EUVIMEDEUVIMED entdecken
Crossref

Deep Dual-Resolution Networks for Real-Time and Accurate Semantic Segmentation of Traffic Scenes

Huihui Pan, Yuanduo Hong, Weichao Sun, Yisong Jia

IEEE Transactions on Intelligent Transportation Systems · 2023-03 · 24 (3) · 3448-3460

DOI: 10.1109/tits.2022.3228042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2023-03. Verfasst von Huihui Pan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 526-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Post-Doctoral Science Foundation, Major Scientific and Technological Special Project of Heilongjiang Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Using light-weight architectures or reasoning on low-resolution images, recent methods realize very fast scene parsing, even running at more than 100 FPS on a single GPU. However, there is still a significant gap in performance between these real-time methods and the models based on dilation backbones. To this end, we proposed a family of deep dual-resolution networks (DDRNets) for real-time and accurate semantic segmentation, which consist of deep dual-resolution backbones and enhanced low-resolution contextual information extractors. The two deep branches and multiple bilateral fusions of backbones generate higher quality details compared to existing two-pathway methods. The enhanced contextual information extractor named Deep Aggregation Pyramid Pooling Module (DAPPM) enlarges effective receptive fields and fuses multi-scale context based on low-resolution feature maps with little time cost. Our method achieves a new state-of-the-art trade-off between accuracy and speed on both Cityscapes and CamVid dataset. For the input of full resolution, on a single 2080Ti GPU without hardware acceleration, DDRNet-23-slim yields 77.4% mIoU at 102 FPS on Cityscapes test set and 74.7% mIoU at 230 FPS on CamVid test set. With widely used test augmentation, our method is superior to most state-of-the-art models and requires much less computation. Codes and trained models are available at https://github.com/ydhongHIT/DDRNet.

Förderung

  • National Natural Science Foundation of China
  • Post-Doctoral Science Foundation
  • Major Scientific and Technological Special Project of Heilongjiang Province
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Pan, H., Hong, Y., Sun, W., & Jia, Y. (2023). Deep Dual-Resolution Networks for Real-Time and Accurate Semantic Segmentation of Traffic Scenes. IEEE Transactions on Intelligent Transportation Systems, 24(3), 3448-3460. https://doi.org/10.1109/tits.2022.3228042

Vancouver

Pan H, Hong Y, Sun W, Jia Y. Deep Dual-Resolution Networks for Real-Time and Accurate Semantic Segmentation of Traffic Scenes. IEEE Transactions on Intelligent Transportation Systems. 2023;24(3):3448-3460. doi:10.1109/tits.2022.3228042

BibTeX
@article{Pan2023,
  author = {Pan, Huihui and Hong, Yuanduo and Sun, Weichao and Jia, Yisong},
  title = {Deep Dual-Resolution Networks for Real-Time and Accurate Semantic Segmentation of Traffic Scenes},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2023},
  volume = {24},
  number = {3},
  pages = {3448--3460},
  doi = {10.1109/tits.2022.3228042}
}
Kostenlos starten →