Course ID: | GEOG 8550. 3 hours. |
Course Title: | Problems in Remote Sensing of Environment II |
Course Description: | Advanced problems in photointerpretation, photogrammetry, and remote sensing for landscape and urbanscape analysis. Topics include emerging geospatial data from unmanned aerial systems (UAS or drones), airborne LiDAR, satellite sensors, mobile devices, and social media. Methods of analysis will explore machine learning/deep learning, spatio-temporal patterns, and ethics/privacy concerns. |
Oasis Title: | Prob Remote Sensing Environ II |
Prerequisite: | GEOG 4350/6350-4350L/6350L or permission of department |
Semester Course Offered: | Offered spring semester every odd-numbered year. |
Grading System: | A-F (Traditional) |
|
Course Objectives: | This seminar course focuses on advanced remote sensing techniques and integration with several fields of geographic information science (GIScience), including geographic information systems (GIS), Global Positioning Systems (GPS), spatial analysis, modeling, and photogrammetry for landscape and urbanscape analysis.
A component of this course is a discussion of geospatial ethics and privacy concerns related to the geospatial techniques we explore.
Students are exposed to current state-of-the-art geospatial techniques, with an aim to identifying techniques best suited to their personal research areas of interest. The intent of this course is to provide students with insights to new methods and technologies in remote sensing.
The first half of the course consists of student-led lectures, readings, and discussion on individual research topics. The second half of the course focuses on student projects. Working individually or in pairs, students explore new techniques in image analysis, including Deep Learning and Machine Learning. Oral and written presentations of project results demonstrate an understanding of advanced remote sensing techniques and their applications. |
Topical Outline: | Topics are updated regularly to include state-of-the-art geospatial techniques in remote sensing and may include:
Advanced methods of image classification and feature extraction for terrestrial and aquatic systems
Modeling biophysical processes with imagery
Challenges of remotely sensed imagery as Big Data
Integration of remotely sensed images, LiDAR, citizen science crowdsourced data and geolocated social media data
Remotely sensed data as input to Location-based Services and the Internet of Things
Remote sensing data of high spatial, temporal, and spectral resolution
Spectral reflectance analysis of landscapes, water bodies, and urbanscapes
3D terrain representation and tangible landscapes for geospatial decision support
Geospatial ethics and privacy issues |