Radar parameters.

<div><p>Millimeter-wave (mmWave) radar has become an important research direction in the field of object detection because of its characteristics of all-time, low cost, strong privacy and not affected by harsh weather conditions. Therefore, the research on millimeter wave radar object de...

Full description

Saved in:
Bibliographic Details
Main Author: Mengqi Yuan (4852555) (author)
Other Authors: Yajing Yuan (22278948) (author), Xiangqun Zhang (9183983) (author), Zhenghao Zhu (8812391) (author), Chenxi Zhao (5557568) (author), Xiangqian Gao (6109775) (author), Genyuan Du (22278951) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852016415780896768
author Mengqi Yuan (4852555)
author2 Yajing Yuan (22278948)
Xiangqun Zhang (9183983)
Zhenghao Zhu (8812391)
Chenxi Zhao (5557568)
Xiangqian Gao (6109775)
Genyuan Du (22278951)
author2_role author
author
author
author
author
author
author_facet Mengqi Yuan (4852555)
Yajing Yuan (22278948)
Xiangqun Zhang (9183983)
Zhenghao Zhu (8812391)
Chenxi Zhao (5557568)
Xiangqian Gao (6109775)
Genyuan Du (22278951)
author_role author
dc.creator.none.fl_str_mv Mengqi Yuan (4852555)
Yajing Yuan (22278948)
Xiangqun Zhang (9183983)
Zhenghao Zhu (8812391)
Chenxi Zhao (5557568)
Xiangqian Gao (6109775)
Genyuan Du (22278951)
dc.date.none.fl_str_mv 2025-09-19T21:26:43Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0332931.t002
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Radar_parameters_/30169116
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
three main improvements
strengthen feature extraction
recover fine details
optimize feature fusion
novel backbone network
model &# 8217
mean average precision
harsh weather conditions
great practical significance
500 annotated images
target detection scene
new target detection
xlink "> millimeter
publicly available 5
map ), precision
important research direction
6 %, respectively
mmwave yolov8n model
object detection
mmwave yolov8n
detection algorithm
strong privacy
sampling technique
results show
poor performance
method evaluation
low cost
intelligent security
including 2
deep learning
data modeling
classification framework
dc.title.none.fl_str_mv Radar parameters.
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <div><p>Millimeter-wave (mmWave) radar has become an important research direction in the field of object detection because of its characteristics of all-time, low cost, strong privacy and not affected by harsh weather conditions. Therefore, the research on millimeter wave radar object detection is of great practical significance for applications in the field of intelligent security and transportation. However, in the multi-target detection scene, millimeter wave radar still faces some problems, such as unable to effectively distinguish multiple objects and poor performance of detection algorithm. Focusing on the above problems, a new target detection and classification framework of S2DB-mmWave YOLOv8n, based on deep learning, is proposed to realize more accuracy. There are three main improvements. First, a novel backbone network was designed by incorporating new convolutional layers and the Simplified Spatial Pyramid Pooling - Fast (SimSPPF) module to strengthen feature extraction. Second, a dynamic up-sampling technique was introduced to improve the model’s ability to recover fine details. Finally, a bidirectional feature pyramid network (BiFPN) was integrated to optimize feature fusion, leveraging a bidirectional information transfer mechanism and an adaptive feature selection strategy. A publicly available 5-class object mmWave radar heatmap dataset, including 2,500 annotated images, were selected for data modeling and method evaluation. The results show that the mean average precision (mAP), precision and recall of the S2DB-mmWave YOLOv8n model were 93.1% mAP@0.5, 55.8% mAP@0.5:0.95, 89.4% and 90.6%, respectively, which is 3.3, 1.6, 4.5 and 7.7 percentage points higher than the baseline YOLOv8n network without increasing the parameter count.</p></div>
eu_rights_str_mv openAccess
id Manara_2c35dde33c43ebb1b3f750dfd63e958e
identifier_str_mv 10.1371/journal.pone.0332931.t002
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30169116
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Radar parameters.Mengqi Yuan (4852555)Yajing Yuan (22278948)Xiangqun Zhang (9183983)Zhenghao Zhu (8812391)Chenxi Zhao (5557568)Xiangqian Gao (6109775)Genyuan Du (22278951)Biological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedthree main improvementsstrengthen feature extractionrecover fine detailsoptimize feature fusionnovel backbone networkmodel &# 8217mean average precisionharsh weather conditionsgreat practical significance500 annotated imagestarget detection scenenew target detectionxlink "> millimeterpublicly available 5map ), precisionimportant research direction6 %, respectivelymmwave yolov8n modelobject detectionmmwave yolov8ndetection algorithmstrong privacysampling techniqueresults showpoor performancemethod evaluationlow costintelligent securityincluding 2deep learningdata modelingclassification framework<div><p>Millimeter-wave (mmWave) radar has become an important research direction in the field of object detection because of its characteristics of all-time, low cost, strong privacy and not affected by harsh weather conditions. Therefore, the research on millimeter wave radar object detection is of great practical significance for applications in the field of intelligent security and transportation. However, in the multi-target detection scene, millimeter wave radar still faces some problems, such as unable to effectively distinguish multiple objects and poor performance of detection algorithm. Focusing on the above problems, a new target detection and classification framework of S2DB-mmWave YOLOv8n, based on deep learning, is proposed to realize more accuracy. There are three main improvements. First, a novel backbone network was designed by incorporating new convolutional layers and the Simplified Spatial Pyramid Pooling - Fast (SimSPPF) module to strengthen feature extraction. Second, a dynamic up-sampling technique was introduced to improve the model’s ability to recover fine details. Finally, a bidirectional feature pyramid network (BiFPN) was integrated to optimize feature fusion, leveraging a bidirectional information transfer mechanism and an adaptive feature selection strategy. A publicly available 5-class object mmWave radar heatmap dataset, including 2,500 annotated images, were selected for data modeling and method evaluation. The results show that the mean average precision (mAP), precision and recall of the S2DB-mmWave YOLOv8n model were 93.1% mAP@0.5, 55.8% mAP@0.5:0.95, 89.4% and 90.6%, respectively, which is 3.3, 1.6, 4.5 and 7.7 percentage points higher than the baseline YOLOv8n network without increasing the parameter count.</p></div>2025-09-19T21:26:43ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0332931.t002https://figshare.com/articles/dataset/Radar_parameters_/30169116CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/301691162025-09-19T21:26:43Z
spellingShingle Radar parameters.
Mengqi Yuan (4852555)
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
three main improvements
strengthen feature extraction
recover fine details
optimize feature fusion
novel backbone network
model &# 8217
mean average precision
harsh weather conditions
great practical significance
500 annotated images
target detection scene
new target detection
xlink "> millimeter
publicly available 5
map ), precision
important research direction
6 %, respectively
mmwave yolov8n model
object detection
mmwave yolov8n
detection algorithm
strong privacy
sampling technique
results show
poor performance
method evaluation
low cost
intelligent security
including 2
deep learning
data modeling
classification framework
status_str publishedVersion
title Radar parameters.
title_full Radar parameters.
title_fullStr Radar parameters.
title_full_unstemmed Radar parameters.
title_short Radar parameters.
title_sort Radar parameters.
topic Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
three main improvements
strengthen feature extraction
recover fine details
optimize feature fusion
novel backbone network
model &# 8217
mean average precision
harsh weather conditions
great practical significance
500 annotated images
target detection scene
new target detection
xlink "> millimeter
publicly available 5
map ), precision
important research direction
6 %, respectively
mmwave yolov8n model
object detection
mmwave yolov8n
detection algorithm
strong privacy
sampling technique
results show
poor performance
method evaluation
low cost
intelligent security
including 2
deep learning
data modeling
classification framework