Improving YoloPX using YoloP and Yolov8 for panoptic driving perception

Autonomous driving technology (ADS) has seen significant advancements over the past decade, with car manufacturers investing heavily in its development to meet the growing demand for safer, more efficient, and eco-friendly transportation solutions. The panoptic driving perception system is central t...

Full description

Bibliographic Details
Main Authors:	Xie, Yumeng, Manshor, Noridayu, Husin, Nor Azura, Liu, Chengzhi
Format:	Article
Language:	English
Published:	Politeknik Negeri Padang 2025
Online Access:	http://psasir.upm.edu.my/id/eprint/118822/ http://psasir.upm.edu.my/id/eprint/118822/1/118822.pdf

_version_	1848867797767028736
author	Xie, Yumeng Manshor, Noridayu Husin, Nor Azura Liu, Chengzhi
author_facet	Xie, Yumeng Manshor, Noridayu Husin, Nor Azura Liu, Chengzhi
author_sort	Xie, Yumeng
building	UPM Institutional Repository
collection	Online Access
description	Autonomous driving technology (ADS) has seen significant advancements over the past decade, with car manufacturers investing heavily in its development to meet the growing demand for safer, more efficient, and eco-friendly transportation solutions. The panoptic driving perception system is central to ADS, essential for accurately interpreting the driving environment. This system requires high precision, lightweight design, and real-time responsiveness to detect surrounding vehicles, lane lines, and drivable areas effectively. This study introduces an enhanced YOLOPX model that combines YOLOP and YOLOv8 to create an adaptive multi-task learning network capable of traffic object detection, drivable area segmentation, and lane detection. The model integrates YOLOP's detection head with YOLOPX's anchor-free detection head to improve generalization, incorporates YOLOv8's advanced backbone structure to enhance feature extraction accuracy, and retains YOLOP's three-neck architecture to optimize multi-task processing. The improved model employs a mode loss function for segmentation tasks, enhancing generalization and improving lane detection accuracy. Experiments conducted using the BDD100k dataset demonstrated the model's effectiveness: achieving 98.8% accuracy and 27.6% IoU for lane line detection, 90.4% mIoU for drivable area segmentation, and 85.9% recall and 76.9% mAP50 for traffic object detection. This model represents a significant advancement in ADS, enhancing both the safety and reliability of autonomous vehicles.
first_indexed	2025-11-15T14:42:13Z
format	Article
id	upm-118822
institution	Universiti Putra Malaysia
institution_category	Local University
language	English
last_indexed	2025-11-15T14:42:13Z
publishDate	2025
publisher	Politeknik Negeri Padang
recordtype	eprints
repository_type	Digital Repository
spelling	upm-1188222025-07-25T01:59:56Z http://psasir.upm.edu.my/id/eprint/118822/ Improving YoloPX using YoloP and Yolov8 for panoptic driving perception Xie, Yumeng Manshor, Noridayu Husin, Nor Azura Liu, Chengzhi Autonomous driving technology (ADS) has seen significant advancements over the past decade, with car manufacturers investing heavily in its development to meet the growing demand for safer, more efficient, and eco-friendly transportation solutions. The panoptic driving perception system is central to ADS, essential for accurately interpreting the driving environment. This system requires high precision, lightweight design, and real-time responsiveness to detect surrounding vehicles, lane lines, and drivable areas effectively. This study introduces an enhanced YOLOPX model that combines YOLOP and YOLOv8 to create an adaptive multi-task learning network capable of traffic object detection, drivable area segmentation, and lane detection. The model integrates YOLOP's detection head with YOLOPX's anchor-free detection head to improve generalization, incorporates YOLOv8's advanced backbone structure to enhance feature extraction accuracy, and retains YOLOP's three-neck architecture to optimize multi-task processing. The improved model employs a mode loss function for segmentation tasks, enhancing generalization and improving lane detection accuracy. Experiments conducted using the BDD100k dataset demonstrated the model's effectiveness: achieving 98.8% accuracy and 27.6% IoU for lane line detection, 90.4% mIoU for drivable area segmentation, and 85.9% recall and 76.9% mAP50 for traffic object detection. This model represents a significant advancement in ADS, enhancing both the safety and reliability of autonomous vehicles. Politeknik Negeri Padang 2025 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/118822/1/118822.pdf Xie, Yumeng and Manshor, Noridayu and Husin, Nor Azura and Liu, Chengzhi (2025) Improving YoloPX using YoloP and Yolov8 for panoptic driving perception. International Journal on Informatics Visualization, 9 (1). pp. 248-257. ISSN 2549-9904; eISSN: 2549-9610 http://joiv.org/index.php/joiv/article/view/3791 10.62527/joiv.9.1.3791
spellingShingle	Xie, Yumeng Manshor, Noridayu Husin, Nor Azura Liu, Chengzhi Improving YoloPX using YoloP and Yolov8 for panoptic driving perception
title	Improving YoloPX using YoloP and Yolov8 for panoptic driving perception
title_full	Improving YoloPX using YoloP and Yolov8 for panoptic driving perception
title_fullStr	Improving YoloPX using YoloP and Yolov8 for panoptic driving perception
title_full_unstemmed	Improving YoloPX using YoloP and Yolov8 for panoptic driving perception
title_short	Improving YoloPX using YoloP and Yolov8 for panoptic driving perception
title_sort	improving yolopx using yolop and yolov8 for panoptic driving perception
url	http://psasir.upm.edu.my/id/eprint/118822/ http://psasir.upm.edu.my/id/eprint/118822/ http://psasir.upm.edu.my/id/eprint/118822/ http://psasir.upm.edu.my/id/eprint/118822/1/118822.pdf

Improving YoloPX using YoloP and Yolov8 for panoptic driving perception

Similar Items