Keywords

Built Environment, Natural Systems, Multispectral Sensor, Orthomosaic, Image Processing

Location

Colorado State University

Start Date

26-6-2018 5:00 PM

End Date

26-6-2018 7:00 PM

Abstract

We are conducting monthly experiments and collecting spectral data using an Unmanned Aircraft System (UAS) mounted multispectral sensor for the University of Texas at El Paso (UTEP) campus. The high-resolution (approx 7cm/px) data collected is being processed to develop orthomosaic for five bands (centers at 475nm, 560nm, 668 nm, 840nm, and 717nm) based on orthorectification for the approx 1.7 Km2 UTEP campus. The data is being processed using Python image processing libraries to assess changes in the Built Environment (BE) and the Natural Systems (NS) for the campus. So far, we have been able to detect changes in vegetation and monitor a construction project on the campus. Experiments are ongoing to use machine learning methods and assess changes to the bare soil, vegetation, roofing material, and buildings in the campus. In these paper, we will present out methods for data acquisition, storage, and processing for this massive data, lessons learned, and some results from the ongoing experiments.

Stream and Session

Stream B: (Big) Data Solutions for Planning, Management, and Operation and Environmental Systems.

B2: Hybrid modelling and innovative data analysis for integrated environmental decision support

Download
COinS
 
Jun 26th, 5:00 PM Jun 26th, 7:00 PM

Using Aerial Multispectral Remote Sensing to Detect Changes to the Built Environment and Natural Systems

Colorado State University

We are conducting monthly experiments and collecting spectral data using an Unmanned Aircraft System (UAS) mounted multispectral sensor for the University of Texas at El Paso (UTEP) campus. The high-resolution (approx 7cm/px) data collected is being processed to develop orthomosaic for five bands (centers at 475nm, 560nm, 668 nm, 840nm, and 717nm) based on orthorectification for the approx 1.7 Km2 UTEP campus. The data is being processed using Python image processing libraries to assess changes in the Built Environment (BE) and the Natural Systems (NS) for the campus. So far, we have been able to detect changes in vegetation and monitor a construction project on the campus. Experiments are ongoing to use machine learning methods and assess changes to the bare soil, vegetation, roofing material, and buildings in the campus. In these paper, we will present out methods for data acquisition, storage, and processing for this massive data, lessons learned, and some results from the ongoing experiments.