DCSN: DEFORMABLE CONVOLUTIONAL SEMANTIC SEGMENTATION NEURAL NETWORK FOR NON-RIGID SCENES

Bor Sheng Huang, Chih Chung Hsu, Wo Ting Liao, Han Yi Kao, Xian Yun Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a novel semantic segmentation network for outdoor and unstructured scenarios for autonomous driving based on deformable convolution and geometric distortion pipelines. The semantic segmentation tasks for autonomous driving are generally designed for the urban scene, city-view, and highly structured scenarios, such as the CityScapes dataset, KITTI, and BDD, while rare study focuses on outskirts scenarios. Therefore, the performance of existing semantic segmentation networks on such datasets might be unreliable. To conquer this issue, a novel densely connected residual block (DCRB) with the deformable convolution is proposed to form our backbone for capturing the non-rigid feature representation. In this way, the gradient flow of our DCRB could be better back-propagated from the segmentation head, resulting in a stable training process. Second, geometric distortion augmentation is introduced in the data augmentation pipeline, simulating the possible deformation situations in real-world outdoor scenarios. The experiments are conducted that the proposed semantic segmentation network significantly outperforms the state-of-the-art methods for both Cityscapes and Outdoor scenarios.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4668-4672
Number of pages5
ISBN (Electronic)9781665405409
DOIs
Publication statusPublished - 2022
Event47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore
Duration: 2022 May 232022 May 27

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityVirtual, Online
Period22-05-2322-05-27

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'DCSN: DEFORMABLE CONVOLUTIONAL SEMANTIC SEGMENTATION NEURAL NETWORK FOR NON-RIGID SCENES'. Together they form a unique fingerprint.

Cite this