Topological Semantic Mapping by Consolidation of Deep Visual Features

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE robotics and automation letters 2022-04, Vol.7 (2), p.4110-4117
Main Authors: Sousa, Ygor C. N., Bassani, Hansenclever F.
Format: Article
Language:English
Subjects:
Artificial neural networks
Bathrooms
Consolidation
Data acquisition
deep learning for visual perception
Feature extraction
Image recognition
Image segmentation
Mapping
Object recognition
representation learning
Representations
Semantic scene understanding
Semantics
Task analysis
Three-dimensional displays
topological mapping
Topology
transfer learning
Visual tasks
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2022.3149572