2019 International Symposium on Remote Sensing 17-19 April, 2019

Howard Civil Service International House, Taipei, Taiwan

No.30, Sec. 3, Xinsheng S. Rd., Da’an Dist., Taipei City.

ISRS 2019| Program

ISRS 2019

Download schedule: ISRS2019_schedule_v2 (Updated:2019/03/16)

ISPRS TC-W/8 Tutorial

Artificial Neural Network for Remote Sensing using Keras

Session: Room 5 (ISPRS TC-W/8 Tutorial)
Date/Time: 18 April (8:30-10:00)

Affiliation: Head of Geomatics Dept., NCKU; Chair of ISPRS WG V/8
E-mail: linhung@mail.ncku.edu.tw
Expertise: Digital Image Processing, Remote Sensing, 3D Point Cloud Modelling, Computer Graphics

This tutorial will guide you through how to use Keras (https://keras.io/), which is a high-level neural networks API running on top of TensorFlow (https://www.tensorflow.org/), in Python to create artificial neural networks for deep learning. This tutorial is designed for beginners, aiming to introduce you the basics of Python deep learning:
  • You will first learn what Artificial Neural Networks are.
  • Then, the tutorial will shop you step-by-step how to use Python and its libraries to understand, explore and visualize your data.
  • How to preprocess your data. You will learn how to split your data in train and test sets, and how you can standardize your data.
  • How to build up multi-layer perceptrons and convolution neural networks for classification tasks.
  • How to compile and fit the data to these models.
  • How to use your model to predict target values, and how to validate the models that you have built.
*Requirements for participants: a laptop with the functions of GPU and WIFI.

Remote Sensing Open Data and Software

Session: Room 5 (ISPRS TC-W/8 Tutorial)
Date/Time: 18 April (13:30-15:00)

Affiliation: Professor, Dept. of Civil Engineering, National Chiao Tung University
E-mail: tateo@mail.nctu.edu.tw
Expertise: Digital Photogrammetry, Remote Sensing, Lidargrammetry

This tutorial includes three hands-on topics on satellite remote sensing. The first topic uses EO browser (https://www.sentinel-hub.com/explore/eobrowser) for searching and downloading free satellite images. The second topic introduces fundamental functions from Orfeo toolbox (i.e. a library for remote sensing image processing, https://www.orfeo-toolbox.org/) for satellite image preprocessing and simple unsupervised classification. The last topic designs an automatic processing chain from Orfeo toolbox using a batch process.

*Requirements for participants: a laptop with WIFI.

Remote Sensing Applications using Google Earth Engine

Session: Room 5 (ISPRS TC-W/8 Tutorial)
Date/Time: 18 April (10:30-12:00)

Affiliation: Professor, Dept. of Civil Engineering, The University of Tokyo; Senior Policy Analyst for Energy and Environment, Cabinet Office of the Government of Japan
E-mail: wataru@iis.u-tokyo.ac.jp
Expertise: Remote Sensing Satellite Image Processing, LULC Modelling in Urban, Agricultural and Forested Regions

This hands-on training session introduces Google Earth Engine (https://earthengine.google.com/) platform for Landsat 8 image classification. Google Earth Engine is a cloud-based remote sensing data processing platform. Specifically following topics shall be covered – 1. Motivation for cloud-based processing (10 min) 2. Introduction to Google Earth Engine interface (10 min) 3. Searching for images and displaying them (10 min) 4. Collecting training features in terms of points and polygons (15 - 20 min) 5. Supervised classification and saving the result to Google Drive (15 - 20 min) 6. (If time permits) Generating NDVI band, classification accuracy.

*Requirements for participants: Laptop with WiFi, Google Earth Engine account using a GMAIL account
(Signup at - https://signup.earthengine.google.com/ ).

Remote Sensing Applications using Google Earth Engine

Session: Room 5 (ISPRS TC-W/8 Tutorial)
Date/Time: 18 April (10:30-12:00)
(Teaching Assistant)

Post-doctoral Fellow
Affiliation: Post-doctoral Fellow, The University of Tokyo
E-mail: mprakhar@iis.u-tokyo.ac.jp
Expertise: Remote Sensing, Urban Air Pollution, Urban Land-use Modelling