One Stage Detection Network with an Auxiliary Classifier for Real-Time Road Marks Detection

Guan Ting Lin, Patrisia Sherryl Santoso, Che Tsung Lin, Chia Chi Tsai, Jiun-In Guo

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

3 Scopus citations

Abstract

We construct a robust road mark detector that achieves high accuracy with real-time processing performance (32 fps) under nVidia Titan-X GPU. We combine one stage deep learning detector with auxiliary CNN classifiers as a robust road marks detector. We found out that one stage detector not only detects multiple objects via single inference efficiently, but also remains a good accuracy in performance perspective. However, to make it better, we add an extra CNN classifier as the back part of the proposed architecture to reduce false positive and get better accuracy. The proposed detector can achieve 86.8% mAP in our in-house six-class road mark database.

Original languageEnglish
Title of host publication2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1379-1382
Number of pages4
ISBN (Electronic)9789881476852
DOIs
StatePublished - 4 Mar 2019
Event10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Honolulu, United States
Duration: 12 Nov 201815 Nov 2018

Publication series

Name2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

Conference

Conference10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
Country/TerritoryUnited States
CityHonolulu
Period12/11/1815/11/18

Keywords

  • CNNs
  • Real-time
  • Road-mark detection

Fingerprint

Dive into the research topics of 'One Stage Detection Network with an Auxiliary Classifier for Real-Time Road Marks Detection'. Together they form a unique fingerprint.

Cite this