YOLOP-MVF: A Multi-Task Autonomous Driving Perception Detection Method Based on Multi Scale Feature Weighted Fusion

To address challenges such as large-scale variations, background interference, and occlusions in multi-task autonomous driving perception, this paper proposes YOLOP-MVF, a multi-task detection framework based on multi-scale feature weighting fusion. The model integrates a sub-pixel 3D fusion module...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanqiu Niu, Jing Zhang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11008744/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849471985501863936
author Yanqiu Niu
Jing Zhang
author_facet Yanqiu Niu
Jing Zhang
author_sort Yanqiu Niu
collection DOAJ
description To address challenges such as large-scale variations, background interference, and occlusions in multi-task autonomous driving perception, this paper proposes YOLOP-MVF, a multi-task detection framework based on multi-scale feature weighting fusion. The model integrates a sub-pixel 3D fusion module and a triple feature encoding module to enhance the representation of multi-scale features. A multi-scale convolutional attention-weighting mechanism is further introduced to adaptively emphasize critical spatial information. To improve feature extraction flexibility, deformable convolutions are incorporated, enabling dynamic sampling based on input characteristics. Additionally, the Powerful-IoU loss is employed to guide anchor box regression with adaptive penalty and gradient regulation, accelerating convergence. Experimental results on the BDD100K dataset demonstrate that YOLOP-MVF outperforms baseline models, achieving improvements of 1.2% in mIoU, 8.8% in accuracy, and 4.7% in mAP50, validating its effectiveness for robust multi-task perception in complex driving scenarios.
format Article
id doaj-art-83b3692788524cfd8de990398c3e08de
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-83b3692788524cfd8de990398c3e08de2025-08-20T03:24:39ZengIEEEIEEE Access2169-35362025-01-0113913749138310.1109/ACCESS.2025.357233111008744YOLOP-MVF: A Multi-Task Autonomous Driving Perception Detection Method Based on Multi Scale Feature Weighted FusionYanqiu Niu0https://orcid.org/0009-0009-8422-8988Jing Zhang1https://orcid.org/0000-0002-7531-7032Department of Basic Sciences, Jilin University of Architecture and Technology, Changchun, ChinaDepartment of Public Instruction, Anhui Vocational College of City Management, Hefei, ChinaTo address challenges such as large-scale variations, background interference, and occlusions in multi-task autonomous driving perception, this paper proposes YOLOP-MVF, a multi-task detection framework based on multi-scale feature weighting fusion. The model integrates a sub-pixel 3D fusion module and a triple feature encoding module to enhance the representation of multi-scale features. A multi-scale convolutional attention-weighting mechanism is further introduced to adaptively emphasize critical spatial information. To improve feature extraction flexibility, deformable convolutions are incorporated, enabling dynamic sampling based on input characteristics. Additionally, the Powerful-IoU loss is employed to guide anchor box regression with adaptive penalty and gradient regulation, accelerating convergence. Experimental results on the BDD100K dataset demonstrate that YOLOP-MVF outperforms baseline models, achieving improvements of 1.2% in mIoU, 8.8% in accuracy, and 4.7% in mAP50, validating its effectiveness for robust multi-task perception in complex driving scenarios.https://ieeexplore.ieee.org/document/11008744/Autonomous drivingmultitask learningdrivable area segmentationlane detectionvehicle detection
spellingShingle Yanqiu Niu
Jing Zhang
YOLOP-MVF: A Multi-Task Autonomous Driving Perception Detection Method Based on Multi Scale Feature Weighted Fusion
IEEE Access
Autonomous driving
multitask learning
drivable area segmentation
lane detection
vehicle detection
title YOLOP-MVF: A Multi-Task Autonomous Driving Perception Detection Method Based on Multi Scale Feature Weighted Fusion
title_full YOLOP-MVF: A Multi-Task Autonomous Driving Perception Detection Method Based on Multi Scale Feature Weighted Fusion
title_fullStr YOLOP-MVF: A Multi-Task Autonomous Driving Perception Detection Method Based on Multi Scale Feature Weighted Fusion
title_full_unstemmed YOLOP-MVF: A Multi-Task Autonomous Driving Perception Detection Method Based on Multi Scale Feature Weighted Fusion
title_short YOLOP-MVF: A Multi-Task Autonomous Driving Perception Detection Method Based on Multi Scale Feature Weighted Fusion
title_sort yolop mvf a multi task autonomous driving perception detection method based on multi scale feature weighted fusion
topic Autonomous driving
multitask learning
drivable area segmentation
lane detection
vehicle detection
url https://ieeexplore.ieee.org/document/11008744/
work_keys_str_mv AT yanqiuniu yolopmvfamultitaskautonomousdrivingperceptiondetectionmethodbasedonmultiscalefeatureweightedfusion
AT jingzhang yolopmvfamultitaskautonomousdrivingperceptiondetectionmethodbasedonmultiscalefeatureweightedfusion