Preprint Article Version 2 This version is not peer-reviewed

Road Segmentation on Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields

Version 1 : Received: 1 June 2017 / Approved: 2 June 2017 / Online: 2 June 2017 (05:55:13 CEST)
Version 2 : Received: 3 June 2017 / Approved: 5 June 2017 / Online: 5 June 2017 (04:32:41 CEST)
Version 3 : Received: 5 June 2017 / Approved: 5 June 2017 / Online: 5 June 2017 (06:39:54 CEST)

A peer-reviewed article of this Preprint also exists.

Panboonyuen, T.; Jitkajornwanich, K.; Lawawirojwong, S.; Srestasathiern, P.; Vateekul, P. Road Segmentation of Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields. Remote Sens. 2017, 9, 680. Panboonyuen, T.; Jitkajornwanich, K.; Lawawirojwong, S.; Srestasathiern, P.; Vateekul, P. Road Segmentation of Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields. Remote Sens. 2017, 9, 680.

Journal reference: Remote Sens. 2017, 9, 680
DOI: 10.3390/rs9070680

Abstract

Object segmentation on remotely-sensed images: aerial (or very high resolution, VHS) images and satellite (or high resolution, HR) images, has been applied to many application domains, especially road extraction in which the segmented objects are served as a mandatory layer in geospatial databases. Several attempts in applying deep convolutional neural network (DCNN) to extract roads from remote sensing images have been made; however, the accuracy is still limited. In this paper, we present an enhanced DCNN framework specifically tailored for road extraction on remote sensing images by applying landscape metrics (LMs) and conditional random fields (CRFs). To improve DCNN, a modern activation function, called exponential linear unit (ELU), is employed in our network resulting in a higher number of and yet more accurate extracted roads. To further reduce falsely classified road objects, a solution based on an adoption of LMs is proposed. Finally, to sharpen the extracted roads, a CRF method is added to our framework. The experiments were conducted on Massachusetts road aerial imagery as well as THEOS satellite imagery data sets. The results showed that our proposed framework outperformed Segnet, the state-of-the-art object segmentation technique on any kinds of remote sensing imagery, in most of the cases in terms of precision, recall, and F1.

Subject Areas

deep convolutional neural networks; road segmentation; conditional random fields; landscape metrics; satellite images; aerial images; THEOS

Readers' Comments and Ratings (0)

Leave a public comment
Send a private comment to the author(s)
Rate this article
Views 0
Downloads 0
Comments 0
Metrics 0
Leave a public comment

×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.