Topological Semantic Mapping by Consolidation of Deep Visual Features
- 8 February 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 4110-4117
Abstract
Many works in the recent literature introduce semantic mapping methods that use CNNs (Convolutional Neural Networks) to recognize semantic properties in images. The types of properties (eg.: room size, place category, and objects) and their classes (eg.: kitchen and bathroom, for place category) are usually predefined and restricted to a specific task. Thus, all the visual data acquired and processed during the construction of the maps are lost and only the recognized semantic properties remain on the maps. In contrast, this work introduces a topological semantic mapping method that uses deep visual features extracted by a CNN (GoogLeNet), from 2D images captured in multiple views of the environment as the robot operates, to create, through averages, consolidated representations of the visual features acquired in the regions covered by each topological node. These representations allow flexible recognition of semantic properties of the regions and use in other visual tasks. Experiments with a real-world indoor dataset showed that the method is able to consolidate the visual features of regions and use them to recognize objects and place categories as semantic properties, and to indicate the topological location of images, with very promising results.Keywords
All Related Versions
Funding Information
- Brazilian Coordination for the Improvement of Higher Education Personnel
- Foundation for the Support of Science and Technology of the State of Pernambuco (APQ-0880-1.03/14)
This publication has 25 references indexed in Scilit:
- Learning Deep NBNN Representations for Robust Place CategorizationIEEE Robotics and Automation Letters, 2017
- Comparison between Bayesian network classifiers and SVMs for semantic localizationExpert Systems with Applications, 2016
- Place categorization and semantic mapping on a mobile robot2016
- Semantic mapping for mobile robotics tasks: A surveyRobotics and Autonomous Systems, 2015
- Dimension Selective Self-Organizing Maps With Time-Varying Structure for Subspace and Projected ClusteringIEEE Transactions on Neural Networks and Learning Systems, 2014
- Self-organizing maps with a time-varying structureACM Computing Surveys, 2013
- Dimension Selective Self-Organizing Maps for clustering high dimensional data2012
- Large-scale semantic mapping and reasoning with heterogeneous modalities2012
- COLD: The CoSy Localization DatabaseThe International Journal of Robotics Research, 2009
- A comparison of uncertainty and sensitivity analysis results obtained with random and Latin hypercube samplingReliability Engineering & System Safety, 2005