Cargando…

Comparison of RetinaNet-Based Single-Target Cascading and Multi-Target Detection Models for Administrative Regions in Network Map Pictures

There is a critical need for detection of administrative regions through network map pictures in map censorship tasks, which can be implemented by target detection technology. However, on map images there tend to be numerous administrative regions overlaying map annotations and symbols, thus making...

Descripción completa

Detalles Bibliográficos
Autores principales: Du, Kaixuan, Che, Xianghong, Wang, Yong, Liu, Jiping, Luo, An, Ma, Ruiyuan, Xu, Shenghua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9572589/
https://www.ncbi.nlm.nih.gov/pubmed/36236693
http://dx.doi.org/10.3390/s22197594
_version_ 1784810653214572544
author Du, Kaixuan
Che, Xianghong
Wang, Yong
Liu, Jiping
Luo, An
Ma, Ruiyuan
Xu, Shenghua
author_facet Du, Kaixuan
Che, Xianghong
Wang, Yong
Liu, Jiping
Luo, An
Ma, Ruiyuan
Xu, Shenghua
author_sort Du, Kaixuan
collection PubMed
description There is a critical need for detection of administrative regions through network map pictures in map censorship tasks, which can be implemented by target detection technology. However, on map images there tend to be numerous administrative regions overlaying map annotations and symbols, thus making it difficult to accurately detect each region. Using a RetinaNet-based target detection model integrating ResNet50 and a feature pyramid network (FPN), this study built a multi-target model and a single-target cascading model from three single-target models by taking Taiwan, Tibet, and the Chinese mainland as target examples. Two models were evaluated both in classification and localization accuracy to investigate their administrative region detection performance. The results show that the single-target cascading model was able to detect more administrative regions, with a higher f1_score of 0.86 and mAP of 0.85 compared to the multi-target model (0.56 and 0.52, respectively). Furthermore, location box size distribution from the single-target cascading model looks more similar to that of manually annotated box sizes, which signifies that the proposed cascading model is superior to the multi-target model. This study is promising in providing support for computer map reading and intelligent map censorship.
format Online
Article
Text
id pubmed-9572589
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95725892022-10-17 Comparison of RetinaNet-Based Single-Target Cascading and Multi-Target Detection Models for Administrative Regions in Network Map Pictures Du, Kaixuan Che, Xianghong Wang, Yong Liu, Jiping Luo, An Ma, Ruiyuan Xu, Shenghua Sensors (Basel) Article There is a critical need for detection of administrative regions through network map pictures in map censorship tasks, which can be implemented by target detection technology. However, on map images there tend to be numerous administrative regions overlaying map annotations and symbols, thus making it difficult to accurately detect each region. Using a RetinaNet-based target detection model integrating ResNet50 and a feature pyramid network (FPN), this study built a multi-target model and a single-target cascading model from three single-target models by taking Taiwan, Tibet, and the Chinese mainland as target examples. Two models were evaluated both in classification and localization accuracy to investigate their administrative region detection performance. The results show that the single-target cascading model was able to detect more administrative regions, with a higher f1_score of 0.86 and mAP of 0.85 compared to the multi-target model (0.56 and 0.52, respectively). Furthermore, location box size distribution from the single-target cascading model looks more similar to that of manually annotated box sizes, which signifies that the proposed cascading model is superior to the multi-target model. This study is promising in providing support for computer map reading and intelligent map censorship. MDPI 2022-10-07 /pmc/articles/PMC9572589/ /pubmed/36236693 http://dx.doi.org/10.3390/s22197594 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Du, Kaixuan
Che, Xianghong
Wang, Yong
Liu, Jiping
Luo, An
Ma, Ruiyuan
Xu, Shenghua
Comparison of RetinaNet-Based Single-Target Cascading and Multi-Target Detection Models for Administrative Regions in Network Map Pictures
title Comparison of RetinaNet-Based Single-Target Cascading and Multi-Target Detection Models for Administrative Regions in Network Map Pictures
title_full Comparison of RetinaNet-Based Single-Target Cascading and Multi-Target Detection Models for Administrative Regions in Network Map Pictures
title_fullStr Comparison of RetinaNet-Based Single-Target Cascading and Multi-Target Detection Models for Administrative Regions in Network Map Pictures
title_full_unstemmed Comparison of RetinaNet-Based Single-Target Cascading and Multi-Target Detection Models for Administrative Regions in Network Map Pictures
title_short Comparison of RetinaNet-Based Single-Target Cascading and Multi-Target Detection Models for Administrative Regions in Network Map Pictures
title_sort comparison of retinanet-based single-target cascading and multi-target detection models for administrative regions in network map pictures
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9572589/
https://www.ncbi.nlm.nih.gov/pubmed/36236693
http://dx.doi.org/10.3390/s22197594
work_keys_str_mv AT dukaixuan comparisonofretinanetbasedsingletargetcascadingandmultitargetdetectionmodelsforadministrativeregionsinnetworkmappictures
AT chexianghong comparisonofretinanetbasedsingletargetcascadingandmultitargetdetectionmodelsforadministrativeregionsinnetworkmappictures
AT wangyong comparisonofretinanetbasedsingletargetcascadingandmultitargetdetectionmodelsforadministrativeregionsinnetworkmappictures
AT liujiping comparisonofretinanetbasedsingletargetcascadingandmultitargetdetectionmodelsforadministrativeregionsinnetworkmappictures
AT luoan comparisonofretinanetbasedsingletargetcascadingandmultitargetdetectionmodelsforadministrativeregionsinnetworkmappictures
AT maruiyuan comparisonofretinanetbasedsingletargetcascadingandmultitargetdetectionmodelsforadministrativeregionsinnetworkmappictures
AT xushenghua comparisonofretinanetbasedsingletargetcascadingandmultitargetdetectionmodelsforadministrativeregionsinnetworkmappictures