Cargando…
Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians
The detection of multi-scale pedestrians is one of the challenging tasks in pedestrian detection applications. Moreover, the task of small-scale pedestrian detection, i.e., accurate localization of pedestrians as low-scale target objects, can help solve the issue of occluded pedestrian detection as...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer Berlin Heidelberg
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9894518/ https://www.ncbi.nlm.nih.gov/pubmed/36748032 http://dx.doi.org/10.1007/s11554-023-01273-z |
_version_ | 1784881759348850688 |
---|---|
author | Alavianmehr, M. A. Helfroush, M. S. Danyali, H. Tashk, A. |
author_facet | Alavianmehr, M. A. Helfroush, M. S. Danyali, H. Tashk, A. |
author_sort | Alavianmehr, M. A. |
collection | PubMed |
description | The detection of multi-scale pedestrians is one of the challenging tasks in pedestrian detection applications. Moreover, the task of small-scale pedestrian detection, i.e., accurate localization of pedestrians as low-scale target objects, can help solve the issue of occluded pedestrian detection as well. In this paper, we present a fully convolutional neural network with a new architecture and an innovative, fully detailed supervision for semantic segmentation of pedestrians. The proposed network has been named butterfly network (BF-Net) because of its architecture analogous to a butterfly. The proposed BF-Net preserves the ability of simplicity so that it can process static images with a real-time image processing rate. The sub-path blocks embedded in the architecture of the proposed BF-Net provides a higher accuracy for detecting multi-scale objective targets including the small ones. The other advantage of the proposed architecture is replacing common batch normalization with conditional one. In conclusion, the experimental results of the proposed method demonstrate that the proposed network outperform the other state-of-the-art networks such as U-Net + + , U-Net3 + , Mask-RCNN, and Deeplabv3 + for the semantic segmentation of the pedestrians. |
format | Online Article Text |
id | pubmed-9894518 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Springer Berlin Heidelberg |
record_format | MEDLINE/PubMed |
spelling | pubmed-98945182023-02-02 Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians Alavianmehr, M. A. Helfroush, M. S. Danyali, H. Tashk, A. J Real Time Image Process Original Research Paper The detection of multi-scale pedestrians is one of the challenging tasks in pedestrian detection applications. Moreover, the task of small-scale pedestrian detection, i.e., accurate localization of pedestrians as low-scale target objects, can help solve the issue of occluded pedestrian detection as well. In this paper, we present a fully convolutional neural network with a new architecture and an innovative, fully detailed supervision for semantic segmentation of pedestrians. The proposed network has been named butterfly network (BF-Net) because of its architecture analogous to a butterfly. The proposed BF-Net preserves the ability of simplicity so that it can process static images with a real-time image processing rate. The sub-path blocks embedded in the architecture of the proposed BF-Net provides a higher accuracy for detecting multi-scale objective targets including the small ones. The other advantage of the proposed architecture is replacing common batch normalization with conditional one. In conclusion, the experimental results of the proposed method demonstrate that the proposed network outperform the other state-of-the-art networks such as U-Net + + , U-Net3 + , Mask-RCNN, and Deeplabv3 + for the semantic segmentation of the pedestrians. Springer Berlin Heidelberg 2023-02-02 2023 /pmc/articles/PMC9894518/ /pubmed/36748032 http://dx.doi.org/10.1007/s11554-023-01273-z Text en © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic. |
spellingShingle | Original Research Paper Alavianmehr, M. A. Helfroush, M. S. Danyali, H. Tashk, A. Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians |
title | Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians |
title_full | Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians |
title_fullStr | Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians |
title_full_unstemmed | Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians |
title_short | Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians |
title_sort | butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians |
topic | Original Research Paper |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9894518/ https://www.ncbi.nlm.nih.gov/pubmed/36748032 http://dx.doi.org/10.1007/s11554-023-01273-z |
work_keys_str_mv | AT alavianmehrma butterflynetworkaconvolutionalneuralnetworkwithanewarchitectureformultiscalesemanticsegmentationofpedestrians AT helfroushms butterflynetworkaconvolutionalneuralnetworkwithanewarchitectureformultiscalesemanticsegmentationofpedestrians AT danyalih butterflynetworkaconvolutionalneuralnetworkwithanewarchitectureformultiscalesemanticsegmentationofpedestrians AT tashka butterflynetworkaconvolutionalneuralnetworkwithanewarchitectureformultiscalesemanticsegmentationofpedestrians |