A Small Target Pedestrian Detection Model Based on Autonomous Driving

Since small-target pedestrians account for a small proportion of pixels in images and lack texture features, the feature information of small-target pedestrians is often ignored in the feature extraction process, leading to reduced accuracy and poor robustness. To improve the accuracy of small-targe...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Zhang, Shuaifeng Zhang, Dongrong Xin, Dewang Chen
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/2023/5349965
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467830715547648
author Yang Zhang
Shuaifeng Zhang
Dongrong Xin
Dewang Chen
author_facet Yang Zhang
Shuaifeng Zhang
Dongrong Xin
Dewang Chen
author_sort Yang Zhang
collection DOAJ
description Since small-target pedestrians account for a small proportion of pixels in images and lack texture features, the feature information of small-target pedestrians is often ignored in the feature extraction process, leading to reduced accuracy and poor robustness. To improve the accuracy of small-target pedestrian detection and the anti-interference ability of the model, a small-target pedestrian detection model that fuses residual networks and feature pyramids is proposed. First, a residual block with a discard layer is constructed to replace the standard residual block in the residual network structure to reduce the complexity of the model computation process and solve the problems of gradient disappearance and explosion in the deep network. Then, feature selection and feature alignment modules are added to the lateral connection part of the feature pyramid to enhance important pedestrian features in the input image, and the multiscale feature fusion capability of the model is enhanced for small-target pedestrians, thereby improving the detection accuracy of small-target pedestrians and solving the problems of feature misalignment and ignored multiscale features in the feature pyramid network. Finally, a cascaded autofocus query module is proposed to increase the inference speed of the feature pyramid network through focusing and querying, thus improving the performance and efficiency of small-target pedestrian detection. The experimental results show that the proposed model achieves better detection results than previous models.
format Article
id doaj-art-e6aec3ef2dd44207bbae93f0cb36e6e5
institution Kabale University
issn 2042-3195
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series Journal of Advanced Transportation
spelling doaj-art-e6aec3ef2dd44207bbae93f0cb36e6e52025-08-20T03:26:03ZengWileyJournal of Advanced Transportation2042-31952023-01-01202310.1155/2023/5349965A Small Target Pedestrian Detection Model Based on Autonomous DrivingYang Zhang0Shuaifeng Zhang1Dongrong Xin2Dewang Chen3School of TransportationSchool of TransportationSchool of TransportationSchool of TransportationSince small-target pedestrians account for a small proportion of pixels in images and lack texture features, the feature information of small-target pedestrians is often ignored in the feature extraction process, leading to reduced accuracy and poor robustness. To improve the accuracy of small-target pedestrian detection and the anti-interference ability of the model, a small-target pedestrian detection model that fuses residual networks and feature pyramids is proposed. First, a residual block with a discard layer is constructed to replace the standard residual block in the residual network structure to reduce the complexity of the model computation process and solve the problems of gradient disappearance and explosion in the deep network. Then, feature selection and feature alignment modules are added to the lateral connection part of the feature pyramid to enhance important pedestrian features in the input image, and the multiscale feature fusion capability of the model is enhanced for small-target pedestrians, thereby improving the detection accuracy of small-target pedestrians and solving the problems of feature misalignment and ignored multiscale features in the feature pyramid network. Finally, a cascaded autofocus query module is proposed to increase the inference speed of the feature pyramid network through focusing and querying, thus improving the performance and efficiency of small-target pedestrian detection. The experimental results show that the proposed model achieves better detection results than previous models.http://dx.doi.org/10.1155/2023/5349965
spellingShingle Yang Zhang
Shuaifeng Zhang
Dongrong Xin
Dewang Chen
A Small Target Pedestrian Detection Model Based on Autonomous Driving
Journal of Advanced Transportation
title A Small Target Pedestrian Detection Model Based on Autonomous Driving
title_full A Small Target Pedestrian Detection Model Based on Autonomous Driving
title_fullStr A Small Target Pedestrian Detection Model Based on Autonomous Driving
title_full_unstemmed A Small Target Pedestrian Detection Model Based on Autonomous Driving
title_short A Small Target Pedestrian Detection Model Based on Autonomous Driving
title_sort small target pedestrian detection model based on autonomous driving
url http://dx.doi.org/10.1155/2023/5349965
work_keys_str_mv AT yangzhang asmalltargetpedestriandetectionmodelbasedonautonomousdriving
AT shuaifengzhang asmalltargetpedestriandetectionmodelbasedonautonomousdriving
AT dongrongxin asmalltargetpedestriandetectionmodelbasedonautonomousdriving
AT dewangchen asmalltargetpedestriandetectionmodelbasedonautonomousdriving
AT yangzhang smalltargetpedestriandetectionmodelbasedonautonomousdriving
AT shuaifengzhang smalltargetpedestriandetectionmodelbasedonautonomousdriving
AT dongrongxin smalltargetpedestriandetectionmodelbasedonautonomousdriving
AT dewangchen smalltargetpedestriandetectionmodelbasedonautonomousdriving