Road Detection and Centerline Extraction Via Deep Recurrent Convolutional Neural Network U-Net

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

76 Scopus Citations
View graph of relations

Author(s)

  • Xiaofei Yang
  • Xutao Li
  • Yunming Ye
  • Xiaofeng Zhang
  • Xiaohui Huang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number8714072
Pages (from-to)7209-7220
Journal / PublicationIEEE Transactions on Geoscience and Remote Sensing
Volume57
Issue number9
Online published14 May 2019
Publication statusPublished - Sep 2019

Abstract

Road information extraction based on aerial images is a critical task for many applications, and it has attracted considerable attention from researchers in the field of remote sensing. The problem is mainly composed of two subtasks, namely, road detection and centerline extraction. Most of the previous studies rely on multistage-based learning methods to solve the problem. However, these approaches may suffer from the well-known problem of propagation errors. In this paper, we propose a novel deep learning model, recurrent convolution neural network U-Net (RCNN-UNet), to tackle the aforementioned problem. Our proposed RCNN-UNet has three distinct advantages. First, the end-to-end deep learning scheme eliminates the propagation errors. Second, a carefully designed RCNN unit is leveraged to build our deep learning architecture, which can better exploit the spatial context and the rich low-level visual features. Thereby, it alleviates the detection problems caused by noises, occlusions, and complex backgrounds of roads. Third, as the tasks of road detection and centerline extraction are strongly correlated, a multitask learning scheme is designed so that two predictors can be simultaneously trained to improve both effectiveness and efficiency. Extensive experiments were carried out based on two publicly available benchmark data sets, and nine state-of-the-art baselines were used in a comparative evaluation. Our experimental results demonstrate the superiority of the proposed RCNN-UNet model for both the road detection and the centerline extraction tasks.

Research Area(s)

  • Recurrent convolutional neural network (RCNN), road centerline extraction, road detection, U-Net

Citation Format(s)

Road Detection and Centerline Extraction Via Deep Recurrent Convolutional Neural Network U-Net. / Yang, Xiaofei; Li, Xutao; Ye, Yunming; Lau, Raymond Y. K.; Zhang, Xiaofeng; Huang, Xiaohui.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, No. 9, 8714072, 09.2019, p. 7209-7220.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review