Cargando…
Research on Small Target Detection Technology Based on the MPH-SSD Algorithm
To address the problems of less semantic information and low measurement accuracy when the SSD (single shot multibox detector) algorithm detects small targets, an MPH-SSD (multiscale pyramid hybrid SSD) algorithm that integrates the attention mechanism and multiscale double pyramid feature enhanceme...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9722284/ https://www.ncbi.nlm.nih.gov/pubmed/36479022 http://dx.doi.org/10.1155/2022/9654930 |
_version_ | 1784843943291125760 |
---|---|
author | Lin, Qingyao Li, Su Wang, Rugang Wang, Yuanyuan Zhou, Feng Chen, Zhaofeng Guo, Naihong |
author_facet | Lin, Qingyao Li, Su Wang, Rugang Wang, Yuanyuan Zhou, Feng Chen, Zhaofeng Guo, Naihong |
author_sort | Lin, Qingyao |
collection | PubMed |
description | To address the problems of less semantic information and low measurement accuracy when the SSD (single shot multibox detector) algorithm detects small targets, an MPH-SSD (multiscale pyramid hybrid SSD) algorithm that integrates the attention mechanism and multiscale double pyramid feature enhancement is proposed in this paper. In this algorithm, firstly, the SSD algorithm is used to extract the feature map of small targets, and the shallow feature enhancement module is added to expand the receptive field of the shallow feature layer so as to enrich the semantic information in the feature layer for small targets and improve the expression ability of shallow features. The processed shallow feature layer and deep feature layer are fused at multiple scales, and the semantic information and location information are fused together to obtain a feature map with rich information. Secondly, the cascaded double pyramid structure is used to transfer from the deep layer to the shallow layer so that the context information between different feature layers can be effectively transferred and the feature information can be further strengthened. The hybrid attention mechanism can retain more context information in the network, adaptively adjust the feature map after addition and fusion, and reduce the background interference. The experimental analysis of MPH-SSD algorithm on Pascal VOC and MS COCO datasets shows that the map of this algorithm is 87.7% and 51.1%, respectively. The results show that the MPH-SSD algorithm can make better use of the feature information in the shallow feature layer in the process of small target detection and has better detection performance for small targets. |
format | Online Article Text |
id | pubmed-9722284 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Hindawi |
record_format | MEDLINE/PubMed |
spelling | pubmed-97222842022-12-06 Research on Small Target Detection Technology Based on the MPH-SSD Algorithm Lin, Qingyao Li, Su Wang, Rugang Wang, Yuanyuan Zhou, Feng Chen, Zhaofeng Guo, Naihong Comput Intell Neurosci Research Article To address the problems of less semantic information and low measurement accuracy when the SSD (single shot multibox detector) algorithm detects small targets, an MPH-SSD (multiscale pyramid hybrid SSD) algorithm that integrates the attention mechanism and multiscale double pyramid feature enhancement is proposed in this paper. In this algorithm, firstly, the SSD algorithm is used to extract the feature map of small targets, and the shallow feature enhancement module is added to expand the receptive field of the shallow feature layer so as to enrich the semantic information in the feature layer for small targets and improve the expression ability of shallow features. The processed shallow feature layer and deep feature layer are fused at multiple scales, and the semantic information and location information are fused together to obtain a feature map with rich information. Secondly, the cascaded double pyramid structure is used to transfer from the deep layer to the shallow layer so that the context information between different feature layers can be effectively transferred and the feature information can be further strengthened. The hybrid attention mechanism can retain more context information in the network, adaptively adjust the feature map after addition and fusion, and reduce the background interference. The experimental analysis of MPH-SSD algorithm on Pascal VOC and MS COCO datasets shows that the map of this algorithm is 87.7% and 51.1%, respectively. The results show that the MPH-SSD algorithm can make better use of the feature information in the shallow feature layer in the process of small target detection and has better detection performance for small targets. Hindawi 2022-11-28 /pmc/articles/PMC9722284/ /pubmed/36479022 http://dx.doi.org/10.1155/2022/9654930 Text en Copyright © 2022 Qingyao Lin et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Lin, Qingyao Li, Su Wang, Rugang Wang, Yuanyuan Zhou, Feng Chen, Zhaofeng Guo, Naihong Research on Small Target Detection Technology Based on the MPH-SSD Algorithm |
title | Research on Small Target Detection Technology Based on the MPH-SSD Algorithm |
title_full | Research on Small Target Detection Technology Based on the MPH-SSD Algorithm |
title_fullStr | Research on Small Target Detection Technology Based on the MPH-SSD Algorithm |
title_full_unstemmed | Research on Small Target Detection Technology Based on the MPH-SSD Algorithm |
title_short | Research on Small Target Detection Technology Based on the MPH-SSD Algorithm |
title_sort | research on small target detection technology based on the mph-ssd algorithm |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9722284/ https://www.ncbi.nlm.nih.gov/pubmed/36479022 http://dx.doi.org/10.1155/2022/9654930 |
work_keys_str_mv | AT linqingyao researchonsmalltargetdetectiontechnologybasedonthemphssdalgorithm AT lisu researchonsmalltargetdetectiontechnologybasedonthemphssdalgorithm AT wangrugang researchonsmalltargetdetectiontechnologybasedonthemphssdalgorithm AT wangyuanyuan researchonsmalltargetdetectiontechnologybasedonthemphssdalgorithm AT zhoufeng researchonsmalltargetdetectiontechnologybasedonthemphssdalgorithm AT chenzhaofeng researchonsmalltargetdetectiontechnologybasedonthemphssdalgorithm AT guonaihong researchonsmalltargetdetectiontechnologybasedonthemphssdalgorithm |