue
2015
10.1109/ECMR.2015.7324198
2015 European Conference on Mobile Robots (ECMR)
Keywords
Field
DocType
semantic map representation,semantic map evaluation,information mapping,spatial information,temporal events,temporal agents,temporal actions,formal description,reasoning engine,learning,spatial location,geometry,appearance,standard benchmarking suites,metric maps,real sensor data,semantic mapping techniques,semantic map ground truth
Computer vision,Semantic reasoner,Semantic mapping,Computer science,Metric map,Semantic grid,Artificial intelligence,Benchmarking,Semantic computing,Semantics,Semantic compression
Conference
Volume
Citations 
PageRank 
abs/1606.03719
3
0.43
References 
Authors
13
6
Name
Order
Citations
PageRank
Roberto Capobianco1409.78
Jacopo Serafin2121.67
Johann Dichtl330.43
Giorgio Grisetti42362130.91
Luca Iocchi51110111.38
Daniele Nardi65968545.67