13 February 2018 UFCN: a fully convolutional neural network for road extraction in RGB imagery acquired by remote sensing from an unmanned aerial vehicle
Author Affiliations +
Abstract
Road extraction in imagery acquired by low altitude remote sensing (LARS) carried out using an unmanned aerial vehicle (UAV) is presented. LARS is carried out using a fixed wing UAV with a high spatial resolution vision spectrum (RGB) camera as the payload. Deep learning techniques, particularly fully convolutional network (FCN), are adopted to extract roads by dense semantic segmentation. The proposed model, UFCN (U-shaped FCN) is an FCN architecture, which is comprised of a stack of convolutions followed by corresponding stack of mirrored deconvolutions with the usage of skip connections in between for preserving the local information. The limited dataset (76 images and their ground truths) is subjected to real-time data augmentation during training phase to increase the size effectively. Classification performance is evaluated using precision, recall, accuracy, F1 score, and brier score parameters. The performance is compared with support vector machine (SVM) classifier, a one-dimensional convolutional neural network (1D-CNN) model, and a standard two-dimensional CNN (2D-CNN). The UFCN model outperforms the SVM, 1D-CNN, and 2D-CNN models across all the performance parameters. Further, the prediction time of the proposed UFCN model is comparable with SVM, 1D-CNN, and 2D-CNN models.
© 2018 Society of Photo-Optical Instrumentation Engineers (SPIE)
Ramesh Kestur, Ramesh Kestur, Shariq Farooq, Shariq Farooq, Rameen Abdal, Rameen Abdal, Emad Mehraj, Emad Mehraj, Omkar Subbaramajois Narasipura, Omkar Subbaramajois Narasipura, Meenavathi Mudigere, Meenavathi Mudigere, } "UFCN: a fully convolutional neural network for road extraction in RGB imagery acquired by remote sensing from an unmanned aerial vehicle," Journal of Applied Remote Sensing 12(1), 016020 (13 February 2018). https://doi.org/10.1117/1.JRS.12.016020 . Submission: Received: 22 August 2017; Accepted: 16 January 2018
Received: 22 August 2017; Accepted: 16 January 2018; Published: 13 February 2018
JOURNAL ARTICLE
15 PAGES


SHARE
Back to Top