Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks

Shao Yuan Lo, Hsueh Ming Hang, Sheng Wei Chan, Jing Jhih Lin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Lane detection plays an important role in a self-driving vehicle. Several studies leverage a semantic segmentation network to extract robust lane features, but few of them can distinguish different types of lanes. In this paper, we focus on the problem of multi-class lane semantic segmentation. Based on the observation that the lane is a small-size and narrow-width object in a road scene image, we propose two techniques, Feature Size Selection (FSS) and Degressive Dilation Block (DD Block). The FSS allows a network to extract thin lane features using appropriate feature sizes. To acquire fine-grained spatial information, the DD Block is made of a series of dilated convolutions with degressive dilation rates. Experimental results show that the proposed techniques provide obvious improvement in accuracy, while they achieve the same or faster inference speed compared to the baseline system, and can run at real-time on high-resolution images.

Original languageEnglish
Title of host publicationIEEE 21st International Workshop on Multimedia Signal Processing, MMSP 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728118178
DOIs
StatePublished - Sep 2019
Event21st IEEE International Workshop on Multimedia Signal Processing, MMSP 2019 - Kuala Lumpur, Malaysia
Duration: 27 Sep 201929 Sep 2019

Publication series

NameIEEE 21st International Workshop on Multimedia Signal Processing, MMSP 2019

Conference

Conference21st IEEE International Workshop on Multimedia Signal Processing, MMSP 2019
CountryMalaysia
CityKuala Lumpur
Period27/09/1929/09/19

Keywords

  • multi-class lanes
  • real-time
  • self-driving
  • semantic segmentation

Fingerprint Dive into the research topics of 'Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks'. Together they form a unique fingerprint.

Cite this