New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection
In the field of computer vision, object detection consists of automatically finding objects in images by giving their positions. The most common fields of application are safety systems (pedestrian detection, identification of behavior) and control systems. Another important application is head/pers...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/17/5848 |
id |
doaj-3352425451c54254a412745b96e01d28 |
---|---|
record_format |
Article |
spelling |
doaj-3352425451c54254a412745b96e01d282021-09-09T13:56:30ZengMDPI AGSensors1424-82202021-08-01215848584810.3390/s21175848New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head DetectionMohamed Chouai0Petr Dolezel1Dominik Stursa2Zdenek Nemec3Faculty of Electrical Engineering and Informatics, University of Pardubice, 532 10 Pardubice, Czech RepublicFaculty of Electrical Engineering and Informatics, University of Pardubice, 532 10 Pardubice, Czech RepublicFaculty of Electrical Engineering and Informatics, University of Pardubice, 532 10 Pardubice, Czech RepublicFaculty of Electrical Engineering and Informatics, University of Pardubice, 532 10 Pardubice, Czech RepublicIn the field of computer vision, object detection consists of automatically finding objects in images by giving their positions. The most common fields of application are safety systems (pedestrian detection, identification of behavior) and control systems. Another important application is head/person detection, which is the primary material for road safety, rescue, surveillance, etc. In this study, we developed a new approach based on two parallel Deeplapv3+ to improve the performance of the person detection system. For the implementation of our semantic segmentation model, a working methodology with two types of ground truths extracted from the bounding boxes given by the original ground truths was established. The approach has been implemented in our two private datasets as well as in a public dataset. To show the performance of the proposed system, a comparative analysis was carried out on two deep learning semantic segmentation state-of-art models: SegNet and U-Net. By achieving 99.14% of global accuracy, the result demonstrated that the developed strategy could be an efficient way to build a deep neural network model for semantic segmentation. This strategy can be used, not only for the detection of the human head but also be applied in several semantic segmentation applications.https://www.mdpi.com/1424-8220/21/17/5848safety systemshead detectionhead countingsemantic segmentationparallel networksDeepLabv3+ |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mohamed Chouai Petr Dolezel Dominik Stursa Zdenek Nemec |
spellingShingle |
Mohamed Chouai Petr Dolezel Dominik Stursa Zdenek Nemec New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection Sensors safety systems head detection head counting semantic segmentation parallel networks DeepLabv3+ |
author_facet |
Mohamed Chouai Petr Dolezel Dominik Stursa Zdenek Nemec |
author_sort |
Mohamed Chouai |
title |
New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection |
title_short |
New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection |
title_full |
New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection |
title_fullStr |
New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection |
title_full_unstemmed |
New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection |
title_sort |
new end-to-end strategy based on deeplabv3+ semantic segmentation for human head detection |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-08-01 |
description |
In the field of computer vision, object detection consists of automatically finding objects in images by giving their positions. The most common fields of application are safety systems (pedestrian detection, identification of behavior) and control systems. Another important application is head/person detection, which is the primary material for road safety, rescue, surveillance, etc. In this study, we developed a new approach based on two parallel Deeplapv3+ to improve the performance of the person detection system. For the implementation of our semantic segmentation model, a working methodology with two types of ground truths extracted from the bounding boxes given by the original ground truths was established. The approach has been implemented in our two private datasets as well as in a public dataset. To show the performance of the proposed system, a comparative analysis was carried out on two deep learning semantic segmentation state-of-art models: SegNet and U-Net. By achieving 99.14% of global accuracy, the result demonstrated that the developed strategy could be an efficient way to build a deep neural network model for semantic segmentation. This strategy can be used, not only for the detection of the human head but also be applied in several semantic segmentation applications. |
topic |
safety systems head detection head counting semantic segmentation parallel networks DeepLabv3+ |
url |
https://www.mdpi.com/1424-8220/21/17/5848 |
work_keys_str_mv |
AT mohamedchouai newendtoendstrategybasedondeeplabv3semanticsegmentationforhumanheaddetection AT petrdolezel newendtoendstrategybasedondeeplabv3semanticsegmentationforhumanheaddetection AT dominikstursa newendtoendstrategybasedondeeplabv3semanticsegmentationforhumanheaddetection AT zdeneknemec newendtoendstrategybasedondeeplabv3semanticsegmentationforhumanheaddetection |
_version_ |
1717759385894125568 |