Deep retinanet-based detection and classification of road markings by visible light camera sensors

Toan Minh Hoang, Phong Ha Nguyen, Noi Quang Truong, Young Won Lee, Kang Ryoung Park

Research output: Contribution to journalArticlepeer-review

34 Scopus citations

Abstract

Detection and classification of road markings are a prerequisite for operating autonomous vehicles. Although most studies have focused on the detection of road lane markings, the detection and classification of other road markings, such as arrows and bike markings, have not received much attention. Therefore, we propose a detection and classification method for various types of arrow markings and bike markings on the road in various complex environments using a one-stage deep convolutional neural network (CNN), called RetinaNet. We tested the proposed method in complex road scenarios with three open datasets captured by visible light camera sensors, namely the Malaga urban dataset, the Cambridge dataset, and the Daimler dataset on both a desktop computer and an NVIDIA Jetson TX2 embedded system. Experimental results obtained using the three open databases showed that the proposed RetinaNet-based method outperformed other methods for detection and classification of road markings in terms of both accuracy and processing time.

Original languageEnglish
Article number281
JournalSensors
Volume19
Issue number2
DOIs
StatePublished - 2 Jan 2019

Keywords

  • Deep CNN
  • Detection and classification of road markings
  • NVIDIA Jetson TX2
  • One-stage RetinaNet
  • Visible light camera sensor

Fingerprint

Dive into the research topics of 'Deep retinanet-based detection and classification of road markings by visible light camera sensors'. Together they form a unique fingerprint.

Cite this