E-Mail Alert

Add your e-mail address to receive forthcoming issues of this journal:

Journal Browser

Journal Browser

Special Issue "Deep Learning Approaches for Urban Sensing Data Analytics"

A special issue of Remote Sensing (ISSN 2072-4292).

Deadline for manuscript submissions: 31 December 2019

Special Issue Editors

Guest Editor
Dr. Jin Xing

School of Engineering, Newcastle University, Newcastle Upon Tyne, NE1 7RU, UK
Website | E-Mail
Interests: machine learning; smart cities; remote sensing; geographic information science; geospatial cyber-infrastructure
Guest Editor
Dr. Wen Xiao

School of Engineering, Newcastle University, Newcastle Upon Tyne, NE1 7RU, UK
Website | E-Mail
Interests: 3D laser scanning; machine learning; photogrammetric computer vision; mobile/airborne mapping; multi-scale modelling
Guest Editor
Prof. Gui-Song Xia

State Key Lab. LIESMARS, Wuhan University, Wuhan 430072, China
Website | E-Mail
Interests: computer vision and photogrammetry, machine learning, mathematical modeling of images/videos/points, remote sensing image recognition
Guest Editor
Prof. Liangpei Zhang

State Key Lab. LIESMARS, Wuhan University, Wuhan 430072, China
Website | E-Mail
Interests: pattern analysis and machine learning; image processing engineering; application of remote sensing; computational Intelligence and its application in remote sensing image processing; application of remote sensing

Special Issue Information

Dear Colleagues,

Deep Learning (DL) has attracted burgeoning research interest in the past few years, due to its strength in automatic learning of hierarchical features from big data. At the same time, different types of remote sensing, such as satellite and airborne imagery and video systems, as well as ground-level mobile mapping systems (e.g., mobile laser scanning systems) have been widely used in urban environment monitoring and analytics at various scales. In addition, existing sensing infrastructures (e.g., CCTV) can be harnessed to extract new information (e.g., pedestrian/vehicle moving patterns) with the help of DL. Although DL is rapidly gaining popularity in remote sensing (Zhang et al., 2016), we are facing numerous challenges in applying it to urban sensing data, such as noisy training datasets, incompatible spatial scales, dense mixture of image objects, short update intervals, onerous hyper parameter tuning, and limited prior knowledge. All these challenges are requiring us to develop special DL approaches for urban sensing data analytics.

This Special Issue aims to provide new DL methods that could transform big urban sensing data into knowledge with limited intervention. Due to the high variety of urban sensing systems, how to develop common architectures of deep neural networks will become the major concern of this Special Issue. Topics of interest mainly include but are not limited to:

  • New deep neural network models for urban scene classification;
  • 3D deep learning for urban scene understanding;
  • New recurrent neural network algorithms for urban change detection;
  • Advanced training and testing of deep learning methods;
  • Real-time urban sensing data analytics using deep learning algorithms;
  • Generative adversarial network for remote sensing data fusion;
  • Innovative reinforcement learning algorithms for transportation management.

Dr. Jin Xing
Dr. Wen Xiao
Prof. Gui-Song Xia
Prof.  Liangpei Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Convolutional neural network
  • Recurrent neural network
  • Deep belief network
  • Remote sensing
  • Lidar data analytics
  • Smart city
  • Sensor network
  • Transfer learning

Published Papers (1 paper)

View options order results:
result details:
Displaying articles 1-1
Export citation of selected articles as:

Research

Open AccessArticle
Deep Learning Based Fossil-Fuel Power Plant Monitoring in High Resolution Remote Sensing Images: A Comparative Study
Remote Sens. 2019, 11(9), 1117; https://doi.org/10.3390/rs11091117
Received: 21 April 2019 / Revised: 29 April 2019 / Accepted: 7 May 2019 / Published: 10 May 2019
PDF Full-text (6971 KB) | HTML Full-text | XML Full-text
Abstract
The frequent hazy weather with air pollution in North China has aroused wide attention in the past few years. One of the most important pollution resource is the anthropogenic emission by fossil-fuel power plants. To relieve the pollution and assist urban environment monitoring, [...] Read more.
The frequent hazy weather with air pollution in North China has aroused wide attention in the past few years. One of the most important pollution resource is the anthropogenic emission by fossil-fuel power plants. To relieve the pollution and assist urban environment monitoring, it is necessary to continuously monitor the working status of power plants. Satellite or airborne remote sensing provides high quality data for such tasks. In this paper, we design a power plant monitoring framework based on deep learning to automatically detect the power plants and determine their working status in high resolution remote sensing images (RSIs). To this end, we collected a dataset named BUAA-FFPP60 containing RSIs of over 60 fossil-fuel power plants in the Beijing-Tianjin-Hebei region in North China, which covers about 123 km 2 of an urban area. We compared eight state-of-the-art deep learning models and comprehensively analyzed their performance on accuracy, speed, and hardware cost. Experimental results illustrate that our deep learning based framework can effectively detect the fossil-fuel power plants and determine their working status with mean average precision up to 0.8273, showing good potential for urban environment monitoring. Full article
(This article belongs to the Special Issue Deep Learning Approaches for Urban Sensing Data Analytics)
Figures

Graphical abstract

Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top