Scene Retrieval for Contextual Visual Mapping
Visual navigation localizes a query place image against a reference database of place images, also known as a `visual map'. Localization accuracy requirements for specific areas of the visual map, `scene classes', vary according to the context of the environment and task. State-of-the-art...
Main Authors: | , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2102.12728 https://arxiv.org/abs/2102.12728 |
id |
ftdatacite:10.48550/arxiv.2102.12728 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2102.12728 2023-05-15T17:24:41+02:00 Scene Retrieval for Contextual Visual Mapping Smith, William H. B. Milford, Michael McDonald-Maier, Klaus D. Ehsan, Shoaib 2021 https://dx.doi.org/10.48550/arxiv.2102.12728 https://arxiv.org/abs/2102.12728 unknown arXiv Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 CC-BY Computer Vision and Pattern Recognition cs.CV Robotics cs.RO FOS Computer and information sciences Article CreativeWork article Preprint 2021 ftdatacite https://doi.org/10.48550/arxiv.2102.12728 2022-03-10T14:54:21Z Visual navigation localizes a query place image against a reference database of place images, also known as a `visual map'. Localization accuracy requirements for specific areas of the visual map, `scene classes', vary according to the context of the environment and task. State-of-the-art visual mapping is unable to reflect these requirements by explicitly targetting scene classes for inclusion in the map. Four different scene classes, including pedestrian crossings and stations, are identified in each of the Nordland and St. Lucia datasets. Instead of re-training separate scene classifiers which struggle with these overlapping scene classes we make our first contribution: defining the problem of `scene retrieval'. Scene retrieval extends image retrieval to classification of scenes defined at test time by associating a single query image to reference images of scene classes. Our second contribution is a triplet-trained convolutional neural network (CNN) to address this problem which increases scene classification accuracy by up to 7% against state-of-the-art networks pre-trained for scene recognition. The second contribution is an algorithm `DMC' that combines our scene classification with distance and memorability for visual mapping. Our analysis shows that DMC includes 64% more images of our chosen scene classes in a visual map than just using distance interval mapping. State-of-the-art visual place descriptors AMOS-Net, Hybrid-Net and NetVLAD are finally used to show that DMC improves scene class localization accuracy by a mean of 3% and localization accuracy of the remaining map images by a mean of 10% across both datasets. : 8 page paper on visual place recogniton and scene classification Article in Journal/Newspaper Nordland Nordland Nordland DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computer Vision and Pattern Recognition cs.CV Robotics cs.RO FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV Robotics cs.RO FOS Computer and information sciences Smith, William H. B. Milford, Michael McDonald-Maier, Klaus D. Ehsan, Shoaib Scene Retrieval for Contextual Visual Mapping |
topic_facet |
Computer Vision and Pattern Recognition cs.CV Robotics cs.RO FOS Computer and information sciences |
description |
Visual navigation localizes a query place image against a reference database of place images, also known as a `visual map'. Localization accuracy requirements for specific areas of the visual map, `scene classes', vary according to the context of the environment and task. State-of-the-art visual mapping is unable to reflect these requirements by explicitly targetting scene classes for inclusion in the map. Four different scene classes, including pedestrian crossings and stations, are identified in each of the Nordland and St. Lucia datasets. Instead of re-training separate scene classifiers which struggle with these overlapping scene classes we make our first contribution: defining the problem of `scene retrieval'. Scene retrieval extends image retrieval to classification of scenes defined at test time by associating a single query image to reference images of scene classes. Our second contribution is a triplet-trained convolutional neural network (CNN) to address this problem which increases scene classification accuracy by up to 7% against state-of-the-art networks pre-trained for scene recognition. The second contribution is an algorithm `DMC' that combines our scene classification with distance and memorability for visual mapping. Our analysis shows that DMC includes 64% more images of our chosen scene classes in a visual map than just using distance interval mapping. State-of-the-art visual place descriptors AMOS-Net, Hybrid-Net and NetVLAD are finally used to show that DMC improves scene class localization accuracy by a mean of 3% and localization accuracy of the remaining map images by a mean of 10% across both datasets. : 8 page paper on visual place recogniton and scene classification |
format |
Article in Journal/Newspaper |
author |
Smith, William H. B. Milford, Michael McDonald-Maier, Klaus D. Ehsan, Shoaib |
author_facet |
Smith, William H. B. Milford, Michael McDonald-Maier, Klaus D. Ehsan, Shoaib |
author_sort |
Smith, William H. B. |
title |
Scene Retrieval for Contextual Visual Mapping |
title_short |
Scene Retrieval for Contextual Visual Mapping |
title_full |
Scene Retrieval for Contextual Visual Mapping |
title_fullStr |
Scene Retrieval for Contextual Visual Mapping |
title_full_unstemmed |
Scene Retrieval for Contextual Visual Mapping |
title_sort |
scene retrieval for contextual visual mapping |
publisher |
arXiv |
publishDate |
2021 |
url |
https://dx.doi.org/10.48550/arxiv.2102.12728 https://arxiv.org/abs/2102.12728 |
genre |
Nordland Nordland Nordland |
genre_facet |
Nordland Nordland Nordland |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.48550/arxiv.2102.12728 |
_version_ |
1766115792196206592 |