A Review of Vision-Based Multi-Task Perception Research Methods for Autonomous Vehicles

Multi-task perception technology for autonomous driving significantly improves the ability of autonomous vehicles to understand complex traffic environments by integrating multiple perception tasks, such as traffic object detection, drivable area segmentation, and lane detection. The collaborative p...

Full description

Saved in:
Bibliographic Details
Main Authors: Hai Wang, Jiayi Li, Haoran Dong
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/8/2611
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713878424879104
author Hai Wang
Jiayi Li
Haoran Dong
author_facet Hai Wang
Jiayi Li
Haoran Dong
author_sort Hai Wang
collection DOAJ
description Multi-task perception technology for autonomous driving significantly improves the ability of autonomous vehicles to understand complex traffic environments by integrating multiple perception tasks, such as traffic object detection, drivable area segmentation, and lane detection. The collaborative processing of these tasks not only improves the overall performance of the perception system but also enhances the robustness and real-time performance of the system. In this paper, we review the research progress in the field of vision-based multi-task perception for autonomous driving and introduce the methods of traffic object detection, drivable area segmentation, and lane detection in detail. Moreover, we discuss the definition, role, and classification of multi-task learning. In addition, we analyze the design of classical network architectures and loss functions for multi-task perception, introduce commonly used datasets and evaluation metrics, and discuss the current challenges and development prospects of multi-task perception. By analyzing these contents, this paper aims to provide a comprehensive reference framework for researchers in the field of autonomous driving and encourage more research work on multi-task perception for autonomous driving.
format Article
id doaj-art-5bfad6d5ca1844de9968be8f8cbd1aa1
institution DOAJ
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-5bfad6d5ca1844de9968be8f8cbd1aa12025-08-20T03:13:51ZengMDPI AGSensors1424-82202025-04-01258261110.3390/s25082611A Review of Vision-Based Multi-Task Perception Research Methods for Autonomous VehiclesHai Wang0Jiayi Li1Haoran Dong2The School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, ChinaThe School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, ChinaThe School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, ChinaMulti-task perception technology for autonomous driving significantly improves the ability of autonomous vehicles to understand complex traffic environments by integrating multiple perception tasks, such as traffic object detection, drivable area segmentation, and lane detection. The collaborative processing of these tasks not only improves the overall performance of the perception system but also enhances the robustness and real-time performance of the system. In this paper, we review the research progress in the field of vision-based multi-task perception for autonomous driving and introduce the methods of traffic object detection, drivable area segmentation, and lane detection in detail. Moreover, we discuss the definition, role, and classification of multi-task learning. In addition, we analyze the design of classical network architectures and loss functions for multi-task perception, introduce commonly used datasets and evaluation metrics, and discuss the current challenges and development prospects of multi-task perception. By analyzing these contents, this paper aims to provide a comprehensive reference framework for researchers in the field of autonomous driving and encourage more research work on multi-task perception for autonomous driving.https://www.mdpi.com/1424-8220/25/8/2611multi-task learningautonomous drivingdetectiondrivable area segmentationdeep learning
spellingShingle Hai Wang
Jiayi Li
Haoran Dong
A Review of Vision-Based Multi-Task Perception Research Methods for Autonomous Vehicles
Sensors
multi-task learning
autonomous driving
detection
drivable area segmentation
deep learning
title A Review of Vision-Based Multi-Task Perception Research Methods for Autonomous Vehicles
title_full A Review of Vision-Based Multi-Task Perception Research Methods for Autonomous Vehicles
title_fullStr A Review of Vision-Based Multi-Task Perception Research Methods for Autonomous Vehicles
title_full_unstemmed A Review of Vision-Based Multi-Task Perception Research Methods for Autonomous Vehicles
title_short A Review of Vision-Based Multi-Task Perception Research Methods for Autonomous Vehicles
title_sort review of vision based multi task perception research methods for autonomous vehicles
topic multi-task learning
autonomous driving
detection
drivable area segmentation
deep learning
url https://www.mdpi.com/1424-8220/25/8/2611
work_keys_str_mv AT haiwang areviewofvisionbasedmultitaskperceptionresearchmethodsforautonomousvehicles
AT jiayili areviewofvisionbasedmultitaskperceptionresearchmethodsforautonomousvehicles
AT haorandong areviewofvisionbasedmultitaskperceptionresearchmethodsforautonomousvehicles
AT haiwang reviewofvisionbasedmultitaskperceptionresearchmethodsforautonomousvehicles
AT jiayili reviewofvisionbasedmultitaskperceptionresearchmethodsforautonomousvehicles
AT haorandong reviewofvisionbasedmultitaskperceptionresearchmethodsforautonomousvehicles