Multi-Task Environmental Perception Methods for Autonomous Driving
Open Access
Abstract
In autonomous driving, environmental perception technology often encounters challenges such as false positives, missed detections, and low accuracy, particularly in detecting small objects and complex scenarios. Existing algorithms frequently suffer from issues like feature redundancy, insufficient contextual interaction, and inadequate information fusion, making it difficult to perform multi-task detection and segmentation efficiently. To address these challenges, this paper proposes an end-to-end multi-task environmental perception model named YOLO-Mg, designed to simultaneously perform traffic object detection, lane line detection, and drivable area segmentation. First, a multi-stage gated aggregation network (MogaNet) is employed during the feature extraction process to enhance contextual interaction by improving diversity in the channel dimension, thereby compensating for the limitations of feed-forward neural networks in contextual understanding. Second, to further improve the model’s accuracy in detecting objects of various scales, a restructured weighted bidirectional feature pyramid network (BiFPN) is introduced, optimizing cross-level information fusion and enabling the model to handle object detection at different scales more accurately. Finally, the model is equipped with one detection head and two segmentation heads to achieve efficient multi-task environmental perception, ensuring the simultaneous execution of multiple tasks. The experimental results on the BDD100K dataset demonstrate that the model achieves a mean average precision (mAP50) of 81.4% in object detection, an Intersection over Union (IoU) of 28.9% in lane detection, and a mean Intersection over Union (mIoU) of 92.6% in drivable area segmentation. The tests conducted in real-world scenarios show that the model performs effectively, significantly enhancing environmental perception in autonomous driving and laying a solid foundation for safer and more reliable autonomous driving systems.Keywords
Funding Information
- 15th Graduate Education Innovative Fund of Wuhan Institute of Technology, China
This publication has 23 references indexed in Scilit:
- Keypoint detection-based and multi-deep learning model integrated method for identifying vehicle axle load spatial-temporal distributionAdvanced Engineering Informatics, 2024
- URLLC-Awared Resource Allocation for Heterogeneous Vehicular Edge ComputingIEEE Transactions on Vehicular Technology, 2024
- A monocular-based framework for accurate identification of spatial-temporal distribution of vehicle wheel loads under occlusion scenariosEngineering Applications of Artificial Intelligence, 2024
- Real-Time Memory Efficient Multitask Learning Model for Autonomous DrivingIEEE Transactions on Intelligent Vehicles, 2023
- YOLOP: You Only Look Once for Panoptic Driving PerceptionMachine Intelligence Research, 2022
- Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- A Survey on Multi-Task LearningIEEE Transactions on Knowledge and Data Engineering, 2021
- DLT-Net: Joint Detection of Drivable Areas, Lane Lines, and Traffic ObjectsIEEE Transactions on Intelligent Transportation Systems, 2019
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- A Model of Inductive Bias LearningJournal of Artificial Intelligence Research, 2000