Next Article in Journal
Sensitivity Analysis of the DART Model for Forest Mensuration with Airborne Laser Scanning
Previous Article in Journal
Evaluation of Hyperspectral Multitemporal Information to Improve Tree Species Identification in the Highly Diverse Atlantic Forest
Previous Article in Special Issue
Remote Sensing Big Data Classification with High Performance Distributed Deep Learning
Open AccessFeature PaperArticle

Deep TEC: Deep Transfer Learning with Ensemble Classifier for Road Extraction from UAV Imagery

1
Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore 138632, Singapore
2
Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar 382007, India
3
Department of Electronics and Electrical Engineering, Indian Institute of Technology, Guwahati 781039, India
4
Department of Aerospace Engineering, Indian Institute of Science, Bangalore 560012, India
5
Electrical and Computer Engineering, University of Iceland, 101 Reykjavik, Iceland
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(2), 245; https://doi.org/10.3390/rs12020245
Received: 16 November 2019 / Revised: 30 December 2019 / Accepted: 7 January 2020 / Published: 10 January 2020
(This article belongs to the Special Issue Analysis of Big Data in Remote Sensing)
Unmanned aerial vehicle (UAV) remote sensing has a wide area of applications and in this paper, we attempt to address one such problem—road extraction from UAV-captured RGB images. The key challenge here is to solve the road extraction problem using the UAV multiple remote sensing scene datasets that are acquired with different sensors over different locations. We aim to extract the knowledge from a dataset that is available in the literature and apply this extracted knowledge on our dataset. The paper focuses on a novel method which consists of deep TEC (deep transfer learning with ensemble classifier) for road extraction using UAV imagery. The proposed deep TEC performs road extraction on UAV imagery in two stages, namely, deep transfer learning and ensemble classifier. In the first stage, with the help of deep learning methods, namely, the conditional generative adversarial network, the cycle generative adversarial network and the fully convolutional network, the model is pre-trained on the benchmark UAV road extraction dataset that is available in the literature. With this extracted knowledge (based on the pre-trained model) the road regions are then extracted on our UAV acquired images. Finally, for the road classified images, ensemble classification is carried out. In particular, the deep TEC method has an average quality of 71%, which is 10% higher than the next best standard deep learning methods. Deep TEC also shows a higher level of performance measures such as completeness, correctness and F1 score measures. Therefore, the obtained results show that the deep TEC is efficient in extracting road networks in an urban region. View Full-Text
Keywords: UAV; remote sensing; road extraction; deep learning; transfer learning; ensemble classifier UAV; remote sensing; road extraction; deep learning; transfer learning; ensemble classifier
Show Figures

Figure 1

MDPI and ACS Style

Senthilnath, J.; Varia, N.; Dokania, A.; Anand, G.; Benediktsson, J.A. Deep TEC: Deep Transfer Learning with Ensemble Classifier for Road Extraction from UAV Imagery. Remote Sens. 2020, 12, 245.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop