Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Feb 28;24(5):1547.
doi: 10.3390/s24051547.

A Multi-Task Network Based on Dual-Neck Structure for Autonomous Driving Perception

Guopeng Tan  1 , Chao Wang  1   2 , Zhihua Li  1   2 , Yuanbiao Zhang  1 , Ruikai Li  1
Affiliations

A Multi-Task Network Based on Dual-Neck Structure for Autonomous Driving Perception

Guopeng Tan et al. Sensors (Basel). .

Abstract

A vision-based autonomous driving perception system necessitates the accomplishment of a suite of tasks, including vehicle detection, drivable area segmentation, and lane line segmentation. In light of the limited computational resources available, multi-task learning has emerged as the preeminent methodology for crafting such systems. In this article, we introduce a highly efficient end-to-end multi-task learning model that showcases promising performance on all fronts. Our approach entails the development of a reliable feature extraction network by introducing a feature extraction module called C2SPD. Moreover, to account for the disparities among various tasks, we propose a dual-neck architecture. Finally, we present an optimized design for the decoders of each task. Our model evinces strong performance on the demanding BDD100K dataset, attaining remarkable accuracy (Acc) in vehicle detection and superior precision in drivable area segmentation (mIoU). In addition, this is the first work that can process these three visual perception tasks simultaneously in real time on an embedded device Atlas 200I A2 and maintain excellent accuracy.

Keywords: drivable area segmentation; lane line segmentation; multi-task learning; vehicle detection.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Performing real-time inference on Atlas 200I A2.
Figure 2
Figure 2
The network of YOLOP-DN.
Figure 3
Figure 3
The backbone of feature extraction.
Figure 4
Figure 4
Dual-neck structure.
Figure 5
Figure 5
Decoders structure.
Figure 6
Figure 6
Methodology flow chart.
Figure 7
Figure 7
The daytime results.
Figure 8
Figure 8
The nighttime results.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Ren S., He K., Girshick R., Sun J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2017;39:1137–1149. doi: 10.1109/TPAMI.2016.2577031. - DOI - PubMed
    1. Redmon J., Farhadi A. Yolov3: An increme-ntal improvement. arXiv. 20181804.02767
    1. Wang C.-Y., Bochkovskiy A., Liao H.-Y.M. Scaled-YOLOv4: Scaling Cross Stage Partial Network; Proceedings of the IEEE International Conference on Computer Vision; Nashville, TN, USA. 20–25 June 2021; pp. 13024–13033.
    1. Jocher G. YOLOv5 Release v6.2. 2022. [(accessed on 25 February 2024)]. Available online: https://github.com/ultralytics/yolov5/releases/tag/v6.2.
    1. Wang C.-Y., Bochkovskiy A., Liao H.-Y.M. Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv. 20222207.02696

LinkOut - more resources